diff --git a/CHANGELOG.md b/CHANGELOG.md
index b1a112d43..f6e275904 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,12 +1,12 @@
# Change Log for SD.Next
-## Update for 2026-05-11
+## Update for 2026-05-10
-### Highlights for 2026-05-11
+### Highlights for 2026-05-10
*What's New?*
- Image editing models now can work with multiple image inputs!
-- Five new base models: *HiDream-O1 Image*, *JoyAI Image Edit*, *Step1X-Edit*, *VIBE Image Edit* and *UltraFlux*
+- New models: *HiDream-O1 Image*, *JoyAI Image Edit*, *Step1X-Edit*, *VIBE Image Edit* and *UltraFlux*
- Enhanced capabilities for *Anima*, *Ernie-Image*, *LTX*, *Flux.2* and *Chroma* models
- UI improvements accross the board: *Main panels*, *Gallery*, *Kanvas*, and more...
@@ -14,7 +14,7 @@ For full details, see [ChangeLog](https://github.com/vladmandic/automatic/blob/m
[ReadMe](https://github.com/vladmandic/automatic/blob/master/README.md) | [ChangeLog](https://github.com/vladmandic/automatic/blob/master/CHANGELOG.md) | [Docs](https://vladmandic.github.io/sdnext-docs/) | [WiKi](https://github.com/vladmandic/automatic/wiki) | [Discord](https://discord.com/invite/sd-next-federal-batch-inspectors-1101998836328697867) | [Sponsor](https://github.com/sponsors/vladmandic)
-### Details for 2026-05-11
+### Details for 2026-05-10
- **Models**
- [HiDream-O1-Image](https://huggingface.co/HiDream-ai/HiDream-O1-Image) pixel-level unified transformer model support
@@ -22,7 +22,6 @@ For full details, see [ChangeLog](https://github.com/vladmandic/automatic/blob/m
includes both **HiDream-O1-Image** *(base)* and **HiDream-O1-Image-Dev** *(distilled*)* variants
includes *T2I* and *I2I edit* capabilities and resolutions up to 2048px
*note*: use steps:50 for base and steps:28 for dev variants
- *note*: when using quantization, make sure that quantized matmul is disabled, otherwise quality degrades significantly
- [JoyAI Image Edit](https://huggingface.co/jdopensource/JoyAI-Image-Edit-Diffusers) image-editing model support
includes multimodal conditioning using *Qwen3-VL* with a dedicated *JoyImageEdit* diffusion transformer
*note* this is a large model at 50GB so use of agressive quantization is recommended
@@ -55,7 +54,6 @@ For full details, see [ChangeLog](https://github.com/vladmandic/automatic/blob/m
- custom **VAE** loader for all pipelines
*note*: vae still needs to be compatible with the model
- **CivitAI** downloaded thumbnails now include metadata
- - **Installer** support for `git+http` style references
- **UI**
- **Networks** using networks to load model or auto-download a reference model will now be reflected in the UI
- ability to manually reorient *input/output* panels
@@ -81,7 +79,6 @@ For full details, see [ChangeLog](https://github.com/vladmandic/automatic/blob/m
- remove obsolete `lora` stepwise and functional code, thanks @awsr
- interrupt model loading between components
- patch `rich` for cleaner exception logging
- - stricter `ruff` linting
- **Fixes**
- add missing `jquery` and `sparkline` js scripts
- save handle already decoded images
diff --git a/cli/api-samplers.py b/cli/api-samplers.py
index 7371ed0de..c63baf37c 100755
--- a/cli/api-samplers.py
+++ b/cli/api-samplers.py
@@ -4,6 +4,7 @@
get list of all samplers and details of current sampler
"""
+import sys
import logging
import urllib3
import requests
diff --git a/modules/api/endpoints.py b/modules/api/endpoints.py
index 3c96449a7..eec9f3666 100644
--- a/modules/api/endpoints.py
+++ b/modules/api/endpoints.py
@@ -361,7 +361,7 @@ def get_deletefile(file: str):
return {"deleted": f"{file}"}
except Exception as e:
log.error(f'Delete: file="{file}" error: {e}')
- raise HTTPException(status_code=500, detail=f"error deleting file {file}: {e!s}") from e
+ raise HTTPException(status_code=500, detail=f"error deleting file {file}: {str(e)}") from e
def get_deleteimage(file: str):
import os
@@ -383,7 +383,7 @@ def get_deleteimage(file: str):
return {"deleted": f"{file}"}
except Exception as e:
log.error(f'Delete: file="{file}" error: {e}')
- raise HTTPException(status_code=500, detail=f"error deleting file {file}: {e!s}") from e
+ raise HTTPException(status_code=500, detail=f"error deleting file {file}: {str(e)}") from e
def get_pnginfo(file: str):
"""Extract generation parameters from a image file path. Returns raw info string and parsed parameters dict."""
diff --git a/modules/api/middleware.py b/modules/api/middleware.py
index 4a3ef052d..db42d901d 100644
--- a/modules/api/middleware.py
+++ b/modules/api/middleware.py
@@ -44,7 +44,7 @@ def setup_middleware(app: FastAPI, cmd_opts):
client = req.scope.get('client', ('0:0.0.0', 0))[0]
token = req.cookies.get("access-token") or req.cookies.get("access-token-unsecure")
validate_request(client, endpoint)
- if cmd_opts.api_log:
+ if (cmd_opts.api_log):
if not validate_log(client, endpoint):
return res
log.info('API user={user} code={code} {prot}/{ver} {method} {endpoint} {client} {duration}'.format( # pylint: disable=consider-using-f-string, logging-format-interpolation
diff --git a/modules/api/validate.py b/modules/api/validate.py
index 3ba4f774a..1ff77be75 100644
--- a/modules/api/validate.py
+++ b/modules/api/validate.py
@@ -9,7 +9,6 @@ request_cost = {
"/run/predict": 0,
"/sdapi/v1/browser/thumb": 0,
"/sdapi/v1/network/thumb": 0,
- "/sdapi/v1/gpu-smi": 0,
"/sdapi/v1/txt2img": 5,
"/sdapi/v1/img2img": 5,
"/sdapi/v1/control": 5,
diff --git a/modules/caption/joycaption.py b/modules/caption/joycaption.py
index 905f932da..a18b46800 100644
--- a/modules/caption/joycaption.py
+++ b/modules/caption/joycaption.py
@@ -65,7 +65,7 @@ def load(repo: str | None = None):
if llava_model is None or opts.repo != repo:
opts.repo = repo
llava_model = None
- log.info(f'Caption: type=vlm model="JoyCaption" {opts!s}')
+ log.info(f'Caption: type=vlm model="JoyCaption" {str(opts)}')
processor = AutoProcessor.from_pretrained(repo, max_pixels=1024*1024, cache_dir=shared.opts.hfcache_dir)
quant_args = model_quant.create_config(module='LLM')
llava_model = LlavaForConditionalGeneration.from_pretrained(
diff --git a/modules/caption/moondream3.py b/modules/caption/moondream3.py
index c3bb8bfc7..7859f0f06 100644
--- a/modules/caption/moondream3.py
+++ b/modules/caption/moondream3.py
@@ -402,7 +402,7 @@ def predict(question: str, image: Image.Image, repo: str, model_name: str | None
except Exception as e:
from modules import errors
errors.display(e, 'Moondream3')
- return f"Error: {e!s}"
+ return f"Error: {str(e)}"
finally:
offload_aux('moondream3')
diff --git a/modules/caption/vqa.py b/modules/caption/vqa.py
index 6655a25e6..74cc3cdca 100644
--- a/modules/caption/vqa.py
+++ b/modules/caption/vqa.py
@@ -13,7 +13,7 @@ from modules import shared, devices, errors, model_quant, sd_models, sd_models_c
from modules.sd_offload_aux import register_aux, deregister_aux, move_aux_to_gpu, offload_aux
from modules.logger import log, console
from modules.caption import vqa_detection
-from modules.caption.models_def import vlm_models, vlm_prefill, vlm_prompt_mapping, vlm_prompt_placeholders, vlm_prompts_common, vlm_prompts_florence, vlm_prompts_moondream, vlm_prompts_moondream2, vlm_prompts_promptgen, get_vlm_repo
+from modules.caption.models_def import vlm_models, vlm_system, vlm_default, vlm_prefill, vlm_prompts, vlm_prompt_mapping, vlm_prompt_placeholders, vlm_prompts_common, vlm_prompts_florence, vlm_prompts_moondream, vlm_prompts_moondream2, vlm_prompts_promptgen, get_vlm_repo
# Debug logging - function-based to avoid circular import
debug_enabled = os.environ.get('SD_CAPTION_DEBUG', None) is not None
diff --git a/modules/cfgzero/cogview4_pipeline.py b/modules/cfgzero/cogview4_pipeline.py
index 07c6a8383..472c2eb72 100644
--- a/modules/cfgzero/cogview4_pipeline.py
+++ b/modules/cfgzero/cogview4_pipeline.py
@@ -191,7 +191,7 @@ class CogView4CFGZeroPipeline(DiffusionPipeline, CogView4LoraLoaderMixin):
def _get_glm_embeds(
self,
- prompt: Union[str, List[str]] | None = None,
+ prompt: Union[str, List[str]] = None,
max_sequence_length: int = 1024,
device: Optional[torch.device] = None,
dtype: Optional[torch.dtype] = None,
diff --git a/modules/cfgzero/flux_pipeline.py b/modules/cfgzero/flux_pipeline.py
index e42d7baa1..362a434e4 100644
--- a/modules/cfgzero/flux_pipeline.py
+++ b/modules/cfgzero/flux_pipeline.py
@@ -217,7 +217,7 @@ class FluxCFGZeroPipeline(
def _get_t5_prompt_embeds(
self,
- prompt: Union[str, List[str]] | None = None,
+ prompt: Union[str, List[str]] = None,
num_images_per_prompt: int = 1,
max_sequence_length: int = 512,
device: Optional[torch.device] = None,
@@ -535,7 +535,7 @@ class FluxCFGZeroPipeline(
@staticmethod
def _unpack_latents(latents, height, width, vae_scale_factor):
- batch_size, _num_patches, channels = latents.shape
+ batch_size, num_patches, channels = latents.shape
# VAE applies 8x compression on images but we must also account for packing which requires
# latent height and width to be divisible by 2.
@@ -637,9 +637,9 @@ class FluxCFGZeroPipeline(
@replace_example_docstring(EXAMPLE_DOC_STRING)
def __call__(
self,
- prompt: Union[str, List[str]] | None = None,
+ prompt: Union[str, List[str]] = None,
prompt_2: Optional[Union[str, List[str]]] = None,
- negative_prompt: Union[str, List[str]] | None = None,
+ negative_prompt: Union[str, List[str]] = None,
negative_prompt_2: Optional[Union[str, List[str]]] = None,
true_cfg_scale: float = 1.0,
height: Optional[int] = None,
diff --git a/modules/cfgzero/hidream_pipeline.py b/modules/cfgzero/hidream_pipeline.py
index edfd47d78..9eaff0878 100644
--- a/modules/cfgzero/hidream_pipeline.py
+++ b/modules/cfgzero/hidream_pipeline.py
@@ -211,7 +211,7 @@ class HiDreamImageCFGZeroPipeline(DiffusionPipeline, HiDreamImageLoraLoaderMixin
def _get_t5_prompt_embeds(
self,
- prompt: Union[str, List[str]] | None = None,
+ prompt: Union[str, List[str]] = None,
max_sequence_length: int = 128,
device: Optional[torch.device] = None,
dtype: Optional[torch.dtype] = None,
@@ -285,7 +285,7 @@ class HiDreamImageCFGZeroPipeline(DiffusionPipeline, HiDreamImageLoraLoaderMixin
def _get_llama3_prompt_embeds(
self,
- prompt: Union[str, List[str]] | None = None,
+ prompt: Union[str, List[str]] = None,
max_sequence_length: int = 128,
device: Optional[torch.device] = None,
dtype: Optional[torch.dtype] = None,
@@ -545,7 +545,7 @@ class HiDreamImageCFGZeroPipeline(DiffusionPipeline, HiDreamImageLoraLoaderMixin
@torch.no_grad()
def __call__(
self,
- prompt: Union[str, List[str]] | None = None,
+ prompt: Union[str, List[str]] = None,
prompt_2: Optional[Union[str, List[str]]] = None,
prompt_3: Optional[Union[str, List[str]]] = None,
prompt_4: Optional[Union[str, List[str]]] = None,
diff --git a/modules/cfgzero/hunyuan_t2v_pipeline.py b/modules/cfgzero/hunyuan_t2v_pipeline.py
index 0f880f576..8494b9b96 100644
--- a/modules/cfgzero/hunyuan_t2v_pipeline.py
+++ b/modules/cfgzero/hunyuan_t2v_pipeline.py
@@ -317,7 +317,7 @@ class HunyuanVideoCFGZeroPipeline(DiffusionPipeline, HunyuanVideoLoraLoaderMixin
def encode_prompt(
self,
prompt: Union[str, List[str]],
- prompt_2: Union[str, List[str]] | None = None,
+ prompt_2: Union[str, List[str]] = None,
prompt_template: Dict[str, Any] = DEFAULT_PROMPT_TEMPLATE,
num_videos_per_prompt: int = 1,
prompt_embeds: Optional[torch.Tensor] = None,
@@ -481,15 +481,15 @@ class HunyuanVideoCFGZeroPipeline(DiffusionPipeline, HunyuanVideoLoraLoaderMixin
@replace_example_docstring(EXAMPLE_DOC_STRING)
def __call__(
self,
- prompt: Union[str, List[str]] | None = None,
- prompt_2: Union[str, List[str]] | None = None,
- negative_prompt: Union[str, List[str]] | None = None,
- negative_prompt_2: Union[str, List[str]] | None = None,
+ prompt: Union[str, List[str]] = None,
+ prompt_2: Union[str, List[str]] = None,
+ negative_prompt: Union[str, List[str]] = None,
+ negative_prompt_2: Union[str, List[str]] = None,
height: int = 720,
width: int = 1280,
num_frames: int = 129,
num_inference_steps: int = 50,
- sigmas: List[float] | None = None,
+ sigmas: List[float] = None,
true_cfg_scale: float = 1.0,
guidance_scale: float = 6.0,
num_videos_per_prompt: Optional[int] = 1,
diff --git a/modules/cfgzero/sd3_pipeline.py b/modules/cfgzero/sd3_pipeline.py
index 1cae06511..946571d81 100644
--- a/modules/cfgzero/sd3_pipeline.py
+++ b/modules/cfgzero/sd3_pipeline.py
@@ -246,7 +246,7 @@ class StableDiffusion3CFGZeroPipeline(DiffusionPipeline, SD3LoraLoaderMixin, Fro
def _get_t5_prompt_embeds(
self,
- prompt: Union[str, List[str]] | None = None,
+ prompt: Union[str, List[str]] = None,
num_images_per_prompt: int = 1,
max_sequence_length: int = 256,
device: Optional[torch.device] = None,
@@ -786,7 +786,7 @@ class StableDiffusion3CFGZeroPipeline(DiffusionPipeline, SD3LoraLoaderMixin, Fro
@replace_example_docstring(EXAMPLE_DOC_STRING)
def __call__(
self,
- prompt: Union[str, List[str]] | None = None,
+ prompt: Union[str, List[str]] = None,
prompt_2: Optional[Union[str, List[str]]] = None,
prompt_3: Optional[Union[str, List[str]]] = None,
height: Optional[int] = None,
@@ -813,7 +813,7 @@ class StableDiffusion3CFGZeroPipeline(DiffusionPipeline, SD3LoraLoaderMixin, Fro
callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
callback_on_step_end_tensor_inputs: List[str] = ["latents"],
max_sequence_length: int = 256,
- skip_guidance_layers: List[int] | None = None,
+ skip_guidance_layers: List[int] = None,
skip_layer_guidance_scale: float = 2.8,
skip_layer_guidance_stop: float = 0.2,
skip_layer_guidance_start: float = 0.01,
diff --git a/modules/cfgzero/wan_t2v_pipeline.py b/modules/cfgzero/wan_t2v_pipeline.py
index 4660b2360..9cc0fa529 100644
--- a/modules/cfgzero/wan_t2v_pipeline.py
+++ b/modules/cfgzero/wan_t2v_pipeline.py
@@ -153,7 +153,7 @@ class WanCFGZeroPipeline(DiffusionPipeline, WanLoraLoaderMixin):
def _get_t5_prompt_embeds(
self,
- prompt: Union[str, List[str]] | None = None,
+ prompt: Union[str, List[str]] = None,
num_videos_per_prompt: int = 1,
max_sequence_length: int = 226,
device: Optional[torch.device] = None,
@@ -374,8 +374,8 @@ class WanCFGZeroPipeline(DiffusionPipeline, WanLoraLoaderMixin):
@replace_example_docstring(EXAMPLE_DOC_STRING)
def __call__(
self,
- prompt: Union[str, List[str]] | None = None,
- negative_prompt: Union[str, List[str]] | None = None,
+ prompt: Union[str, List[str]] = None,
+ negative_prompt: Union[str, List[str]] = None,
height: int = 480,
width: int = 832,
num_frames: int = 81,
diff --git a/modules/civitai/metadata_civitai.py b/modules/civitai/metadata_civitai.py
index 88f50a1da..258cb8143 100644
--- a/modules/civitai/metadata_civitai.py
+++ b/modules/civitai/metadata_civitai.py
@@ -93,7 +93,7 @@ def civit_update_metadata(raw: bool = False):
model.latest_name = f.get('name', '')
if model.vername == model.latest:
model.status = 'Latest version'
- elif any(map(lambda v: v in model.latest_hashes, all_hashes)): # pylint: disable=cell-var-from-loop
+ elif any(map(lambda v: v in model.latest_hashes, all_hashes)): # pylint: disable=cell-var-from-loop # noqa: C417
model.status = 'Update downloaded'
else:
model.status = 'Update available'
diff --git a/modules/control/proc/canny.py b/modules/control/proc/canny.py
index ad0113a92..1e4bb3176 100644
--- a/modules/control/proc/canny.py
+++ b/modules/control/proc/canny.py
@@ -7,7 +7,7 @@ from modules.control.util import HWC3, resize_image
class CannyDetector:
def __call__(self, input_image=None, low_threshold=100, high_threshold=200, detect_resolution=512, image_resolution=512, output_type=None, **kwargs):
if "img" in kwargs:
- warnings.warn("img is deprecated, please use `input_image=...` instead.", DeprecationWarning, stacklevel=2)
+ warnings.warn("img is deprecated, please use `input_image=...` instead.", DeprecationWarning)
input_image = kwargs.pop("img")
if input_image is None:
raise ValueError("input_image must be defined.")
diff --git a/modules/control/proc/depth_anything/util/transform.py b/modules/control/proc/depth_anything/util/transform.py
index 21bc0c146..d542fefee 100644
--- a/modules/control/proc/depth_anything/util/transform.py
+++ b/modules/control/proc/depth_anything/util/transform.py
@@ -1,4 +1,7 @@
+import random
+from PIL import Image, ImageOps, ImageFilter
import torch
+from torchvision import transforms
import torch.nn.functional as F
import numpy as np
diff --git a/modules/control/proc/depth_pro/__init__.py b/modules/control/proc/depth_pro/__init__.py
index f0f74852e..e9bd20793 100644
--- a/modules/control/proc/depth_pro/__init__.py
+++ b/modules/control/proc/depth_pro/__init__.py
@@ -16,7 +16,7 @@ class DepthProDetector:
self.processor = processor
@classmethod
- def from_pretrained(cls, pretrained_model_or_path: str = "apple/DepthPro-hf", cache_dir: str | None = None, local_files_only = False) -> "DepthProDetector":
+ def from_pretrained(cls, pretrained_model_or_path: str = "apple/DepthPro-hf", cache_dir: str = None, local_files_only = False) -> "DepthProDetector":
from transformers import AutoImageProcessor, DepthProForDepthEstimation
processor = AutoImageProcessor.from_pretrained(pretrained_model_or_path, cache_dir=cache_dir, local_files_only=local_files_only)
diff --git a/modules/control/proc/edge.py b/modules/control/proc/edge.py
index 9de932172..f91ab83bb 100644
--- a/modules/control/proc/edge.py
+++ b/modules/control/proc/edge.py
@@ -33,7 +33,7 @@ class EdgeDetector:
params.PFmode = pf
ed.setParams(params)
if "img" in kwargs:
- warnings.warn("img is deprecated, please use `input_image=...` instead.", DeprecationWarning, stacklevel=2)
+ warnings.warn("img is deprecated, please use `input_image=...` instead.", DeprecationWarning)
input_image = kwargs.pop("img")
if input_image is None:
raise ValueError("input_image must be defined.")
diff --git a/modules/control/proc/leres/leres/Resnext_torch.py b/modules/control/proc/leres/leres/Resnext_torch.py
index e45d52176..1a3dac630 100644
--- a/modules/control/proc/leres/leres/Resnext_torch.py
+++ b/modules/control/proc/leres/leres/Resnext_torch.py
@@ -5,7 +5,7 @@ import torch.nn as nn
try:
from urllib import urlretrieve
except ImportError:
- pass
+ from urllib.request import urlretrieve
__all__ = ['resnext101_32x8d']
diff --git a/modules/control/proc/leres/leres/multi_depth_model_woauxi.py b/modules/control/proc/leres/leres/multi_depth_model_woauxi.py
index bb5286f44..c1266bef1 100644
--- a/modules/control/proc/leres/leres/multi_depth_model_woauxi.py
+++ b/modules/control/proc/leres/leres/multi_depth_model_woauxi.py
@@ -1,3 +1,4 @@
+import torch
import torch.nn as nn
from . import network_auxi as network
diff --git a/modules/control/proc/leres/leres/network_auxi.py b/modules/control/proc/leres/leres/network_auxi.py
index 5e9688832..34007c9c9 100644
--- a/modules/control/proc/leres/leres/network_auxi.py
+++ b/modules/control/proc/leres/leres/network_auxi.py
@@ -384,7 +384,7 @@ class SenceUnderstand(nn.Module):
self.initial_params()
def forward(self, x):
- n, _c, h, w = x.size()
+ n, c, h, w = x.size()
x = self.conv1(x)
x = self.pool(x)
x = x.view(n, -1)
diff --git a/modules/control/proc/leres/pix2pix/options/base_options.py b/modules/control/proc/leres/pix2pix/options/base_options.py
index a48914fba..533a1e88a 100644
--- a/modules/control/proc/leres/pix2pix/options/base_options.py
+++ b/modules/control/proc/leres/pix2pix/options/base_options.py
@@ -1,8 +1,8 @@
import argparse
import os
-from ...pix2pix.util import util # noqa: TID252
+from ...pix2pix.util import util
# import torch
-from ...pix2pix import models # noqa: TID252
+from ...pix2pix import models
# import pix2pix.data
import numpy as np
diff --git a/modules/control/proc/marigold/marigold_pipeline.py b/modules/control/proc/marigold/marigold_pipeline.py
index 4ab8c0495..768c67684 100644
--- a/modules/control/proc/marigold/marigold_pipeline.py
+++ b/modules/control/proc/marigold/marigold_pipeline.py
@@ -113,7 +113,7 @@ class MarigoldPipeline(DiffusionPipeline):
batch_size: int = 0,
color_map: str = "Spectral",
show_progress_bar: bool = True,
- ensemble_kwargs: Dict | None = None,
+ ensemble_kwargs: Dict = None,
) -> MarigoldDepthOutput:
"""
Function invoked when calling the pipeline.
diff --git a/modules/control/proc/marigold/util/ensemble.py b/modules/control/proc/marigold/util/ensemble.py
index 1139b5554..710db1cc2 100644
--- a/modules/control/proc/marigold/util/ensemble.py
+++ b/modules/control/proc/marigold/util/ensemble.py
@@ -43,7 +43,7 @@ def ensemble_depths(
max_iter: int = 2,
tol: float = 1e-3,
reduction: str = "median",
- max_res: int | None = None,
+ max_res: int = None,
):
"""
To ensemble multiple affine-invariant depth images (up to scale and shift),
diff --git a/modules/control/proc/marigold/util/seed_all.py b/modules/control/proc/marigold/util/seed_all.py
index b3cdcaae5..b09006c9b 100644
--- a/modules/control/proc/marigold/util/seed_all.py
+++ b/modules/control/proc/marigold/util/seed_all.py
@@ -28,6 +28,6 @@ def seed_all(seed: int = 0):
Set random seeds of all components.
"""
random.seed(seed)
- np.random.seed(seed)
+ np.random.seed(seed) # noqa
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
diff --git a/modules/control/proc/mediapipe_face.py b/modules/control/proc/mediapipe_face.py
index a8f24533b..ceda9f857 100644
--- a/modules/control/proc/mediapipe_face.py
+++ b/modules/control/proc/mediapipe_face.py
@@ -16,6 +16,7 @@ def check_dependencies():
if not installed(pkg[1], quiet=True):
install(pkg[0], pkg[1], ignore=False)
try:
+ import mediapipe as mp # pylint: disable=unused-import
checked_ok = True
return True
except Exception as e:
diff --git a/modules/control/proc/midas/api.py b/modules/control/proc/midas/api.py
index 724700c30..c08c02cdd 100644
--- a/modules/control/proc/midas/api.py
+++ b/modules/control/proc/midas/api.py
@@ -2,6 +2,7 @@
import cv2
import os
+import torch
import torch.nn as nn
from torchvision.transforms import Compose
diff --git a/modules/control/proc/midas/midas/blocks.py b/modules/control/proc/midas/midas/blocks.py
index 9281efd1d..861687fe3 100644
--- a/modules/control/proc/midas/midas/blocks.py
+++ b/modules/control/proc/midas/midas/blocks.py
@@ -5,6 +5,7 @@ from .vit import (
_make_pretrained_vitb_rn50_384,
_make_pretrained_vitl16_384,
_make_pretrained_vitb16_384,
+ forward_vit,
)
def _make_encoder(backbone, features, use_pretrained, groups=1, expand=False, exportable=True, hooks=None, use_vit_only=False, use_readout="ignore",):
diff --git a/modules/control/proc/midas/midas/dpt_depth.py b/modules/control/proc/midas/midas/dpt_depth.py
index 81d46d4d1..600a42cd8 100644
--- a/modules/control/proc/midas/midas/dpt_depth.py
+++ b/modules/control/proc/midas/midas/dpt_depth.py
@@ -1,8 +1,10 @@
import torch
import torch.nn as nn
+import torch.nn.functional as F
from .base_model import BaseModel
from .blocks import (
+ FeatureFusionBlock,
FeatureFusionBlock_custom,
Interpolate,
_make_encoder,
diff --git a/modules/control/proc/midas/midas/midas_net_custom.py b/modules/control/proc/midas/midas/midas_net_custom.py
index 7f09df0a6..cba1bcfff 100644
--- a/modules/control/proc/midas/midas/midas_net_custom.py
+++ b/modules/control/proc/midas/midas/midas_net_custom.py
@@ -6,7 +6,7 @@ import torch
import torch.nn as nn
from .base_model import BaseModel
-from .blocks import FeatureFusionBlock_custom, Interpolate, _make_encoder
+from .blocks import FeatureFusionBlock, FeatureFusionBlock_custom, Interpolate, _make_encoder
class MidasNet_small(BaseModel):
diff --git a/modules/control/proc/midas/midas/vit.py b/modules/control/proc/midas/midas/vit.py
index 0f2aae284..f268a9fc4 100644
--- a/modules/control/proc/midas/midas/vit.py
+++ b/modules/control/proc/midas/midas/vit.py
@@ -54,7 +54,7 @@ class Transpose(nn.Module):
def forward_vit(pretrained, x):
- _b, _c, h, w = x.shape
+ b, c, h, w = x.shape
pretrained.model.forward_flex(x)
@@ -115,7 +115,7 @@ def _resize_pos_embed(self, posemb, gs_h, gs_w):
def forward_flex(self, x):
- _b, _c, h, w = x.shape
+ b, c, h, w = x.shape
pos_embed = self._resize_pos_embed(
self.pos_embed, h // self.patch_size[1], w // self.patch_size[0]
diff --git a/modules/control/proc/midas/utils.py b/modules/control/proc/midas/utils.py
index f3de55e64..9a9d3b5b6 100644
--- a/modules/control/proc/midas/utils.py
+++ b/modules/control/proc/midas/utils.py
@@ -75,7 +75,7 @@ def write_pfm(path, image, scale=1):
if len(image.shape) == 3 and image.shape[2] == 3: # color image
color = True
elif (
- len(image.shape) == 2 or (len(image.shape) == 3 and image.shape[2] == 1)
+ len(image.shape) == 2 or len(image.shape) == 3 and image.shape[2] == 1
): # greyscale
color = False
else:
@@ -86,7 +86,7 @@ def write_pfm(path, image, scale=1):
endian = image.dtype.byteorder
- if endian == "<" or (endian == "=" and sys.byteorder == "little"):
+ if endian == "<" or endian == "=" and sys.byteorder == "little":
scale = -scale
file.write("%f\n".encode() % scale)
diff --git a/modules/control/proc/mlsd/models/mbv2_mlsd_large.py b/modules/control/proc/mlsd/models/mbv2_mlsd_large.py
index 1e27a788f..39acf8dd5 100644
--- a/modules/control/proc/mlsd/models/mbv2_mlsd_large.py
+++ b/modules/control/proc/mlsd/models/mbv2_mlsd_large.py
@@ -1,3 +1,5 @@
+import os
+import sys
import torch
import torch.nn as nn
import torch.utils.model_zoo as model_zoo
diff --git a/modules/control/proc/mlsd/models/mbv2_mlsd_tiny.py b/modules/control/proc/mlsd/models/mbv2_mlsd_tiny.py
index 38ffe3e8d..4f043851e 100644
--- a/modules/control/proc/mlsd/models/mbv2_mlsd_tiny.py
+++ b/modules/control/proc/mlsd/models/mbv2_mlsd_tiny.py
@@ -1,3 +1,5 @@
+import os
+import sys
import torch
import torch.nn as nn
import torch.utils.model_zoo as model_zoo
diff --git a/modules/control/proc/mlsd/utils.py b/modules/control/proc/mlsd/utils.py
index 246a45741..ca8034370 100644
--- a/modules/control/proc/mlsd/utils.py
+++ b/modules/control/proc/mlsd/utils.py
@@ -9,6 +9,7 @@ Copyright 2021-present NAVER Corp.
Apache License v2.0
'''
+import os
import numpy as np
import cv2
import torch
@@ -21,7 +22,7 @@ def deccode_output_score_and_ptss(tpMap, topk_n = 200, ksize = 5):
center: tpMap[1, 0, :, :]
displacement: tpMap[1, 1:5, :, :]
'''
- b, _c, _h, w = tpMap.shape
+ b, c, h, w = tpMap.shape
assert b==1, 'only support bsize==1'
displacement = tpMap[:, 1:5, :, :][0]
center = tpMap[:, 0, :, :]
@@ -470,9 +471,9 @@ def pred_squares(image,
square[end_idx]
# check whether outside or inside
- _start_position, start_min, start_cover_param, start_peri_param = check_outside_inside(start_segments,
+ start_position, start_min, start_cover_param, start_peri_param = check_outside_inside(start_segments,
connect_idx)
- _end_position, end_min, end_cover_param, end_peri_param = check_outside_inside(end_segments, connect_idx)
+ end_position, end_min, end_cover_param, end_peri_param = check_outside_inside(end_segments, connect_idx)
cover += dist_segments[connect_idx] + start_cover_param * start_min + end_cover_param * end_min
perimeter += dist_segments[connect_idx] + start_peri_param * start_min + end_peri_param * end_min
diff --git a/modules/control/proc/openpose/__init__.py b/modules/control/proc/openpose/__init__.py
index 4d4c72911..746351718 100644
--- a/modules/control/proc/openpose/__init__.py
+++ b/modules/control/proc/openpose/__init__.py
@@ -194,14 +194,14 @@ class OpenposeDetector:
def __call__(self, input_image, detect_resolution=512, image_resolution=512, include_body=True, include_hand=False, include_face=False, hand_and_face=None, output_type="pil", **kwargs):
self.to(devices.device)
if hand_and_face is not None:
- warnings.warn("hand_and_face is deprecated. Use include_hand and include_face instead.", DeprecationWarning, stacklevel=2)
+ warnings.warn("hand_and_face is deprecated. Use include_hand and include_face instead.", DeprecationWarning)
include_hand = hand_and_face
include_face = hand_and_face
if "return_pil" in kwargs:
- warnings.warn("return_pil is deprecated. Use output_type instead.", DeprecationWarning, stacklevel=2)
+ warnings.warn("return_pil is deprecated. Use output_type instead.", DeprecationWarning)
output_type = "pil" if kwargs["return_pil"] else "np"
if type(output_type) is bool:
- warnings.warn("Passing `True` or `False` to `output_type` is deprecated and will raise an error in future versions", stacklevel=2)
+ warnings.warn("Passing `True` or `False` to `output_type` is deprecated and will raise an error in future versions")
if output_type:
output_type = "pil"
if not isinstance(input_image, np.ndarray):
diff --git a/modules/control/proc/openpose/face.py b/modules/control/proc/openpose/face.py
index 43e7d04cb..e8e34451c 100644
--- a/modules/control/proc/openpose/face.py
+++ b/modules/control/proc/openpose/face.py
@@ -328,7 +328,7 @@ class Face(object):
def __call__(self, face_img):
device = next(iter(self.model.parameters())).device
- H, W, _C = face_img.shape
+ H, W, C = face_img.shape
w_size = 384
x_data = torch.from_numpy(util.smart_resize(face_img, (w_size, w_size))).permute([2, 0, 1]) / 256.0 - 0.5
diff --git a/modules/control/proc/openpose/hand.py b/modules/control/proc/openpose/hand.py
index 576ad7172..78e00213e 100644
--- a/modules/control/proc/openpose/hand.py
+++ b/modules/control/proc/openpose/hand.py
@@ -32,7 +32,7 @@ class Hand(object):
wsize = 128
heatmap_avg = np.zeros((wsize, wsize, 22))
- Hr, Wr, _Cr = oriImgRaw.shape
+ Hr, Wr, Cr = oriImgRaw.shape
oriImg = cv2.GaussianBlur(oriImgRaw, (0, 0), 0.8)
diff --git a/modules/control/proc/segment_anything/__init__.py b/modules/control/proc/segment_anything/__init__.py
index a86c7d6d7..121421c18 100644
--- a/modules/control/proc/segment_anything/__init__.py
+++ b/modules/control/proc/segment_anything/__init__.py
@@ -53,7 +53,7 @@ class SamDetector:
def __call__(self, input_image: Union[np.ndarray, Image.Image]=None, detect_resolution=512, image_resolution=512, output_type="pil", **kwargs) -> Image.Image:
if "image" in kwargs:
- warnings.warn("image is deprecated, please use `input_image=...` instead.", DeprecationWarning, stacklevel=2)
+ warnings.warn("image is deprecated, please use `input_image=...` instead.", DeprecationWarning)
input_image = kwargs.pop("image")
if input_image is None:
raise ValueError("input_image must be defined.")
diff --git a/modules/control/proc/segment_anything/modeling/sam.py b/modules/control/proc/segment_anything/modeling/sam.py
index a056a7215..614fd7483 100644
--- a/modules/control/proc/segment_anything/modeling/sam.py
+++ b/modules/control/proc/segment_anything/modeling/sam.py
@@ -25,8 +25,8 @@ class Sam(nn.Module):
image_encoder: Union[ImageEncoderViT, TinyViT],
prompt_encoder: PromptEncoder,
mask_decoder: MaskDecoder,
- pixel_mean: List[float] | None = None,
- pixel_std: List[float] | None = None,
+ pixel_mean: List[float] = None,
+ pixel_std: List[float] = None,
) -> None:
"""
SAM predicts object masks from an image and input prompts.
diff --git a/modules/control/proc/segment_anything/modeling/transformer.py b/modules/control/proc/segment_anything/modeling/transformer.py
index 5d6155002..28fafea52 100644
--- a/modules/control/proc/segment_anything/modeling/transformer.py
+++ b/modules/control/proc/segment_anything/modeling/transformer.py
@@ -79,7 +79,7 @@ class TwoWayTransformer(nn.Module):
torch.Tensor: the processed image_embedding
"""
# BxCxHxW -> BxHWxC == B x N_image_tokens x C
- _bs, _c, _h, _w = image_embedding.shape
+ bs, c, h, w = image_embedding.shape
image_embedding = image_embedding.flatten(2).permute(0, 2, 1)
image_pe = image_pe.flatten(2).permute(0, 2, 1)
diff --git a/modules/control/proc/segment_anything/utils/onnx.py b/modules/control/proc/segment_anything/utils/onnx.py
index cd678117c..103867faf 100644
--- a/modules/control/proc/segment_anything/utils/onnx.py
+++ b/modules/control/proc/segment_anything/utils/onnx.py
@@ -10,7 +10,7 @@ from torch.nn import functional as F
from typing import Tuple
-from ..modeling import Sam # noqa: TID252
+from ..modeling import Sam
from .amg import calculate_stability_score
diff --git a/modules/control/proc/shuffle.py b/modules/control/proc/shuffle.py
index 01da6719c..3ee285857 100644
--- a/modules/control/proc/shuffle.py
+++ b/modules/control/proc/shuffle.py
@@ -10,10 +10,10 @@ from modules.control.util import HWC3, img2mask, make_noise_disk, resize_image
class ContentShuffleDetector:
def __call__(self, input_image, h=None, w=None, f=None, detect_resolution=512, image_resolution=512, output_type="pil", **kwargs):
if "return_pil" in kwargs:
- warnings.warn("return_pil is deprecated. Use output_type instead.", DeprecationWarning, stacklevel=2)
+ warnings.warn("return_pil is deprecated. Use output_type instead.", DeprecationWarning)
output_type = "pil" if kwargs["return_pil"] else "np"
if type(output_type) is bool:
- warnings.warn("Passing `True` or `False` to `output_type` is deprecated and will raise an error in future versions", stacklevel=2)
+ warnings.warn("Passing `True` or `False` to `output_type` is deprecated and will raise an error in future versions")
if output_type:
output_type = "pil"
@@ -49,7 +49,7 @@ class ContentShuffleDetector:
class ColorShuffleDetector:
def __call__(self, img):
H, W, C = img.shape
- F = np.random.randint(64, 384)
+ F = np.random.randint(64, 384) # noqa
A = make_noise_disk(H, W, 3, F)
B = make_noise_disk(H, W, 3, F)
C = (A + B) / 2.0
@@ -82,11 +82,11 @@ class DownSampleDetector:
def __call__(self, img, level=3, k=16.0):
h = img.astype(np.float32)
for _ in range(level):
- h += np.random.normal(loc=0.0, scale=k, size=h.shape)
+ h += np.random.normal(loc=0.0, scale=k, size=h.shape) # noqa
h = cv2.pyrDown(h)
for _ in range(level):
h = cv2.pyrUp(h)
- h += np.random.normal(loc=0.0, scale=k, size=h.shape)
+ h += np.random.normal(loc=0.0, scale=k, size=h.shape) # noqa
return h.clip(0, 255).astype(np.uint8)
diff --git a/modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/beit.py b/modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/beit.py
index cd835ebc1..ab7458704 100644
--- a/modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/beit.py
+++ b/modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/beit.py
@@ -66,7 +66,7 @@ def attention_forward(self, x, resolution, shared_rel_pos_bias: Optional[torch.T
"""
Modification of timm.models.beit.py: Attention.forward to support arbitrary window sizes.
"""
- B, N, _C = x.shape
+ B, N, C = x.shape
qkv_bias = torch.cat((self.q_bias, self.k_bias, self.v_bias)) if self.q_bias is not None else None
qkv = F.linear(input=x, weight=self.qkv.weight, bias=qkv_bias)
diff --git a/modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/utils.py b/modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/utils.py
index a58fa876b..bed17f97d 100644
--- a/modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/utils.py
+++ b/modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/utils.py
@@ -81,7 +81,7 @@ def forward_default(pretrained, x, function_name="forward_features"):
def forward_adapted_unflatten(pretrained, x, function_name="forward_features"):
- _b, _c, h, w = x.shape
+ b, c, h, w = x.shape
exec(f"glob = pretrained.model.{function_name}(x)")
diff --git a/modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/vit.py b/modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/vit.py
index ce8ea0176..71e864cdf 100644
--- a/modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/vit.py
+++ b/modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/vit.py
@@ -31,7 +31,7 @@ def _resize_pos_embed(self, posemb, gs_h, gs_w):
def forward_flex(self, x):
- _b, _c, h, w = x.shape
+ b, c, h, w = x.shape
pos_embed = self._resize_pos_embed(
self.pos_embed, h // self.patch_size[1], w // self.patch_size[0]
diff --git a/modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/blocks.py b/modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/blocks.py
index 46e10c14e..c480bbb66 100644
--- a/modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/blocks.py
+++ b/modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/blocks.py
@@ -5,6 +5,10 @@ from .backbones.beit import (
_make_pretrained_beitl16_512,
_make_pretrained_beitl16_384,
_make_pretrained_beitb16_384,
+ forward_beit,
+)
+from .backbones.swin_common import (
+ forward_swin,
)
from .backbones.swin2 import (
_make_pretrained_swin2l24_384,
@@ -16,11 +20,13 @@ from .backbones.swin import (
)
from .backbones.levit import (
_make_pretrained_levit_384,
+ forward_levit,
)
from .backbones.vit import (
_make_pretrained_vitb_rn50_384,
_make_pretrained_vitl16_384,
_make_pretrained_vitb16_384,
+ forward_vit,
)
def _make_encoder(backbone, features, use_pretrained, groups=1, expand=False, exportable=True, hooks=None,
diff --git a/modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/midas_net_custom.py b/modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/midas_net_custom.py
index 7f09df0a6..cba1bcfff 100644
--- a/modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/midas_net_custom.py
+++ b/modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/midas_net_custom.py
@@ -6,7 +6,7 @@ import torch
import torch.nn as nn
from .base_model import BaseModel
-from .blocks import FeatureFusionBlock_custom, Interpolate, _make_encoder
+from .blocks import FeatureFusionBlock, FeatureFusionBlock_custom, Interpolate, _make_encoder
class MidasNet_small(BaseModel):
diff --git a/modules/control/proc/zoe/zoedepth/models/layers/attractor.py b/modules/control/proc/zoe/zoedepth/models/layers/attractor.py
index 5e58ee348..c2fe653ed 100644
--- a/modules/control/proc/zoe/zoedepth/models/layers/attractor.py
+++ b/modules/control/proc/zoe/zoedepth/models/layers/attractor.py
@@ -100,7 +100,7 @@ class AttractorLayer(nn.Module):
A = self._net(x)
eps = 1e-3
A = A + eps
- n, _c, h, w = A.shape
+ n, c, h, w = A.shape
A = A.view(n, self.n_attractors, 2, h, w)
A_normed = A / A.sum(dim=2, keepdim=True) # n, a, 2, h, w
A_normed = A[:, :, 0, ...] # n, na, h, w
@@ -177,7 +177,7 @@ class AttractorLayerUnnormed(nn.Module):
x = x + prev_b_embedding
A = self._net(x)
- _n, _c, h, w = A.shape
+ n, c, h, w = A.shape
b_prev = nn.functional.interpolate(
b_prev, (h, w), mode='bilinear', align_corners=True)
diff --git a/modules/control/proc/zoe/zoedepth/models/layers/localbins_layers.py b/modules/control/proc/zoe/zoedepth/models/layers/localbins_layers.py
index 9af4dc463..b70ae562e 100644
--- a/modules/control/proc/zoe/zoedepth/models/layers/localbins_layers.py
+++ b/modules/control/proc/zoe/zoedepth/models/layers/localbins_layers.py
@@ -146,7 +146,7 @@ class LinearSplitter(nn.Module):
S = self._net(x)
eps = 1e-3
S = S + eps
- n, _c, h, w = S.shape
+ n, c, h, w = S.shape
S = S.view(n, self.prev_nbins, self.split_factor, h, w)
S_normed = S / S.sum(dim=2, keepdim=True) # fractional splits
diff --git a/modules/control/proc/zoe/zoedepth/models/zoedepth/zoedepth_v1.py b/modules/control/proc/zoe/zoedepth/models/zoedepth/zoedepth_v1.py
index 1dc3635b3..1705442c6 100644
--- a/modules/control/proc/zoe/zoedepth/models/zoedepth/zoedepth_v1.py
+++ b/modules/control/proc/zoe/zoedepth/models/zoedepth/zoedepth_v1.py
@@ -26,13 +26,13 @@ import itertools
import torch
import torch.nn as nn
-from ..depth_model import DepthModel # noqa: TID252
-from ..base_models.midas import MidasCore # noqa: TID252
-from ..layers.attractor import AttractorLayer, AttractorLayerUnnormed # noqa: TID252
-from ..layers.dist_layers import ConditionalLogBinomial # noqa: TID252
-from ..layers.localbins_layers import (Projector, SeedBinRegressor, # noqa: TID252
+from ..depth_model import DepthModel
+from ..base_models.midas import MidasCore
+from ..layers.attractor import AttractorLayer, AttractorLayerUnnormed
+from ..layers.dist_layers import ConditionalLogBinomial
+from ..layers.localbins_layers import (Projector, SeedBinRegressor,
SeedBinRegressorUnnormed)
-from ..model_io import load_state_from_resource # noqa: TID252
+from ..model_io import load_state_from_resource
class ZoeDepth(DepthModel):
@@ -139,7 +139,7 @@ class ZoeDepth(DepthModel):
- probs (torch.Tensor): Output probability distribution of shape (B, n_bins, H, W). Present only if return_probs is True
"""
- b, _c, h, w = x.shape
+ b, c, h, w = x.shape
# print("input shape ", x.shape)
self.orig_input_width = w
self.orig_input_height = h
diff --git a/modules/control/proc/zoe/zoedepth/models/zoedepth_nk/zoedepth_nk_v1.py b/modules/control/proc/zoe/zoedepth/models/zoedepth_nk/zoedepth_nk_v1.py
index 0b8f73074..889b1e282 100644
--- a/modules/control/proc/zoe/zoedepth/models/zoedepth_nk/zoedepth_nk_v1.py
+++ b/modules/control/proc/zoe/zoedepth/models/zoedepth_nk/zoedepth_nk_v1.py
@@ -27,14 +27,14 @@ import itertools
import torch
import torch.nn as nn
-from ..depth_model import DepthModel # noqa: TID252
-from ..base_models.midas import MidasCore # noqa: TID252
-from ..layers.attractor import AttractorLayer, AttractorLayerUnnormed # noqa: TID252
-from ..layers.dist_layers import ConditionalLogBinomial # noqa: TID252
-from ..layers.localbins_layers import (Projector, SeedBinRegressor, # noqa: TID252
+from ..depth_model import DepthModel
+from ..base_models.midas import MidasCore
+from ..layers.attractor import AttractorLayer, AttractorLayerUnnormed
+from ..layers.dist_layers import ConditionalLogBinomial
+from ..layers.localbins_layers import (Projector, SeedBinRegressor,
SeedBinRegressorUnnormed)
-from ..layers.patch_transformer import PatchTransformerEncoder # noqa: TID252
-from ..model_io import load_state_from_resource # noqa: TID252
+from ..layers.patch_transformer import PatchTransformerEncoder
+from ..model_io import load_state_from_resource
class ZoeDepthNK(DepthModel):
def __init__(self, core, bin_conf, bin_centers_type="softplus", bin_embedding_dim=128,
@@ -173,10 +173,10 @@ class ZoeDepthNK(DepthModel):
- "bin_centers": Bin centers of shape (B, N, H, W). Present only if return_final_centers is True
- "probs": Bin probabilities of shape (B, N, H, W). Present only if return_probs is True
"""
- b, _c, h, w = x.shape
+ b, c, h, w = x.shape
self.orig_input_width = w
self.orig_input_height = h
- _rel_depth, out = self.core(x, denorm=denorm, return_rel_depth=True)
+ rel_depth, out = self.core(x, denorm=denorm, return_rel_depth=True)
outconv_activation = out[0]
btlnck = out[1]
diff --git a/modules/control/units/controlnet.py b/modules/control/units/controlnet.py
index 34658cf0a..5bc231f56 100644
--- a/modules/control/units/controlnet.py
+++ b/modules/control/units/controlnet.py
@@ -5,7 +5,7 @@ from typing import Union
from diffusers import StableDiffusionPipeline, StableDiffusionXLPipeline, FluxPipeline, StableDiffusion3Pipeline, ControlNetModel
from modules.control.units import detect
from modules.shared import log, opts, cmd_opts, state, listdir
-from modules import errors, sd_models, devices
+from modules import errors, sd_models, devices, model_quant
from modules.processing import StableDiffusionProcessingControl
@@ -163,7 +163,7 @@ def find_models():
find_models()
-def api_list_models(model_type: str | None = None):
+def api_list_models(model_type: str = None):
import modules.shared
model_type = model_type or modules.shared.sd_model_type
model_list = []
@@ -215,7 +215,7 @@ def list_models(refresh=False):
class ControlNet():
- def __init__(self, model_id: str | None = None, device = None, dtype = None, load_config = None):
+ def __init__(self, model_id: str = None, device = None, dtype = None, load_config = None):
self.model: ControlNetModel = None
self.model_id: str = model_id
self.device = device
@@ -311,7 +311,7 @@ class ControlNet():
self.load_config['original_config_file '] = config_path
self.model = cls.from_single_file(model_path, config=config, **self.load_config)
- def load(self, model_id: str | None = None, force: bool = False) -> str:
+ def load(self, model_id: str = None, force: bool = False) -> str:
with load_lock:
try:
t0 = time.time()
diff --git a/modules/control/units/lite.py b/modules/control/units/lite.py
index 0c5bbf32a..107ebb0a0 100644
--- a/modules/control/units/lite.py
+++ b/modules/control/units/lite.py
@@ -63,7 +63,7 @@ def list_models(refresh=False):
class ControlLLLite():
- def __init__(self, model_id: str | None = None, device = None, dtype = None, load_config = None):
+ def __init__(self, model_id: str = None, device = None, dtype = None, load_config = None):
self.model: ControlNetLLLite = None
self.model_id: str = model_id
self.device = device
@@ -83,7 +83,7 @@ class ControlLLLite():
self.model = None
self.model_id = None
- def load(self, model_id: str | None = None, force: bool = True) -> str:
+ def load(self, model_id: str = None, force: bool = True) -> str:
with load_lock:
try:
t0 = time.time()
diff --git a/modules/control/units/t2iadapter.py b/modules/control/units/t2iadapter.py
index cb3a2da4e..5bdf99fb8 100644
--- a/modules/control/units/t2iadapter.py
+++ b/modules/control/units/t2iadapter.py
@@ -71,7 +71,7 @@ class AdapterModel(T2IAdapter):
class Adapter():
- def __init__(self, model_id: str | None = None, device = None, dtype = None, load_config = None):
+ def __init__(self, model_id: str = None, device = None, dtype = None, load_config = None):
self.model: AdapterModel = None
self.model_id: str = model_id
self.device = device
@@ -91,7 +91,7 @@ class Adapter():
self.model = None
self.model_id = None
- def load(self, model_id: str | None = None, force: bool = True) -> str:
+ def load(self, model_id: str = None, force: bool = True) -> str:
with load_lock:
try:
t0 = time.time()
diff --git a/modules/control/units/xs.py b/modules/control/units/xs.py
index 754273cdb..2d56fd7ff 100644
--- a/modules/control/units/xs.py
+++ b/modules/control/units/xs.py
@@ -59,7 +59,7 @@ def list_models(refresh=False):
class ControlNetXS():
- def __init__(self, model_id: str | None = None, device = None, dtype = None, load_config = None):
+ def __init__(self, model_id: str = None, device = None, dtype = None, load_config = None):
self.model: ControlNetXSModel = None
self.model_id: str = model_id
self.device = device
@@ -79,7 +79,7 @@ class ControlNetXS():
self.model = None
self.model_id = None
- def load(self, model_id: str | None = None, time_embedding_mix: float = 0.0, force: bool = True) -> str:
+ def load(self, model_id: str = None, time_embedding_mix: float = 0.0, force: bool = True) -> str:
with load_lock:
try:
t0 = time.time()
diff --git a/modules/control/units/xs_model.py b/modules/control/units/xs_model.py
index 9040d24a7..f4866b58d 100644
--- a/modules/control/units/xs_model.py
+++ b/modules/control/units/xs_model.py
@@ -64,9 +64,9 @@ class ControlNetXSOutput(BaseOutput):
class ControlNetConditioningEmbedding(nn.Module):
"""
Quoting from https://arxiv.org/abs/2302.05543: "Stable Diffusion uses a pre-processing method similar to VQ-GAN
- [11] to convert the entire dataset of 512 x 512 images into smaller 64 x 64 “latent images” for stabilized
- training. This requires ControlNets to convert image-based conditions to 64 x 64 feature space to match the
- convolution size. We use a tiny network E(·) of four convolution layers with 4 x 4 kernels and 2 x 2 strides
+ [11] to convert the entire dataset of 512 × 512 images into smaller 64 × 64 “latent images” for stabilized
+ training. This requires ControlNets to convert image-based conditions to 64 × 64 feature space to match the
+ convolution size. We use a tiny network E(·) of four convolution layers with 4 × 4 kernels and 2 × 2 strides
(activated by ReLU, channels are 16, 32, 64, 128, initialized with Gaussian weights, trained jointly with the full
model) to encode image-space conditions ... into feature maps ..."
"""
@@ -657,7 +657,7 @@ class ControlNetXSModel(ModelMixin, ConfigMixin):
if base_model.config.addition_embed_type == "text":
aug_emb = base_model.add_embedding(encoder_hidden_states)
elif base_model.config.addition_embed_type == "text_image":
- raise NotImplementedError
+ raise NotImplementedError()
elif base_model.config.addition_embed_type == "text_time":
# SDXL - style
if "text_embeds" not in added_cond_kwargs:
@@ -676,9 +676,9 @@ class ControlNetXSModel(ModelMixin, ConfigMixin):
add_embeds = add_embeds.to(temb.dtype)
aug_emb = base_model.add_embedding(add_embeds)
elif base_model.config.addition_embed_type == "image":
- raise NotImplementedError
+ raise NotImplementedError()
elif base_model.config.addition_embed_type == "image_hint":
- raise NotImplementedError
+ raise NotImplementedError()
temb = temb + aug_emb if aug_emb is not None else temb
diff --git a/modules/control/units/xs_pipe.py b/modules/control/units/xs_pipe.py
index e61e5f1c8..f178c11b1 100644
--- a/modules/control/units/xs_pipe.py
+++ b/modules/control/units/xs_pipe.py
@@ -518,8 +518,8 @@ class StableDiffusionXLControlNetXSPipeline(
)
if (
isinstance(self.controlnet, ControlNetXSModel)
- or (is_compiled
- and isinstance(self.controlnet._orig_mod, ControlNetXSModel))
+ or is_compiled
+ and isinstance(self.controlnet._orig_mod, ControlNetXSModel)
):
self.check_image(image, prompt, prompt_embeds)
else:
@@ -528,8 +528,8 @@ class StableDiffusionXLControlNetXSPipeline(
# Check `controlnet_conditioning_scale`
if (
isinstance(self.controlnet, ControlNetXSModel)
- or (is_compiled
- and isinstance(self.controlnet._orig_mod, ControlNetXSModel))
+ or is_compiled
+ and isinstance(self.controlnet._orig_mod, ControlNetXSModel)
):
if not isinstance(controlnet_conditioning_scale, float):
raise TypeError("For single controlnet: `controlnet_conditioning_scale` must be type `float`.")
@@ -1521,8 +1521,8 @@ class StableDiffusionControlNetXSPipeline(
)
if (
isinstance(self.controlnet, ControlNetXSModel)
- or (is_compiled
- and isinstance(self.controlnet._orig_mod, ControlNetXSModel))
+ or is_compiled
+ and isinstance(self.controlnet._orig_mod, ControlNetXSModel)
):
self.check_image(image, prompt, prompt_embeds)
else:
@@ -1531,8 +1531,8 @@ class StableDiffusionControlNetXSPipeline(
# Check `controlnet_conditioning_scale`
if (
isinstance(self.controlnet, ControlNetXSModel)
- or (is_compiled
- and isinstance(self.controlnet._orig_mod, ControlNetXSModel))
+ or is_compiled
+ and isinstance(self.controlnet._orig_mod, ControlNetXSModel)
):
if not isinstance(controlnet_conditioning_scale, float):
raise TypeError("For single controlnet: `controlnet_conditioning_scale` must be type `float`.")
diff --git a/modules/errorlimiter.py b/modules/errorlimiter.py
index 4f23ffcd7..b869a8553 100644
--- a/modules/errorlimiter.py
+++ b/modules/errorlimiter.py
@@ -2,8 +2,10 @@ from __future__ import annotations
from contextlib import contextmanager
from threading import Lock
-from typing import ClassVar
+from typing import TYPE_CHECKING, ClassVar
+if TYPE_CHECKING:
+ from collections.abc import Iterable
_instance_id = 0
_lock = Lock()
diff --git a/modules/framepack/pipeline/hunyuan_video_packed.py b/modules/framepack/pipeline/hunyuan_video_packed.py
index a5f171b5c..a852fbc10 100644
--- a/modules/framepack/pipeline/hunyuan_video_packed.py
+++ b/modules/framepack/pipeline/hunyuan_video_packed.py
@@ -832,7 +832,7 @@ class HunyuanVideoTransformer3DModelPacked(ModelMixin, ConfigMixin, PeftAdapterM
clean_latents_4x=None, clean_latent_4x_indices=None
):
hidden_states = self.gradient_checkpointing_method(self.x_embedder.proj, latents)
- B, _C, T, H, W = hidden_states.shape
+ B, C, T, H, W = hidden_states.shape
if latent_indices is None:
latent_indices = torch.arange(0, T).unsqueeze(0).expand(B, -1)
@@ -897,7 +897,7 @@ class HunyuanVideoTransformer3DModelPacked(ModelMixin, ConfigMixin, PeftAdapterM
if attention_kwargs is None:
attention_kwargs = {}
- batch_size, _num_channels, num_frames, height, width = hidden_states.shape
+ batch_size, num_channels, num_frames, height, width = hidden_states.shape
p, p_t = self.config['patch_size'], self.config['patch_size_t']
post_patch_num_frames = num_frames // p_t
post_patch_height = height // p
diff --git a/modules/framepack/pipeline/uni_pc_fm.py b/modules/framepack/pipeline/uni_pc_fm.py
index 4cc22eec0..123c2b059 100644
--- a/modules/framepack/pipeline/uni_pc_fm.py
+++ b/modules/framepack/pipeline/uni_pc_fm.py
@@ -18,7 +18,7 @@ torch_linalg_solve = None
def test_solver():
- from modules import devices
+ from modules import devices, shared
try:
a = torch.randn(50, 50).to(device=devices.device, dtype=torch.float32)
b = torch.randn(50, 2).to(device=devices.device, dtype=torch.float32)
diff --git a/modules/hidiffusion/hidiffusion.py b/modules/hidiffusion/hidiffusion.py
index fd2c4b408..b0ddf3b58 100644
--- a/modules/hidiffusion/hidiffusion.py
+++ b/modules/hidiffusion/hidiffusion.py
@@ -107,7 +107,7 @@ def make_diffusers_transformer_block(block_class: Type[torch.nn.Module]) -> Type
encoder_hidden_states: Optional[torch.FloatTensor] = None,
encoder_attention_mask: Optional[torch.FloatTensor] = None,
timestep: Optional[torch.LongTensor] = None,
- cross_attention_kwargs: Dict[str, Any] | None = None,
+ cross_attention_kwargs: Dict[str, Any] = None,
class_labels: Optional[torch.LongTensor] = None,
added_cond_kwargs: Optional[Dict[str, torch.Tensor]] = None,
) -> torch.FloatTensor:
diff --git a/modules/hidiffusion/hidiffusion_controlnet.py b/modules/hidiffusion/hidiffusion_controlnet.py
index ef7ce0457..990ecf8da 100644
--- a/modules/hidiffusion/hidiffusion_controlnet.py
+++ b/modules/hidiffusion/hidiffusion_controlnet.py
@@ -272,7 +272,7 @@ def make_diffusers_sdxl_contrtolnet_ppl(block_class):
@torch.no_grad()
def __call__(
self,
- prompt: Union[str, List[str]] | None = None,
+ prompt: Union[str, List[str]] = None,
prompt_2: Optional[Union[str, List[str]]] = None,
image: PipelineImageInput = None,
control_image: PipelineImageInput = None,
@@ -298,9 +298,9 @@ def make_diffusers_sdxl_contrtolnet_ppl(block_class):
guess_mode: bool = False,
control_guidance_start: Union[float, List[float]] = 0.0,
control_guidance_end: Union[float, List[float]] = 1.0,
- original_size: Tuple[int, int] | None = None,
+ original_size: Tuple[int, int] = None,
crops_coords_top_left: Tuple[int, int] = (0, 0),
- target_size: Tuple[int, int] | None = None,
+ target_size: Tuple[int, int] = None,
negative_original_size: Optional[Tuple[int, int]] = None,
negative_crops_coords_top_left: Tuple[int, int] = (0, 0),
negative_target_size: Optional[Tuple[int, int]] = None,
diff --git a/modules/images.py b/modules/images.py
index 1e50ec104..05c33d802 100644
--- a/modules/images.py
+++ b/modules/images.py
@@ -6,21 +6,21 @@ from modules.image.grid import Grid, image_grid, check_grid_size, get_grid_size,
from modules.image.util import draw_text, flatten
__all__ = [
- 'FilenameGenerator',
- 'Grid',
'check_grid_size',
'combine_grid',
'draw_grid_annotations',
'draw_prompt_matrix',
- 'draw_text',
- 'flatten',
- 'get_font',
+ 'FilenameGenerator',
'get_grid_size',
- 'get_next_sequence_number',
+ 'Grid',
'image_data',
'image_grid',
'read_info_from_image',
'resize_image',
'sanitize_filename_part',
'save_image',
+ 'get_font',
+ 'get_next_sequence_number',
+ 'draw_text',
+ 'flatten',
]
diff --git a/modules/intel/ipex/diffusers.py b/modules/intel/ipex/diffusers.py
index 5c36efd67..363f3a991 100644
--- a/modules/intel/ipex/diffusers.py
+++ b/modules/intel/ipex/diffusers.py
@@ -50,7 +50,7 @@ def hidream_rope(pos: torch.Tensor, dim: int, theta: int) -> torch.Tensor:
scale = torch.arange(0, dim, 2, dtype=torch.float64, device=pos.device) / dim
omega = 1.0 / (theta**scale)
- batch_size, _seq_length = pos.shape
+ batch_size, seq_length = pos.shape
out = torch.einsum("...n,d->...nd", pos, omega)
cos_out = torch.cos(out)
sin_out = torch.sin(out)
diff --git a/modules/intel/ipex/hijacks.py b/modules/intel/ipex/hijacks.py
index 6fb0714c0..e4662bfa9 100644
--- a/modules/intel/ipex/hijacks.py
+++ b/modules/intel/ipex/hijacks.py
@@ -52,7 +52,7 @@ def autocast_init(self, device_type=None, dtype=None, enabled=True, cache_enable
original_grad_scaler_init = torch.amp.grad_scaler.GradScaler.__init__
@wraps(torch.amp.grad_scaler.GradScaler.__init__)
-def GradScaler_init(self, device: str | None = None, init_scale: float = 2.0**16, growth_factor: float = 2.0, backoff_factor: float = 0.5, growth_interval: int = 2000, enabled: bool = True):
+def GradScaler_init(self, device: str = None, init_scale: float = 2.0**16, growth_factor: float = 2.0, backoff_factor: float = 0.5, growth_interval: int = 2000, enabled: bool = True):
if device is None or check_cuda(device):
return original_grad_scaler_init(self, device=return_xpu(device), init_scale=init_scale, growth_factor=growth_factor, backoff_factor=backoff_factor, growth_interval=growth_interval, enabled=enabled)
else:
diff --git a/modules/loader.py b/modules/loader.py
index b623ed32e..d57bfd3b7 100644
--- a/modules/loader.py
+++ b/modules/loader.py
@@ -75,7 +75,7 @@ except Exception:
pass
try:
- pass # pylint: disable=unused-import,ungrouped-imports
+ import torch.distributed.distributed_c10d as _c10d # pylint: disable=unused-import,ungrouped-imports
except Exception:
log.warning('Loader: torch is not built with distributed support')
@@ -96,6 +96,7 @@ warnings.filterwarnings(action="ignore", category=UserWarning, module="torchvisi
torchvision = None
try:
import torchvision # pylint: disable=W0611,C0411
+ import pytorch_lightning # pytorch_lightning should be imported after torch, but it re-enables warnings on import so import once to disable them # pylint: disable=W0611,C0411
except Exception as e:
report(f'torchvision=={torchvision.__version__ if torchvision is not None else None}', e)
@@ -126,6 +127,7 @@ if ".dev" in torch.__version__ or "+git" in torch.__version__:
timer.startup.record("torch")
try:
+ import bitsandbytes # pylint: disable=unused-import
_bnb = True
except Exception:
_bnb = False
@@ -209,9 +211,10 @@ except Exception as e:
sys.exit(1)
try:
- pass # pylint: disable=W0611,C0411
+ import pillow_jxl # pylint: disable=W0611,C0411
except Exception:
pass
+from PIL import Image # pylint: disable=W0611,C0411
timer.startup.record("pillow")
diff --git a/modules/lora/lora_load.py b/modules/lora/lora_load.py
index f4e868f1c..b3c4b0908 100644
--- a/modules/lora/lora_load.py
+++ b/modules/lora/lora_load.py
@@ -354,7 +354,7 @@ def network_load(names, te_multipliers=None, unet_multipliers=None, dyn_dims=Non
sd_model.set_adapters(adapter_names=lora_diffusers.diffuser_loaded, adapter_weights=lora_diffusers.diffuser_scales)
except Exception as e:
if str(e) not in exclude_errors:
- log.error(f'Network load: type=LoRA action=strength {e!s}')
+ log.error(f'Network load: type=LoRA action=strength {str(e)}')
if l.debug:
errors.display(e, 'LoRA')
try:
@@ -363,7 +363,7 @@ def network_load(names, te_multipliers=None, unet_multipliers=None, dyn_dims=Non
sd_model.unload_lora_weights()
l.timer.activate += time.time() - t1
except Exception as e:
- log.error(f'Network load: type=LoRA action=fuse {e!s}')
+ log.error(f'Network load: type=LoRA action=fuse {str(e)}')
if l.debug:
errors.display(e, 'LoRA')
shared.sd_model = sd_models.apply_balanced_offload(shared.sd_model, force=True, silent=True) # some layers may end up on cpu without hook
diff --git a/modules/ltx/ltx_process.py b/modules/ltx/ltx_process.py
index fef91478c..4c5bdc26c 100644
--- a/modules/ltx/ltx_process.py
+++ b/modules/ltx/ltx_process.py
@@ -149,7 +149,7 @@ def run_ltx(task_id,
extra_networks.deactivate(p)
shared.state.end()
progress.finish_task(task_id)
- yield None, f'LTX Error: {e!s}'
+ yield None, f'LTX Error: {str(e)}'
if model is None or len(model) == 0 or model == 'None':
yield from abort('Video: no model selected', ok=True)
diff --git a/modules/merging/merge_methods.py b/modules/merging/merge_methods.py
index 8bece57ab..256baeb05 100644
--- a/modules/merging/merge_methods.py
+++ b/modules/merging/merge_methods.py
@@ -4,18 +4,18 @@ import torch
from torch import Tensor
__all__ = [
+ "weighted_sum",
+ "weighted_subtraction",
+ "tensor_sum",
"add_difference",
- "distribution_crossover",
+ "sum_twice",
+ "triple_sum",
"euclidean_add_difference",
"multiply_difference",
- "similarity_add_difference",
- "sum_twice",
- "tensor_sum",
- "ties_add_difference",
"top_k_tensor_sum",
- "triple_sum",
- "weighted_subtraction",
- "weighted_sum",
+ "similarity_add_difference",
+ "distribution_crossover",
+ "ties_add_difference",
]
diff --git a/modules/onnx_impl/execution_providers.py b/modules/onnx_impl/execution_providers.py
index 82d6270d2..1b0a47be5 100644
--- a/modules/onnx_impl/execution_providers.py
+++ b/modules/onnx_impl/execution_providers.py
@@ -96,7 +96,7 @@ def get_provider() -> tuple:
def install_execution_provider(ep: ExecutionProvider):
import importlib # pylint: disable=deprecated-module
- from installer import install, uninstall
+ from installer import installed, install, uninstall
res = "
"
res += uninstall(["onnxruntime", "onnxruntime-directml", "onnxruntime-gpu", "onnxruntime-training", "onnxruntime-openvino"], quiet=True)
packages = ["onnxruntime"] # Failed to load olive: cannot import name '__version__' from 'onnxruntime'
diff --git a/modules/postprocess/swinir_model_arch.py b/modules/postprocess/swinir_model_arch.py
index 8064e0fef..4b306433d 100644
--- a/modules/postprocess/swinir_model_arch.py
+++ b/modules/postprocess/swinir_model_arch.py
@@ -238,7 +238,7 @@ class SwinTransformerBlock(nn.Module):
def forward(self, x, x_size):
H, W = x_size
- B, _L, C = x.shape
+ B, L, C = x.shape
# assert L == H * W, "input feature has wrong size"
shortcut = x
@@ -559,7 +559,7 @@ class PatchUnEmbed(nn.Module):
self.embed_dim = embed_dim
def forward(self, x, x_size):
- B, _HW, _C = x.shape
+ B, HW, C = x.shape
x = x.transpose(1, 2).view(B, self.embed_dim, x_size[0], x_size[1]) # B Ph*Pw C
return x
diff --git a/modules/postprocess/swinir_model_arch_v2.py b/modules/postprocess/swinir_model_arch_v2.py
index 00577c8ba..d61e92668 100644
--- a/modules/postprocess/swinir_model_arch_v2.py
+++ b/modules/postprocess/swinir_model_arch_v2.py
@@ -266,7 +266,7 @@ class SwinTransformerBlock(nn.Module):
def forward(self, x, x_size):
H, W = x_size
- B, _L, C = x.shape
+ B, L, C = x.shape
#assert L == H * W, "input feature has wrong size"
shortcut = x
@@ -476,7 +476,7 @@ class PatchEmbed(nn.Module):
self.norm = None
def forward(self, x):
- _B, _C, _H, _W = x.shape
+ B, C, H, W = x.shape
# FIXME look at relaxing size constraints
# assert H == self.img_size[0] and W == self.img_size[1],
# f"Input image size ({H}*{W}) doesn't match model ({self.img_size[0]}*{self.img_size[1]})."
@@ -591,7 +591,7 @@ class PatchUnEmbed(nn.Module):
self.embed_dim = embed_dim
def forward(self, x, x_size):
- B, _HW, _C = x.shape
+ B, HW, C = x.shape
x = x.transpose(1, 2).view(B, self.embed_dim, x_size[0], x_size[1]) # B Ph*Pw C
return x
diff --git a/modules/processing.py b/modules/processing.py
index 4e8b001b8..0306b20a8 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -8,6 +8,10 @@ from modules.logger import log
from modules.sd_hijack_hypertile import context_hypertile_vae, context_hypertile_unet
from modules.processing_class import ( # pylint: disable=unused-import
StableDiffusionProcessing,
+ StableDiffusionProcessingTxt2Img,
+ StableDiffusionProcessingImg2Img,
+ StableDiffusionProcessingVideo,
+ StableDiffusionProcessingControl,
)
from modules.processing_info import create_infotext
diff --git a/modules/ras/__init__.py b/modules/ras/__init__.py
index 8384812f1..717772600 100644
--- a/modules/ras/__init__.py
+++ b/modules/ras/__init__.py
@@ -19,7 +19,7 @@ def apply(pipe, p: processing.StableDiffusionProcessing):
MANAGER.width = p.width
MANAGER.height = p.height
MANAGER.error_reset_steps = [int(1*p.steps/3), int(2*p.steps/3)]
- log.info(f'RAS: scheduler={pipe.scheduler.__class__.__name__} {MANAGER!s}')
+ log.info(f'RAS: scheduler={pipe.scheduler.__class__.__name__} {str(MANAGER)}')
MANAGER.reset_cache()
MANAGER.generate_skip_token_list()
pipe.transformer.old_forward = pipe.transformer.forward
diff --git a/modules/res4lyf/res_unified_scheduler.py b/modules/res4lyf/res_unified_scheduler.py
index 2b1d1bf0a..061517f10 100644
--- a/modules/res4lyf/res_unified_scheduler.py
+++ b/modules/res4lyf/res_unified_scheduler.py
@@ -304,7 +304,7 @@ class RESUnifiedScheduler(SchedulerMixin, ConfigMixin):
return SchedulerOutput(prev_sample=x_next)
# GET COEFFICIENTS
- b, _h_val = self._get_coefficients(sigma, sigma_next)
+ b, h_val = self._get_coefficients(sigma, sigma_next)
if len(b) == 1:
res = b[0] * x0
diff --git a/modules/schedulers/scheduler_dc.py b/modules/schedulers/scheduler_dc.py
index d13fd940b..7121d4364 100644
--- a/modules/schedulers/scheduler_dc.py
+++ b/modules/schedulers/scheduler_dc.py
@@ -126,7 +126,7 @@ class DCSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
Any other scheduler that if specified, the algorithm becomes `solver_p + UniC`.
use_karras_sigmas (`bool`, *optional*, defaults to `False`):
Whether to use Karras sigmas for step sizes in the noise schedule during the sampling process. If `True`,
- the sigmas are determined according to a sequence of noise levels {sigma_i}.
+ the sigmas are determined according to a sequence of noise levels {σi}.
timestep_spacing (`str`, defaults to `"linspace"`):
The way the timesteps should be scaled. Refer to Table 2 of the [Common Diffusion Noise Schedules and
Sample Steps are Flawed](https://huggingface.co/papers/2305.08891) for more information.
@@ -449,7 +449,7 @@ class DCSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
model_output: torch.FloatTensor = None,
*args,
sample: torch.FloatTensor = None,
- order: int | None = None,
+ order: int = None,
**kwargs,
) -> torch.FloatTensor:
"""
@@ -488,12 +488,13 @@ class DCSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
)
model_output_list = self.model_outputs
+ s0 = self.timestep_list[-1]
m0 = model_output_list[-1]
assert m0 is not None
x = sample
if self.solver_p:
- raise NotImplementedError
+ raise NotImplementedError()
sigma_t, sigma_s0 = self.sigmas[self.step_index + 1], self.sigmas[self.step_index]
alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma_t)
@@ -533,7 +534,7 @@ class DCSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
elif self.config.solver_type == "bh2":
B_h = torch.expm1(hh)
else:
- raise NotImplementedError
+ raise NotImplementedError()
for i in range(1, order + 1):
R.append(torch.pow(rks, i - 1))
@@ -578,7 +579,7 @@ class DCSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
*args,
last_sample: torch.FloatTensor = None,
this_sample: torch.FloatTensor = None,
- order: int | None = None,
+ order: int = None,
**kwargs,
) -> torch.FloatTensor:
"""
@@ -668,7 +669,7 @@ class DCSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
elif self.config.solver_type == "bh2":
B_h = torch.expm1(hh)
else:
- raise NotImplementedError
+ raise NotImplementedError()
for i in range(1, order + 1):
R.append(torch.pow(rks, i - 1))
@@ -810,7 +811,7 @@ class DCSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
return loss
optimizer = torch.optim.AdamW([ratio_param], lr=0.1)
- for _ in range(self.num_iters):
+ for iter_ in range(self.num_iters):
optimizer.zero_grad()
loss = closure(ratio_param)
loss.backward()
diff --git a/modules/schedulers/scheduler_dpm_flowmatch.py b/modules/schedulers/scheduler_dpm_flowmatch.py
index 2dff1b9d4..97472f754 100644
--- a/modules/schedulers/scheduler_dpm_flowmatch.py
+++ b/modules/schedulers/scheduler_dpm_flowmatch.py
@@ -170,7 +170,7 @@ class FlowMatchDPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
from installer import install
install('torchsde==0.2.6', 'torchsde', quiet=True)
try:
- pass
+ import torchsde
except Exception as e:
raise ImportError("Failed to import torchsde. Please make sure it is installed correctly.") from e
@@ -234,7 +234,7 @@ class FlowMatchDPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
return math.exp(mu) / (math.exp(mu) + (1 / t - 1) ** sigma)
def set_timesteps(self,
- num_inference_steps: int | None = None,
+ num_inference_steps: int = None,
device: Union[str, torch.device] = None,
sigmas: Optional[List[float]] = None,
mu: Optional[float] = None,
diff --git a/modules/schedulers/scheduler_tdd.py b/modules/schedulers/scheduler_tdd.py
index f7939f012..05b49f35c 100644
--- a/modules/schedulers/scheduler_tdd.py
+++ b/modules/schedulers/scheduler_tdd.py
@@ -395,7 +395,7 @@ class TDDScheduler(DPMSolverSinglestepScheduler):
model_output_list: List[torch.FloatTensor],
*args,
sample: torch.FloatTensor = None,
- order: int | None = None,
+ order: int = None,
**kwargs,
) -> torch.FloatTensor:
timestep_list = args[0] if len(args) > 0 else kwargs.pop("timestep_list", None)
diff --git a/modules/schedulers/scheduler_unipc_flowmatch.py b/modules/schedulers/scheduler_unipc_flowmatch.py
index d981ac8bd..1adbd0799 100644
--- a/modules/schedulers/scheduler_unipc_flowmatch.py
+++ b/modules/schedulers/scheduler_unipc_flowmatch.py
@@ -54,7 +54,7 @@ class FlowUniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
Any other scheduler that if specified, the algorithm becomes `solver_p + UniC`.
use_karras_sigmas (`bool`, *optional*, defaults to `False`):
Whether to use Karras sigmas for step sizes in the noise schedule during the sampling process. If `True`,
- the sigmas are determined according to a sequence of noise levels {sigma_i}.
+ the sigmas are determined according to a sequence of noise levels {σi}.
use_exponential_sigmas (`bool`, *optional*, defaults to `False`):
Whether to use exponential sigmas for step sizes in the noise schedule during the sampling process.
timestep_spacing (`str`, defaults to `"linspace"`):
@@ -311,7 +311,7 @@ class FlowUniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
)
sigma = self.sigmas[self.step_index]
- _alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma)
+ alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma)
if self.predict_x0:
if self.config.prediction_type == "flow_prediction":
@@ -350,7 +350,7 @@ class FlowUniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
model_output: torch.Tensor,
*args,
sample: torch.Tensor = None,
- order: int | None = None, # pyright: ignore
+ order: int = None, # pyright: ignore
**kwargs,
) -> torch.Tensor:
"""
@@ -439,7 +439,7 @@ class FlowUniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
elif self.config.solver_type == "bh2":
B_h = torch.expm1(hh)
else:
- raise NotImplementedError
+ raise NotImplementedError()
for i in range(1, order + 1):
R.append(torch.pow(rks, i - 1))
@@ -487,7 +487,7 @@ class FlowUniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
*args,
last_sample: torch.Tensor = None,
this_sample: torch.Tensor = None,
- order: int | None = None, # pyright: ignore
+ order: int = None, # pyright: ignore
**kwargs,
) -> torch.Tensor:
"""
@@ -582,7 +582,7 @@ class FlowUniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
elif self.config.solver_type == "bh2":
B_h = torch.expm1(hh)
else:
- raise NotImplementedError
+ raise NotImplementedError()
for i in range(1, order + 1):
R.append(torch.pow(rks, i - 1))
diff --git a/modules/sd_models.py b/modules/sd_models.py
index c66871897..288d10ab3 100644
--- a/modules/sd_models.py
+++ b/modules/sd_models.py
@@ -15,9 +15,9 @@ from modules import timer, paths, shared, shared_items, modelloader, devices, sc
from modules.memstats import memory_stats
from modules.shared_helpers import walk_files
from modules.modeldata import model_data
-from modules.sd_checkpoint import CheckpointInfo, select_checkpoint, list_models, checkpoint_titles, get_closest_checkpoint_match # pylint: disable=unused-import
+from modules.sd_checkpoint import CheckpointInfo, select_checkpoint, list_models, checkpoint_titles, get_closest_checkpoint_match, update_model_hashes, write_metadata, checkpoints_list # pylint: disable=unused-import
from modules.sd_offload import get_module_names, disable_offload, set_diffuser_offload, apply_balanced_offload, set_accelerate # pylint: disable=unused-import
-from modules.sd_models_utils import NoWatermark, get_signature, path_to_repo, apply_function_to_model # pylint: disable=unused-import
+from modules.sd_models_utils import NoWatermark, get_signature, get_call, path_to_repo, apply_function_to_model, read_state_dict, get_state_dict_from_checkpoint # pylint: disable=unused-import
model_dir = "Stable-diffusion"
@@ -331,6 +331,7 @@ def load_diffuser_initial(diffusers_load_config, op='model'):
def load_diffuser_force(detected_model_type, checkpoint_info, diffusers_load_config, op='model'):
+ from modules import sdnq # pylint: disable=unused-import
sd_model = None
global allow_post_quant # pylint: disable=global-statement
unload_model_weights(op=op)
diff --git a/modules/sdnq/layers/__init__.py b/modules/sdnq/layers/__init__.py
index d848b8655..a7b96ce23 100644
--- a/modules/sdnq/layers/__init__.py
+++ b/modules/sdnq/layers/__init__.py
@@ -28,7 +28,7 @@ class SDNQLayer(torch.nn.Module):
return self.forward_func(self, *args, **kwargs)
def __repr__(self):
- return f"{self.__class__.__name__}(original_class={self.original_class} forward_func={self.forward_func} sdnq_dequantizer={getattr(self, 'sdnq_dequantizer', None)!r})"
+ return f"{self.__class__.__name__}(original_class={self.original_class} forward_func={self.forward_func} sdnq_dequantizer={repr(getattr(self, 'sdnq_dequantizer', None))})"
class SDNQLinear(SDNQLayer, torch.nn.Linear):
diff --git a/modules/seedvr/src/utils/color_fix.py b/modules/seedvr/src/utils/color_fix.py
index 26445ea24..efe80b67d 100644
--- a/modules/seedvr/src/utils/color_fix.py
+++ b/modules/seedvr/src/utils/color_fix.py
@@ -2,8 +2,8 @@ import torch
from PIL import Image
from torch import Tensor
from torch.nn import functional as F
+from ..common.half_precision_fixes import safe_pad_operation, safe_interpolate_operation
from torchvision.transforms import ToTensor, ToPILImage
-from modules.seedvr.src.common.half_precision_fixes import safe_pad_operation, safe_interpolate_operation
def adain_color_fix(target: Image.Image, source: Image.Image):
# Convert images to tensors
diff --git a/modules/shared.py b/modules/shared.py
index 5445ca701..1a292c3dc 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -15,17 +15,21 @@ log.debug('Initializing: shared module')
import modules.memmon
import modules.paths as paths
from modules.json_helpers import readfile # pylint: disable=W0611
-from modules.shared_helpers import listdir # pylint: disable=W0611
-from modules import errors, devices, shared_state, cmd_args, history, files_cache # pylint: disable=unused-import
+from modules.shared_helpers import listdir, req # pylint: disable=W0611
+from modules import errors, devices, shared_state, cmd_args, theme, history, files_cache # pylint: disable=unused-import
from modules.shared_defaults import get_default_modes
from modules.memstats import memory_stats # pylint: disable=unused-import
log.debug('Initializing: pipelines')
+from modules import shared_items # pylint: disable=unused-import
+from modules.caption.openclip import get_clip_models, refresh_clip_models # pylint: disable=unused-import
+from modules.caption.vqa import vlm_models, vlm_prompts, vlm_system, vlm_default # pylint: disable=unused-import
if TYPE_CHECKING:
# Behavior modified by __future__.annotations
from diffusers import DiffusionPipeline
+ from modules.shared_legacy import LegacyOption
from modules.ui_extra_networks import ExtraNetworksPage
@@ -77,6 +81,7 @@ data_path = paths.data_path
backend = Backend.DIFFUSERS
if cmd_opts.use_openvino: # override for openvino
os.environ.setdefault('PYTORCH_TRACING_MODE', 'TORCHFX')
+ from modules.intel.openvino import get_device_list as get_openvino_device_list # pylint: disable=ungrouped-imports,unused-import
elif cmd_opts.use_ipex or devices.has_xpu():
from modules.intel.ipex import ipex_init
ok, e = ipex_init()
@@ -152,6 +157,7 @@ startup_offload_mode, startup_offload_min_gpu, startup_offload_max_gpu, startup_
log.debug('Initializing: settings')
from modules import ui_definitions
+from modules.ui_definitions import OptionInfo, options_section # pylint: disable=unused-import
options_templates = ui_definitions.create_settings(cmd_opts)
from modules.shared_legacy import get_legacy_options
options_templates.update(get_legacy_options())
diff --git a/modules/sharpfin/cms.py b/modules/sharpfin/cms.py
index 30c71f902..18f88bfe3 100644
--- a/modules/sharpfin/cms.py
+++ b/modules/sharpfin/cms.py
@@ -131,7 +131,7 @@ def apply_srgb(
flags=flags
)
else:
- img = cast('Image', profileToProfile(
+ img = cast(Image, profileToProfile(
img,
profile,
_SRGB,
diff --git a/modules/teacache/teacache_hidream.py b/modules/teacache/teacache_hidream.py
index f2f05c6a4..cb3767cab 100644
--- a/modules/teacache/teacache_hidream.py
+++ b/modules/teacache/teacache_hidream.py
@@ -1,6 +1,6 @@
from typing import Any, Dict, List, Optional, Tuple
from diffusers.models.modeling_outputs import Transformer2DModelOutput
-from diffusers.utils import deprecate, USE_PEFT_BACKEND, logging, scale_lora_layers, unscale_lora_layers
+from diffusers.utils import logging, deprecate, USE_PEFT_BACKEND, logging, scale_lora_layers, unscale_lora_layers
import torch
import numpy as np
diff --git a/modules/ui_models_load.py b/modules/ui_models_load.py
index 72da42c18..9246a10d6 100644
--- a/modules/ui_models_load.py
+++ b/modules/ui_models_load.py
@@ -222,7 +222,7 @@ def create_ui(gr_status, gr_file):
if param.name == 'self' or param.name == 'args' or param.name == 'kwargs':
continue
component = Component(param)
- debug_log(f'Model component: {component!s}')
+ debug_log(f'Model component: {str(component)}')
components.append(component)
return components
diff --git a/modules/video_models/google_veo.py b/modules/video_models/google_veo.py
index 557499511..158ff05c0 100644
--- a/modules/video_models/google_veo.py
+++ b/modules/video_models/google_veo.py
@@ -6,7 +6,7 @@ import sys
sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..', '..')))
from PIL import Image
-from installer import install
+from installer import install, reload
from modules.logger import log
diff --git a/modules/video_models/video_load.py b/modules/video_models/video_load.py
index 642147e54..819706767 100644
--- a/modules/video_models/video_load.py
+++ b/modules/video_models/video_load.py
@@ -30,6 +30,7 @@ def load_custom(model_name: str):
def load_model(selected: models_def.Model):
+ from modules import sdnq # pylint: disable=unused-import
if selected is None or selected.repo is None:
return ''
global loaded_model # pylint: disable=global-statement
diff --git a/modules/video_models/video_ui.py b/modules/video_models/video_ui.py
index 5d2c71b2c..baab34bd1 100644
--- a/modules/video_models/video_ui.py
+++ b/modules/video_models/video_ui.py
@@ -64,7 +64,7 @@ def run_video(*args):
selected = get_selected(engine, model)
if not selected or engine is None or model is None or engine == 'None' or model == 'None':
return video_utils.queue_err('model not selected')
- debug(f'Video run: {selected!s}')
+ debug(f'Video run: {str(selected)}')
if selected and 'Hunyuan' in selected.name:
return video_run.generate(*args)
elif selected and 'LTX' in selected.name:
diff --git a/pipelines/bria/bria_pipeline.py b/pipelines/bria/bria_pipeline.py
index 0c4d160d7..6049e3f45 100644
--- a/pipelines/bria/bria_pipeline.py
+++ b/pipelines/bria/bria_pipeline.py
@@ -622,7 +622,7 @@ class BriaPipeline(FluxPipeline):
@staticmethod
def _unpack_latents(latents, height, width, vae_scale_factor):
- batch_size, _num_patches, channels = latents.shape
+ batch_size, num_patches, channels = latents.shape
height = height // vae_scale_factor
width = width // vae_scale_factor
diff --git a/pipelines/f_lite/f_lite.model.py b/pipelines/f_lite/f_lite.model.py
index 3adbb9b85..e56e6545b 100644
--- a/pipelines/f_lite/f_lite.model.py
+++ b/pipelines/f_lite/f_lite.model.py
@@ -233,7 +233,7 @@ class PatchEmbed(nn.Module):
self.patch_size = patch_size
def forward(self, x):
- _B, _C, _H, _W = x.shape
+ B, C, H, W = x.shape
x = self.patch_proj(x)
x = rearrange(x, "b c h w -> b (h w) c")
return x
@@ -380,7 +380,7 @@ class DiT(ModelMixin, ConfigMixin, FromOriginalModelMixin, PeftAdapterMixin): #
@apply_forward_hook
def forward(self, x, context, timesteps):
- b, _c, h, w = x.shape
+ b, c, h, w = x.shape
x = self.patch_embed(x) # b, T, d
x = torch.cat([self.register_tokens.repeat(b, 1, 1), x], 1) # b, T + N, d
diff --git a/pipelines/f_lite/model.py b/pipelines/f_lite/model.py
index 3adbb9b85..e56e6545b 100644
--- a/pipelines/f_lite/model.py
+++ b/pipelines/f_lite/model.py
@@ -233,7 +233,7 @@ class PatchEmbed(nn.Module):
self.patch_size = patch_size
def forward(self, x):
- _B, _C, _H, _W = x.shape
+ B, C, H, W = x.shape
x = self.patch_proj(x)
x = rearrange(x, "b c h w -> b (h w) c")
return x
@@ -380,7 +380,7 @@ class DiT(ModelMixin, ConfigMixin, FromOriginalModelMixin, PeftAdapterMixin): #
@apply_forward_hook
def forward(self, x, context, timesteps):
- b, _c, h, w = x.shape
+ b, c, h, w = x.shape
x = self.patch_embed(x) # b, T, d
x = torch.cat([self.register_tokens.repeat(b, 1, 1), x], 1) # b, T + N, d
diff --git a/pipelines/hidream/scheduler_flashfloweuler.py b/pipelines/hidream/scheduler_flashfloweuler.py
index 97b7fa16a..3d6f32c27 100644
--- a/pipelines/hidream/scheduler_flashfloweuler.py
+++ b/pipelines/hidream/scheduler_flashfloweuler.py
@@ -194,7 +194,7 @@ class FlashFlowMatchEulerDiscreteScheduler(SchedulerMixin, ConfigMixin):
def set_timesteps(
self,
- num_inference_steps: int | None = None,
+ num_inference_steps: int = None,
device: Union[str, torch.device] = None,
sigmas: Optional[List[float]] = None,
mu: Optional[float] = None,
diff --git a/pipelines/hidream/scheduler_flowunipc.py b/pipelines/hidream/scheduler_flowunipc.py
index a25a751dc..3b3d8ce29 100644
--- a/pipelines/hidream/scheduler_flowunipc.py
+++ b/pipelines/hidream/scheduler_flowunipc.py
@@ -53,7 +53,7 @@ class FlowUniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
Any other scheduler that if specified, the algorithm becomes `solver_p + UniC`.
use_karras_sigmas (`bool`, *optional*, defaults to `False`):
Whether to use Karras sigmas for step sizes in the noise schedule during the sampling process. If `True`,
- the sigmas are determined according to a sequence of noise levels {sigma_i}.
+ the sigmas are determined according to a sequence of noise levels {σi}.
use_exponential_sigmas (`bool`, *optional*, defaults to `False`):
Whether to use exponential sigmas for step sizes in the noise schedule during the sampling process.
timestep_spacing (`str`, defaults to `"linspace"`):
@@ -294,7 +294,7 @@ class FlowUniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
`torch.Tensor`:
The converted model output.
"""
- _ = args[0] if len(args) > 0 else kwargs.pop("timestep", None)
+ timestep = args[0] if len(args) > 0 else kwargs.pop("timestep", None)
if sample is None:
if len(args) > 1:
sample = args[1]
@@ -303,7 +303,7 @@ class FlowUniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
"missing `sample` as a required keyward argument")
sigma = self.sigmas[self.step_index]
- _alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma)
+ alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma)
if self.predict_x0:
if self.config.prediction_type == "flow_prediction":
@@ -342,7 +342,7 @@ class FlowUniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
model_output: torch.Tensor,
*args,
sample: torch.Tensor = None,
- order: int | None = None, # pyright: ignore
+ order: int = None, # pyright: ignore
**kwargs,
) -> torch.Tensor:
"""
@@ -362,7 +362,7 @@ class FlowUniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
`torch.Tensor`:
The sample tensor at the previous timestep.
"""
- _ = args[0] if len(args) > 0 else kwargs.pop(
+ prev_timestep = args[0] if len(args) > 0 else kwargs.pop(
"prev_timestep", None)
if sample is None:
if len(args) > 1:
@@ -473,7 +473,7 @@ class FlowUniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
*args,
last_sample: torch.Tensor = None,
this_sample: torch.Tensor = None,
- order: int | None = None, # pyright: ignore
+ order: int = None, # pyright: ignore
**kwargs,
) -> torch.Tensor:
"""
@@ -495,7 +495,7 @@ class FlowUniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
`torch.Tensor`:
The corrected sample tensor at the current timestep.
"""
- _ = args[0] if len(args) > 0 else kwargs.pop(
+ this_timestep = args[0] if len(args) > 0 else kwargs.pop(
"this_timestep", None)
if last_sample is None:
if len(args) > 1:
diff --git a/pipelines/lumina_dimmo/lumina_dimoo.py b/pipelines/lumina_dimmo/lumina_dimoo.py
index 44efbffef..1ce6298af 100644
--- a/pipelines/lumina_dimmo/lumina_dimoo.py
+++ b/pipelines/lumina_dimmo/lumina_dimoo.py
@@ -17,7 +17,8 @@ import sys
from abc import abstractmethod
from dataclasses import dataclass, fields
from enum import Enum
-from typing import Callable, Dict, Iterable, List, NamedTuple, Optional, Sequence, Tuple, Union, cast
+from typing import Any, Callable, Dict, Iterable, List, NamedTuple, Optional, Sequence, Tuple, Union, cast
+from accelerate import init_empty_weights
from tqdm.rich import tqdm
import numpy as np
@@ -34,6 +35,7 @@ from diffusers import DiffusionPipeline, VQModel
from diffusers.utils import BaseOutput, logging, replace_example_docstring
from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
+from diffusers.pipelines.pipeline_utils import ImagePipelineOutput
logger = logging.get_logger(__name__) # pylint: disable=invalid-name
@@ -51,7 +53,7 @@ class StrEnum(str, Enum):
return self.value
def __repr__(self) -> str:
- return f"'{self!s}'"
+ return f"'{str(self)}'"
class LayerNormType(StrEnum):
@@ -943,7 +945,7 @@ class LLaDALlamaBlock(LLaDABlock):
cat="cond",
to_compute_mask=None,
) -> Tuple[torch.Tensor, Optional[Tuple[torch.Tensor, torch.Tensor]]]:
- _B, _T, D = x.shape
+ B, T, D = x.shape
x_normed = self.attn_norm(x)
q = self.q_proj(x_normed)
@@ -1610,7 +1612,7 @@ def get_num_transfer_tokens(mask_index, steps):
def mask_by_random_topk(keep_n, probs, temperature=1.0, generator=None):
- B, _S = probs.shape
+ B, S = probs.shape
noise = gumbel_noise(probs, generator=generator)
conf = probs / temperature + noise
@@ -2047,7 +2049,7 @@ class LuminaDiMOOPipeline(DiffusionPipeline):
"""
device = next(model.parameters()).device
prompt = prompt.to(device)
- B, _P = prompt.shape
+ B, P = prompt.shape
assert B == 1, "batch>1 not supported - wrap in loop if needed"
x = prompt
@@ -2163,7 +2165,7 @@ class LuminaDiMOOPipeline(DiffusionPipeline):
device = next(model.parameters()).device
prompt = prompt.to(device)
- B, _P = prompt.shape
+ B, P = prompt.shape
assert B == 1, "batch>1 not supported - wrap in loop if needed"
x = prompt
@@ -2492,7 +2494,7 @@ class LuminaDiMOOPipeline(DiffusionPipeline):
uncon_prompt_token = self.tokenizer(uncon_prompt)["input_ids"]
if painting_mode:
- img_mask_token, _img_vis = encode_img_with_paint(
+ img_mask_token, img_vis = encode_img_with_paint(
painting_image,
vqvae=self.vqvae,
mask_h_ratio=mask_h_ratio,
@@ -2572,7 +2574,7 @@ class LuminaDiMOOPipeline(DiffusionPipeline):
processed_image = var_center_crop(image, crop_size_list=crop_size_list)
image_width, image_height = processed_image.size
- _seq_len, _newline_every, _token_grid_height, _token_grid_width = calculate_vq_params(
+ seq_len, newline_every, _token_grid_height, _token_grid_width = calculate_vq_params(
image_height, image_width, self.vae_scale_factor
)
diff --git a/pipelines/meissonic/pipeline_img2img.py b/pipelines/meissonic/pipeline_img2img.py
index 12359d42f..2aaf9d987 100644
--- a/pipelines/meissonic/pipeline_img2img.py
+++ b/pipelines/meissonic/pipeline_img2img.py
@@ -17,7 +17,7 @@ import torch
from transformers import CLIPTextModelWithProjection, CLIPTokenizer
from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
-from diffusers.models import VQModel
+from diffusers.models import UVit2DModel, VQModel
# from diffusers.schedulers import AmusedScheduler
from .scheduler import Scheduler
from diffusers.utils import replace_example_docstring
@@ -276,7 +276,7 @@ class MeissonicImg2ImgPipeline(DiffusionPipeline):
self.vqvae.float()
latents = self.vqvae.encode(image.to(dtype=self.vqvae.dtype, device=self._execution_device)).latents
- latents_bsz, _channels, latents_height, latents_width = latents.shape
+ latents_bsz, channels, latents_height, latents_width = latents.shape
latents = self.vqvae.quantize(latents)[2][2].reshape(latents_bsz, latents_height, latents_width)
latents = self.scheduler.add_noise(
latents, self.scheduler.timesteps[start_timestep_idx - 1], generator=generator
diff --git a/pipelines/meissonic/pipeline_inpaint.py b/pipelines/meissonic/pipeline_inpaint.py
index f43290d3a..aa352d9b4 100644
--- a/pipelines/meissonic/pipeline_inpaint.py
+++ b/pipelines/meissonic/pipeline_inpaint.py
@@ -289,7 +289,7 @@ class MeissonicInpaintPipeline(DiffusionPipeline):
self.vqvae.float()
latents = self.vqvae.encode(image.to(dtype=self.vqvae.dtype, device=self._execution_device)).latents
- latents_bsz, _channels, latents_height, latents_width = latents.shape
+ latents_bsz, channels, latents_height, latents_width = latents.shape
latents = self.vqvae.quantize(latents)[2][2].reshape(latents_bsz, latents_height, latents_width)
mask = self.mask_processor.preprocess(
diff --git a/pipelines/meissonic/transformer.py b/pipelines/meissonic/transformer.py
index 683e34947..c2336d323 100644
--- a/pipelines/meissonic/transformer.py
+++ b/pipelines/meissonic/transformer.py
@@ -22,7 +22,7 @@ import torch.nn.functional as F
from diffusers.configuration_utils import ConfigMixin, register_to_config
from diffusers.loaders import FromOriginalModelMixin, PeftAdapterMixin
-from diffusers.models.attention import FeedForward, SkipFFTransformerBlock
+from diffusers.models.attention import FeedForward, BasicTransformerBlock, SkipFFTransformerBlock
from diffusers.models.attention_processor import (
Attention,
AttentionProcessor,
@@ -30,7 +30,7 @@ from diffusers.models.attention_processor import (
# FusedFluxAttnProcessor2_0,
)
from diffusers.models.modeling_utils import ModelMixin
-from diffusers.models.normalization import AdaLayerNormZero, AdaLayerNormZeroSingle, GlobalResponseNorm, RMSNorm
+from diffusers.models.normalization import AdaLayerNormContinuous, AdaLayerNormZero, AdaLayerNormZeroSingle, GlobalResponseNorm, RMSNorm
from diffusers.utils import USE_PEFT_BACKEND, is_torch_version, logging, scale_lora_layers, unscale_lora_layers
from diffusers.utils.torch_utils import maybe_allow_in_graph
from diffusers.models.embeddings import CombinedTimestepGuidanceTextProjEmbeddings, CombinedTimestepTextProjEmbeddings,TimestepEmbedding, get_timestep_embedding #,FluxPosEmbed
diff --git a/pipelines/model_nextstep.py b/pipelines/model_nextstep.py
index cf993a0df..b3b962c6c 100644
--- a/pipelines/model_nextstep.py
+++ b/pipelines/model_nextstep.py
@@ -1,6 +1,7 @@
# import transformers
-from modules import sd_models # pylint: disable=unused-import
+from modules import shared, devices, sd_models, model_quant # pylint: disable=unused-import
from modules.logger import log
+from pipelines import generic # pylint: disable=unused-import
def load_nextstep(checkpoint_info, diffusers_load_config=None): # pylint: disable=unused-argument
diff --git a/pipelines/segmoe/segmoe_model.py b/pipelines/segmoe/segmoe_model.py
index d861bc776..a542c1fbb 100644
--- a/pipelines/segmoe/segmoe_model.py
+++ b/pipelines/segmoe/segmoe_model.py
@@ -1,6 +1,6 @@
import gc
from collections import OrderedDict
-from typing import Any
+from typing import Any, Dict, Callable
import os
from copy import deepcopy
from math import ceil
@@ -166,7 +166,7 @@ class SegMoEPipeline:
if not os.path.isfile("base/model.safetensors"):
os.system(
"wget -O "
- "base/model.safetensors"
+ + "base/model.safetensors"
+ self.config["base_model"]
+ " --content-disposition"
)
@@ -221,8 +221,8 @@ class SegMoEPipeline:
if not os.path.isfile(f"expert_{i}/model.safetensors"):
os.system(
f"wget {exp['source_model']} -O "
- f"expert_{i}/model.safetensors"
- " --content-disposition"
+ + f"expert_{i}/model.safetensors"
+ + " --content-disposition"
)
exp["source_model"] = f"expert_{i}/model.safetensors"
expert = DiffusionPipeline.from_single_file(
@@ -267,8 +267,8 @@ class SegMoEPipeline:
):
os.system(
f"wget {lora['source_model']} -O "
- f"expert_{i}/lora_{j}/pytorch_lora_weights.safetensors"
- " --content-disposition"
+ + f"expert_{i}/lora_{j}/pytorch_lora_weights.safetensors"
+ + " --content-disposition"
)
lora["source_model"] = f"expert_{j}/lora_{j}"
expert.load_lora_weights(lora["source_model"])
@@ -299,8 +299,8 @@ class SegMoEPipeline:
):
os.system(
f"wget {lora['source_model']} -O "
- f"lora_{i}/pytorch_lora_weights.safetensors"
- " --content-disposition"
+ + f"lora_{i}/pytorch_lora_weights.safetensors"
+ + " --content-disposition"
)
lora["source_model"] = f"lora_{i}"
self.pipe.load_lora_weights(lora["source_model"])
@@ -338,8 +338,8 @@ class SegMoEPipeline:
):
os.system(
f"wget {lora['source_model']} -O "
- f"lora_{i}/pytorch_lora_weights.safetensors"
- " --content-disposition"
+ + f"lora_{i}/pytorch_lora_weights.safetensors"
+ + " --content-disposition"
)
lora["source_model"] = f"lora_{i}"
experts[j[i]].load_lora_weights(lora["source_model"])
diff --git a/pipelines/step1x/pipeline_step1x_edit.py b/pipelines/step1x/pipeline_step1x_edit.py
index 7c4f0e228..9584cfd18 100644
--- a/pipelines/step1x/pipeline_step1x_edit.py
+++ b/pipelines/step1x/pipeline_step1x_edit.py
@@ -507,7 +507,7 @@ User Prompt:'''
@staticmethod
# Copied from diffusers.pipelines.flux.pipeline_flux.FluxPipeline._unpack_latents
def _unpack_latents(latents, height, width, vae_scale_factor):
- batch_size, _num_patches, channels = latents.shape
+ batch_size, num_patches, channels = latents.shape
# VAE applies 8x compression on images but we must also account for packing which requires
# latent height and width to be divisible by 2.
diff --git a/pipelines/step1x/transformer_step1x_edit.py b/pipelines/step1x/transformer_step1x_edit.py
index 796833b86..fe09e71c5 100644
--- a/pipelines/step1x/transformer_step1x_edit.py
+++ b/pipelines/step1x/transformer_step1x_edit.py
@@ -2,13 +2,16 @@ import inspect
from typing import Any, Dict, List, Optional, Tuple, Union
import math
+from functools import partial
+import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
from diffusers.configuration_utils import ConfigMixin, register_to_config
from diffusers.loaders import FromOriginalModelMixin, PeftAdapterMixin
-from diffusers.utils import USE_PEFT_BACKEND, logging, scale_lora_layers, unscale_lora_layers
+from diffusers.utils import USE_PEFT_BACKEND, deprecate, logging, scale_lora_layers, unscale_lora_layers
+from diffusers.utils.import_utils import is_torch_npu_available
from diffusers.utils.torch_utils import maybe_allow_in_graph
from diffusers.models.attention import AttentionMixin, AttentionModuleMixin, FeedForward
from diffusers.models.attention_dispatch import dispatch_attention_fn
@@ -527,7 +530,7 @@ class Step1XEditCrossAttnBlock(torch.nn.Module):
y: torch.Tensor=None,
):
- gate_msa, _gate_mlp = self.adaLN_modulation(c).chunk(2, dim=1)
+ gate_msa, gate_mlp = self.adaLN_modulation(c).chunk(2, dim=1)
norm_x = self.norm1(x)
norm_y = self.norm1_2(y)
diff --git a/pipelines/ultraflux/autoencoder_kl.py b/pipelines/ultraflux/autoencoder_kl.py
index f624bec4a..5a47ba970 100644
--- a/pipelines/ultraflux/autoencoder_kl.py
+++ b/pipelines/ultraflux/autoencoder_kl.py
@@ -1,6 +1,7 @@
# Code borrow from https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/autoencoders/autoencoder_kl.py
from typing import Dict, Optional, Tuple, Union
+import os
import torch
import torch.nn as nn
diff --git a/pipelines/ultraflux/pipeline_flux.py b/pipelines/ultraflux/pipeline_flux.py
index 5874ba2c8..6ceb9f7bb 100644
--- a/pipelines/ultraflux/pipeline_flux.py
+++ b/pipelines/ultraflux/pipeline_flux.py
@@ -8,7 +8,7 @@ from transformers import CLIPTextModel, CLIPTokenizer, T5EncoderModel, T5Tokeniz
from diffusers.image_processor import VaeImageProcessor
-from diffusers.loaders import FluxLoraLoaderMixin
+from diffusers.loaders import FluxLoraLoaderMixin, FromSingleFileMixin
from pipelines.ultraflux.autoencoder_kl import AutoencoderUltraFluxKL
from diffusers.models.transformers import FluxTransformer2DModel
from diffusers.schedulers import FlowMatchEulerDiscreteScheduler
@@ -430,7 +430,7 @@ class UltraFluxPipeline(DiffusionPipeline, FluxLoraLoaderMixin):
@staticmethod
def _unpack_latents(latents, height, width, vae_scale_factor):
- batch_size, _num_patches, channels = latents.shape
+ batch_size, num_patches, channels = latents.shape
height = height // vae_scale_factor
width = width // vae_scale_factor
diff --git a/pipelines/vibe/vibe_sana_editing.py b/pipelines/vibe/vibe_sana_editing.py
index aa1f6adcb..3b88bed2e 100644
--- a/pipelines/vibe/vibe_sana_editing.py
+++ b/pipelines/vibe/vibe_sana_editing.py
@@ -3,7 +3,7 @@
from typing import Any
import torch
-from diffusers import SanaTransformer2DModel
+from diffusers import ModelMixin, SanaTransformer2DModel
from diffusers.configuration_utils import register_to_config
from diffusers.models.attention_processor import Attention
from diffusers.models.embeddings import PatchEmbed, PixArtAlphaTextProjection
diff --git a/pipelines/xomni/modeling_vit.py b/pipelines/xomni/modeling_vit.py
index 260098fc8..150571c1d 100644
--- a/pipelines/xomni/modeling_vit.py
+++ b/pipelines/xomni/modeling_vit.py
@@ -39,7 +39,7 @@ def _no_grad_trunc_normal_(tensor, mean, std, a, b):
# Values are generated by using a truncated uniform distribution and
# then using the inverse CDF for the normal distribution.
# Get upper and lower cdf values
- l = norm_cdf((a - mean) / std)
+ l = norm_cdf((a - mean) / std) # noqa: E741
u = norm_cdf((b - mean) / std)
# Uniformly fill tensor with values from [l, u], then translate to
diff --git a/pyproject.toml b/pyproject.toml
index de1c4b741..eb2fd67e8 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -12,26 +12,43 @@ target-version = "py310"
exclude = [
"venv",
".git",
- ".vscode",
".ruff_cache",
- "__pycache__",
- "node_modules",
- "modules/teacache",
- "modules/sharpfin",
- "modules/seedvr/src",
- "modules/postprocess/aurasr_arch.py",
- "modules/flash_attn_triton_amd/utils.py",
- "modules/control/units/xs_pipe.py",
+ ".vscode",
+ "modules/cfgzero",
+ "modules/flash_attn_triton_amd",
+ "modules/hidiffusion",
+ "modules/intel/ipex",
"modules/pag",
- "scripts/consistory",
- "scripts/daam",
- "scripts/freescale",
- "scripts/instantir",
- "scripts/lbm",
- "scripts/pulid",
- "pipelines/xomni",
+ "modules/schedulers",
+ "modules/teacache",
+ "modules/seedvr",
+ "modules/sharpfin",
+ "modules/control/proc",
+ "modules/control/units",
+ "modules/control/units/xs_pipe.py",
+ "modules/postprocess/aurasr_arch.py",
+ "pipelines/meissonic",
"pipelines/omnigen2",
+ "pipelines/hdm",
+ "pipelines/hidream",
+ "pipelines/segmoe",
+ "pipelines/xomni",
+ "pipelines/chrono",
+ "pipelines/step1x",
+ "pipelines/vibe",
+ "pipelines/ultraflux",
+ "pipelines/lumina_dimmo",
+ "scripts/lbm",
+ "scripts/daam",
+ "scripts/xadapter",
+ "scripts/pulid",
+ "scripts/instantir",
+ "scripts/freescale",
+ "scripts/consistory",
+ "extensions-builtin/Lora",
"extensions-builtin/sd-extension-chainner/nodes",
+ "extensions-builtin/sd-webui-agent-scheduler",
+ "extensions-builtin/sdnext-modernui/node_modules",
]
[tool.ruff.lint]
@@ -64,23 +81,25 @@ ignore = [
"B008", # Do not perform function call in argument defaults
"B905", # Strict zip() usage
"C408", # Unnecessary `dict` call
- "C417", # Unnecessary `map` comprehension
- "C420", # Unnecessary `dict` comprehension
+ "C420", # Unnecessary dict comprehension for iterable; use `dict.fromkeys` instead
"E402", # Module level import not at top of file
"E501", # Line too long
- "E721", # Do not compare types
- "E731", # Do not assign a `lambda` expression
+ "E721", # Do not compare types, use `isinstance()`
+ "E731", # Do not assign a `lambda` expression, use a `def`
"E741", # Ambiguous variable name
- "F401", # Import unused
- "I001", # Import block un-sorted
+ "EXE001", # file with shebang is not marked executable
+ "F401", # Imported by unused
+ "I001", # Import block is un-sorted or un-formatted
"NPY002", # replace legacy random
"RUF005", # Consider iterable unpacking
"RUF008", # Do not use mutable default values for dataclass
+ "RUF010", # Use explicit conversion flag
"RUF012", # Mutable class attributes
"RUF015", # Prefer `next(...)` over single element slice
"RUF022", # All is not sorted
"RUF046", # Value being cast to `int` is already an integer
"RUF051", # Prefer pop over del
+ "RUF059", # Unpacked variables are not used
]
fixable = ["ALL"]
unfixable = []
@@ -110,11 +129,12 @@ main.fail-on=""
main.fail-under=10
main.ignore="CVS"
main.ignore-paths=[
+ "venv",
+ "node_modules",
"__pycache__",
".git",
".ruff_cache",
".vscode",
- "venv",
"modules/apg",
"modules/cfgzero",
"modules/control/proc",
@@ -122,55 +142,58 @@ main.ignore-paths=[
"modules/dml",
"modules/face",
"modules/flash_attn_triton_amd",
- "modules/framepack/pipeline",
"modules/ggml",
"modules/hidiffusion",
"modules/hijack/ddpm_edit.py",
"modules/intel",
"modules/intel/ipex",
+ "modules/framepack/pipeline",
"modules/onnx_impl",
"modules/pag",
"modules/postprocess/aurasr_arch.py",
"modules/prompt_parser_xhinker.py",
"modules/ras",
- "modules/res4lyf",
- "modules/rife",
- "modules/schedulers",
"modules/seedvr",
"modules/sharpfin",
+ "modules/rife",
+ "modules/schedulers",
"modules/taesd",
"modules/teacache",
"modules/todo",
- "node_modules",
+ "modules/res4lyf",
"pipelines/bria",
- "pipelines/chrono",
- "pipelines/f_lite",
"pipelines/flex2",
- "pipelines/hdm",
+ "pipelines/f_lite",
"pipelines/hidream",
- "pipelines/lumina_dimmo",
+ "pipelines/hdm",
"pipelines/meissonic",
"pipelines/omnigen2",
"pipelines/segmoe",
- "pipelines/step1x",
- "pipelines/ultraflux",
- "pipelines/vibe",
"pipelines/xomni",
+ "pipelines/chrono",
+ "pipelines/step1x",
+ "pipelines/vibe",
+ "pipelines/ultraflux",
+ "pipelines/lumina_dimmo",
"scripts/consistory",
"scripts/ctrlx",
"scripts/daam",
"scripts/demofusion",
- "scripts/differential_diffusion.py",
"scripts/freescale",
"scripts/infiniteyou",
"scripts/instantir",
- "scripts/layerdiffuse",
"scripts/lbm",
+ "scripts/layerdiffuse",
"scripts/mod",
"scripts/pixelsmith",
+ "scripts/differential_diffusion.py",
"scripts/pulid",
"scripts/xadapter",
+ "repositories",
"extensions-builtin/sd-extension-chainner/nodes",
+ "extensions-builtin/sd-webui-agent-scheduler",
+ "extensions-builtin/sdnext-modernui/node_modules",
+ "extensions-builtin/sdnext-kanvas/node_modules",
]
main.ignore-patterns=[
".*test*.py$",
diff --git a/scripts/consistory/consistory_unet_sdxl.py b/scripts/consistory/consistory_unet_sdxl.py
index 2c19f0de5..4e6e4b335 100644
--- a/scripts/consistory/consistory_unet_sdxl.py
+++ b/scripts/consistory/consistory_unet_sdxl.py
@@ -789,10 +789,10 @@ class ConsistorySDXLUNet2DConditionModel(ModelMixin, ConfigMixin, UNet2DConditio
b2 (`float`): Scaling factor for stage 2 to amplify the contributions of backbone features.
"""
for i, upsample_block in enumerate(self.up_blocks):
- upsample_block.s1 = s1
- upsample_block.s2 = s2
- upsample_block.b1 = b1
- upsample_block.b2 = b2
+ setattr(upsample_block, "s1", s1)
+ setattr(upsample_block, "s2", s2)
+ setattr(upsample_block, "b1", b1)
+ setattr(upsample_block, "b2", b2)
def disable_freeu(self):
"""Disables the FreeU mechanism."""
diff --git a/scripts/consistory_ext.py b/scripts/consistory_ext.py
index 4f077abc9..e0de9f1d4 100644
--- a/scripts/consistory_ext.py
+++ b/scripts/consistory_ext.py
@@ -196,7 +196,7 @@ class ConsiStoryScript(scripts_manager.Script):
log.warning(f'ConsiStory: class={shared.sd_model.__class__.__name__} model={shared.sd_model_type} required={supported_model_list}')
return None
- _subject, concepts, prompts, dropout, _sampler, steps, same, queries, sdsa, _freeu, _freeu_preset, alpha, injection = args # pylint: disable=unused-variable
+ subject, concepts, prompts, dropout, sampler, steps, same, queries, sdsa, freeu, _freeu_preset, alpha, injection = args # pylint: disable=unused-variable
self.create_model() # create model if not already done
concepts, anchors, prompts, alpha, steps, seed = self.set_args(p, *args) # set arguments
diff --git a/scripts/custom_code.py b/scripts/custom_code.py
index 42133c22f..1701cdf8b 100644
--- a/scripts/custom_code.py
+++ b/scripts/custom_code.py
@@ -3,7 +3,7 @@ import ast
import gradio as gr
from modules import scripts_manager
from modules.processing import Processed, get_processed
-from modules.shared import cmd_opts # pylint: disable=unused-import
+from modules.shared import opts, cmd_opts, state # pylint: disable=unused-import
def convertExpr2Expression(expr):
diff --git a/scripts/differential_diffusion.py b/scripts/differential_diffusion.py
index 0ca8fc463..d0f13a078 100644
--- a/scripts/differential_diffusion.py
+++ b/scripts/differential_diffusion.py
@@ -1627,7 +1627,7 @@ class StableDiffusionDiffImg2ImgPipeline(DiffusionPipeline):
if isinstance(image[0], PIL.Image.Image):
w, h = image[0].size
- w, h = map(lambda x: x - x % 8, (w, h)) # resize to integer multiple of 8
+ w, h = map(lambda x: x - x % 8, (w, h)) # resize to integer multiple of 8 # noqa: C417
image = [np.array(i.resize((w, h), resample=PIL_INTERPOLATION["lanczos"]))[None, :] for i in image]
image = np.concatenate(image, axis=0)
diff --git a/scripts/example.py b/scripts/example.py
index 61efe02f1..dafcd578f 100644
--- a/scripts/example.py
+++ b/scripts/example.py
@@ -1,5 +1,5 @@
import gradio as gr
-from diffusers.pipelines import StableDiffusionPipeline # pylint: disable=unused-import
+from diffusers.pipelines import StableDiffusionPipeline, StableDiffusionXLPipeline # pylint: disable=unused-import
from modules import shared, scripts_manager, processing, sd_models, devices
from modules.logger import log
diff --git a/scripts/freescale/free_lunch_utils.py b/scripts/freescale/free_lunch_utils.py
index 0852584b9..ebf165105 100644
--- a/scripts/freescale/free_lunch_utils.py
+++ b/scripts/freescale/free_lunch_utils.py
@@ -137,10 +137,10 @@ def register_free_upblock2d(model, b1=1.2, b2=1.4, s1=0.9, s2=0.2):
for i, upsample_block in enumerate(model.unet.up_blocks):
if isinstance_str(upsample_block, "UpBlock2D"):
upsample_block.forward = up_forward(upsample_block)
- upsample_block.b1 = b1
- upsample_block.b2 = b2
- upsample_block.s1 = s1
- upsample_block.s2 = s2
+ setattr(upsample_block, 'b1', b1)
+ setattr(upsample_block, 'b2', b2)
+ setattr(upsample_block, 's1', s1)
+ setattr(upsample_block, 's2', s2)
def register_crossattn_upblock2d(model):
@@ -300,7 +300,7 @@ def register_free_crossattn_upblock2d(model, b1=1.2, b2=1.4, s1=0.9, s2=0.2):
for i, upsample_block in enumerate(model.unet.up_blocks):
if isinstance_str(upsample_block, "CrossAttnUpBlock2D"):
upsample_block.forward = up_forward(upsample_block)
- upsample_block.b1 = b1
- upsample_block.b2 = b2
- upsample_block.s1 = s1
- upsample_block.s2 = s2
+ setattr(upsample_block, 'b1', b1)
+ setattr(upsample_block, 'b2', b2)
+ setattr(upsample_block, 's1', s1)
+ setattr(upsample_block, 's2', s2)
diff --git a/scripts/infiniteyou/resampler.py b/scripts/infiniteyou/resampler.py
index f6f3d5c56..6d0011e83 100644
--- a/scripts/infiniteyou/resampler.py
+++ b/scripts/infiniteyou/resampler.py
@@ -18,7 +18,7 @@ def FeedForward(dim, mult=4):
def reshape_tensor(x, heads):
- bs, length, _width = x.shape
+ bs, length, width = x.shape
#(bs, length, width) --> (bs, length, n_heads, dim_per_head)
x = x.view(bs, length, heads, -1)
# (bs, length, n_heads, dim_per_head) --> (bs, n_heads, length, dim_per_head)
diff --git a/scripts/instantir/sdxl_instantir.py b/scripts/instantir/sdxl_instantir.py
index ea376ef02..bfb4f84e9 100644
--- a/scripts/instantir/sdxl_instantir.py
+++ b/scripts/instantir/sdxl_instantir.py
@@ -166,11 +166,11 @@ PREVIEWER_LORA_MODULES = [
def remove_attn2(model):
def recursive_find_module(name, module):
- if "up_blocks" not in name and "down_blocks" not in name and "mid_block" not in name: return
+ if not "up_blocks" in name and not "down_blocks" in name and not "mid_block" in name: return
elif "resnets" in name: return
if hasattr(module, "attn2"):
- module.attn2 = None
- module.norm2 = None
+ setattr(module, "attn2", None)
+ setattr(module, "norm2", None)
return
for sub_name, sub_module in module.named_children():
recursive_find_module(f"{name}.{sub_name}", sub_module)
@@ -834,8 +834,8 @@ class InstantIRPipeline(
)
if (
isinstance(self.aggregator, Aggregator)
- or (is_compiled
- and isinstance(self.aggregator._orig_mod, Aggregator))
+ or is_compiled
+ and isinstance(self.aggregator._orig_mod, Aggregator)
):
self.check_image(image, prompt, prompt_embeds)
else:
diff --git a/scripts/mixture_of_diffusers.py b/scripts/mixture_of_diffusers.py
index 8d101ee78..601133590 100644
--- a/scripts/mixture_of_diffusers.py
+++ b/scripts/mixture_of_diffusers.py
@@ -71,6 +71,7 @@ class MoDScript(scripts_manager.Script):
from installer import install
install('ligo-segments')
try:
+ from ligo.segments import segment # pylint: disable=unused-import
return True
except Exception as e:
log.error(f'MoD: {e}')
diff --git a/scripts/mixture_tiling.py b/scripts/mixture_tiling.py
index e8315e84d..fcf7b7cf1 100644
--- a/scripts/mixture_tiling.py
+++ b/scripts/mixture_tiling.py
@@ -17,6 +17,7 @@ def check_dependencies():
if not installed(pkg[1], quiet=True):
install(pkg[0], pkg[1], ignore=False)
try:
+ from ligo.segments import segment # pylint: disable=unused-import
checked_ok = True
return True
except Exception as e:
diff --git a/scripts/prompt_enhance.py b/scripts/prompt_enhance.py
index a60857cd4..3162f0787 100644
--- a/scripts/prompt_enhance.py
+++ b/scripts/prompt_enhance.py
@@ -798,7 +798,7 @@ class PromptEnhanceScript(scripts_manager.Script):
if debug_enabled:
errors.display(e, 'Prompt enhance')
self.busy = False
- response = f'Error: {e!s}'
+ response = f'Error: {str(e)}'
finally:
offload_aux('prompt_enhance')
devices.torch_gc(force=False, reason='prompt-enhance')
diff --git a/scripts/pulid/eva_clip/factory.py b/scripts/pulid/eva_clip/factory.py
index 3051e7c6c..b33929625 100644
--- a/scripts/pulid/eva_clip/factory.py
+++ b/scripts/pulid/eva_clip/factory.py
@@ -18,7 +18,7 @@ from .tokenizer import HFTokenizer, tokenize
from .utils import resize_clip_pos_embed, resize_evaclip_pos_embed, resize_visual_pos_embed, resize_eva_pos_embed
-_MODEL_CONFIG_PATHS = [Path(__file__).parent / "model_configs/"]
+_MODEL_CONFIG_PATHS = [Path(__file__).parent / f"model_configs/"]
_MODEL_CONFIGS = {} # directory (model_name: config) of model architecture configs
diff --git a/scripts/pulid/eva_clip/hf_model.py b/scripts/pulid/eva_clip/hf_model.py
index 29d2f592c..1665ada0b 100644
--- a/scripts/pulid/eva_clip/hf_model.py
+++ b/scripts/pulid/eva_clip/hf_model.py
@@ -14,7 +14,7 @@ try:
from transformers import AutoModel, AutoModelForMaskedLM, AutoTokenizer, AutoConfig, PretrainedConfig
from transformers.modeling_outputs import BaseModelOutput, BaseModelOutputWithPooling, \
BaseModelOutputWithPoolingAndCrossAttentions
-except ImportError:
+except ImportError as e:
transformers = None
diff --git a/scripts/pulid/eva_clip/model.py b/scripts/pulid/eva_clip/model.py
index 5be65b752..05b055794 100644
--- a/scripts/pulid/eva_clip/model.py
+++ b/scripts/pulid/eva_clip/model.py
@@ -385,7 +385,7 @@ def build_model_from_openai_state_dict(
vocab_size = state_dict["token_embedding.weight"].shape[0]
transformer_width = state_dict["ln_final.weight"].shape[0]
transformer_heads = transformer_width // 64
- transformer_layers = len(set(k.split(".")[2] for k in state_dict if k.startswith("transformer.resblocks")))
+ transformer_layers = len(set(k.split(".")[2] for k in state_dict if k.startswith(f"transformer.resblocks")))
vision_cfg = CLIPVisionCfg(
layers=vision_layers,
diff --git a/scripts/pulid/eva_clip/timm_model.py b/scripts/pulid/eva_clip/timm_model.py
index 9b9233327..53bc4d469 100644
--- a/scripts/pulid/eva_clip/timm_model.py
+++ b/scripts/pulid/eva_clip/timm_model.py
@@ -110,7 +110,7 @@ class TimmModel(nn.Module):
def set_grad_checkpointing(self, enable=True):
try:
self.trunk.set_grad_checkpointing(enable)
- except Exception:
+ except Exception as e:
logging.warning('grad checkpointing not supported for this timm image tower, continuing without...')
def forward(self, x):
diff --git a/scripts/pulid/eva_clip/tokenizer.py b/scripts/pulid/eva_clip/tokenizer.py
index 45fa860a9..b76e2a3aa 100644
--- a/scripts/pulid/eva_clip/tokenizer.py
+++ b/scripts/pulid/eva_clip/tokenizer.py
@@ -12,6 +12,7 @@ import regex as re
import torch
# https://stackoverflow.com/q/62691279
+import os
os.environ["TOKENIZERS_PARALLELISM"] = "false"
diff --git a/scripts/pulid/eva_clip/utils.py b/scripts/pulid/eva_clip/utils.py
index c5e3dfd3b..1c3c06201 100644
--- a/scripts/pulid/eva_clip/utils.py
+++ b/scripts/pulid/eva_clip/utils.py
@@ -149,7 +149,7 @@ def resize_rel_pos_embed(state_dict, model, interpolation: str = 'bicubic', seq_
dst_num_pos, _ = model.visual.state_dict()[key].size()
dst_patch_shape = model.visual.patch_embed.patch_shape
if dst_patch_shape[0] != dst_patch_shape[1]:
- raise NotImplementedError
+ raise NotImplementedError()
num_extra_tokens = dst_num_pos - (dst_patch_shape[0] * 2 - 1) * (dst_patch_shape[1] * 2 - 1)
src_size = int((src_num_pos - num_extra_tokens) ** 0.5)
dst_size = int((dst_num_pos - num_extra_tokens) ** 0.5)
diff --git a/scripts/pulid/pulid_flux.py b/scripts/pulid/pulid_flux.py
index 8e90d6b27..13ea880c4 100644
--- a/scripts/pulid/pulid_flux.py
+++ b/scripts/pulid/pulid_flux.py
@@ -6,7 +6,7 @@ from modules.logger import log
def apply_flux(pipe: FluxPipeline):
- if not hasattr(pipe, 'transformer') or 'Nunchaku' not in pipe.transformer.__class__.__name__:
+ if not hasattr(pipe, 'transformer') or not 'Nunchaku' in pipe.transformer.__class__.__name__:
log.error('PuLID: flux support requires nunchaku')
return pipe
diff --git a/scripts/stablevideodiffusion.py b/scripts/stablevideodiffusion.py
index 779abef2d..6e023dd46 100644
--- a/scripts/stablevideodiffusion.py
+++ b/scripts/stablevideodiffusion.py
@@ -87,6 +87,7 @@ class SVDScript(scripts_manager.Script):
c = shared.sd_model.__class__.__name__
model_loaded = shared.sd_model.sd_checkpoint_info.model_name if shared.sd_loaded else None
if model_name != model_loaded or c != 'StableVideoDiffusionPipeline':
+ from diffusers import StableVideoDiffusionPipeline # pylint: disable=unused-import
shared.opts.sd_model_checkpoint = model_path
sd_models.reload_model_weights()
shared.sd_model._encode_vae_image = self._encode_image # pylint: disable=protected-access
diff --git a/scripts/xyz/xyz_grid_classes.py b/scripts/xyz/xyz_grid_classes.py
index c13016ba4..ca78569ad 100644
--- a/scripts/xyz/xyz_grid_classes.py
+++ b/scripts/xyz/xyz_grid_classes.py
@@ -34,6 +34,7 @@ from scripts.xyz.xyz_grid_shared import ( # pylint: disable=no-name-in-module, u
apply_control,
format_value_add_label,
format_bool,
+ format_value,
format_value_join_list,
do_nothing,
format_nothing,
diff --git a/scripts/xyz_grid.py b/scripts/xyz_grid.py
index 49ea4c9a2..d86e22af6 100644
--- a/scripts/xyz_grid.py
+++ b/scripts/xyz_grid.py
@@ -11,6 +11,7 @@ import gradio as gr
from scripts.xyz.xyz_grid_shared import str_permutations, list_to_csv_string, restore_comma, re_range, re_plain_comma # pylint: disable=no-name-in-module
from scripts.xyz.xyz_grid_classes import axis_options, AxisOption, SharedSettingsStackHelper # pylint: disable=no-name-in-module
from scripts.xyz.xyz_grid_draw import draw_xyz_grid # pylint: disable=no-name-in-module
+from scripts.xyz.xyz_grid_shared import apply_field, apply_task_args, apply_setting, apply_prompt, apply_order, apply_sampler, apply_hr_sampler_name, confirm_samplers, apply_checkpoint, apply_refiner, apply_unet, apply_clip_skip, apply_vae, list_lora, apply_lora, apply_lora_strength, apply_te, apply_styles, apply_upscaler, apply_context, apply_detailer, apply_override, apply_processing, apply_options, apply_seed, format_value_add_label, format_value, format_value_join_list, do_nothing, format_nothing # pylint: disable=no-name-in-module, unused-import
from modules import shared, errors, scripts_manager, images, video, processing
from modules.ui_components import ToolButton
from modules.ui_sections import create_video_inputs
diff --git a/test/test-generation-api.py b/test/test-generation-api.py
index 98ec18982..1359d59e5 100644
--- a/test/test-generation-api.py
+++ b/test/test-generation-api.py
@@ -417,7 +417,7 @@ class GenerationAPITest:
self.skip(f'param_{name}', 'baseline generation failed')
return
- data, _elapsed = self._txt2img(params)
+ data, elapsed = self._txt2img(params)
if 'error' in data:
self.record(False, f'param_{name}', f"generation error: {data}")
return
@@ -505,7 +505,7 @@ class GenerationAPITest:
# Vignette: corners should be darker than baseline corners
def check_vignette(base, result, _data):
- h, _w = base.shape[:2]
+ h, w = base.shape[:2]
corner_size = h // 8
base_corners = np.concatenate([
base[:corner_size, :corner_size].flatten(),
diff --git a/webui.py b/webui.py
index adf3b693d..b8d06697f 100644
--- a/webui.py
+++ b/webui.py
@@ -18,7 +18,7 @@ import modules.paths
import modules.devices
import modules.migrate
from modules import shared
-from modules.call_queue import queue_lock, wrap_queued_call # pylint: disable=unused-import
+from modules.call_queue import queue_lock, wrap_queued_call, wrap_gradio_gpu_call # pylint: disable=unused-import
import modules.gr_tempdir
import modules.modeldata
import modules.extensions