verify sampler index before use

CHANGELOG.md

@@ -2,11 +2,41 @@
 
 ## Update for 2023-12-30
 
-- Fixes:
-  - img2img interrogate
+- **Fixes**:
+  - img2img clip and blip interrogate
+  - guard against invalid sampler index
+  - reset default cfg scale to 6.0
 
 ## Update for 2023-12-29
 
+To wrap up this amazing year, we're releasing a new version of [SD.Next](https://github.com/vladmandic/automatic), this one is absolutely massive!  
+
+### Highlights  
+
+- Brand new Control module for *text, image, batch and video* processing  
+  Native implementation of all control methods for both *SD15* and *SD-XL*  
+  ▹ **ControlNet | ControlNet XS | Control LLLite | T2I Adapters | IP Adapters**  
+  For details, see [Wiki](https://github.com/vladmandic/automatic/wiki/Control) documentation:  
+- Support for new models types out-of-the-box  
+  This brings number of supported t2i/i2i model families to 13!  
+  ▹ **Stable Diffusion 1.5/2.1 | SD-XL | LCM | Segmind | Kandinsky | Pixart-α | Würstchen | aMUSEd | DeepFloyd IF | UniDiffusion | SD-Distilled | BLiP Diffusion | etc.**  
+- New video capabilities:  
+  ▹ **AnimateDiff | SVD | ModelScope | ZeroScope**  
+- Enhanced platform support  
+  ▹ **Windows | Linux | MacOS** with **nVidia | AMD | IntelArc | DirectML | OpenVINO | ONNX+Olive** backends  
+- Better onboarding experience (first install)  
+  with all model types available for single click download & load (networks -> reference)  
+- Performance optimizations!
+  For comparisment of different processing options and compile backends, see [Wiki](https://github.com/vladmandic/automatic/wiki/Benchmark)  
+  As a highlight, we're reaching **~100 it/s** (no tricks, this is with full features enabled and end-to-end on a standard nVidia RTX4090)  
+- New [custom pipelines](https://github.com/vladmandic/automatic/blob/dev/scripts/example.py) framework for quickly porting any new pipeline  
+
+And others improvements in areas such as: Upscaling (up to 8x now with 40+ available upscalers), Inpainting (better quality), Prompt scheduling, new Sampler options, new LoRA types, additional UI themes, better HDR processing, built-in Video interpolation, parallel Batch processing, etc.  
+
+Plus some nifty new modules such as **FaceID** automatic face guidance using embeds during generation and **Depth 3D** image to 3D scene
+
+### Full changelog
+
 - **Control**  
   - native implementation of all image control methods:  
     **ControlNet**, **ControlNet XS**, **Control LLLite**, **T2I Adapters** and **IP Adapters**  

modules/control/run.py

@@ -15,7 +15,7 @@ from modules.control.units import lite # Kohya ControlLLLite
 from modules.control.units import t2iadapter # TencentARC T2I-Adapter
 from modules.control.units import reference # ControlNet-Reference
 from modules.control.units import ipadapter # IP-Adapter
-from modules import devices, shared, errors, processing, images, sd_models, sd_samplers
+from modules import devices, shared, errors, processing, images, sd_models
 
 
 debug = shared.log.trace if os.environ.get('SD_CONTROL_DEBUG', None) is not None else lambda *args, **kwargs: None
@@ -90,8 +90,8 @@ def control_run(units: List[unit.Unit], inputs, inits, unit_type: str, is_genera
         negative_prompt = negative,
         styles = styles,
         steps = steps,
-        sampler_name = sd_samplers.samplers[sampler_index].name,
-        latent_sampler = sd_samplers.samplers[sampler_index].name,
+        sampler_name = processing.get_sampler_name(sampler_index),
+        latent_sampler = processing.get_sampler_name(sampler_index),
         seed = seed,
         subseed = subseed,
         subseed_strength = subseed_strength,

modules/hypernetworks/hypernetwork.py

@@ -11,7 +11,7 @@ from torch import einsum
 from torch.nn.init import normal_, xavier_normal_, xavier_uniform_, kaiming_normal_, kaiming_uniform_, zeros_
 from einops import rearrange, repeat
 from ldm.util import default
-from modules import devices, processing, sd_models, shared, sd_samplers, hashes, sd_hijack_checkpoint, errors
+from modules import devices, processing, sd_models, shared, hashes, sd_hijack_checkpoint, errors
 import modules.textual_inversion.dataset
 from modules.textual_inversion import textual_inversion, ti_logging
 from modules.textual_inversion.learn_schedule import LearnRateScheduler
@@ -445,7 +445,7 @@ def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None,
     return name
 
 
-def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, use_weight, create_image_every, save_hypernetwork_every, template_filename, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
+def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, use_weight, create_image_every, save_hypernetwork_every, template_filename, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height): # pylint: disable=unused-argument
     # images allows training previews to have infotext. Importing it at the top causes a circular import problem.
     from modules import images
 
@@ -672,7 +672,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi
                         p.prompt = preview_prompt
                         p.negative_prompt = preview_negative_prompt
                         p.steps = preview_steps
-                        p.sampler_name = sd_samplers.samplers[preview_sampler_index].name
+                        p.sampler_name = processing.get_sampler_name(preview_sampler_index)
                         p.cfg_scale = preview_cfg_scale
                         p.seed = preview_seed
                         p.width = preview_width

modules/img2img.py

@@ -3,7 +3,7 @@ import itertools # SBM Batch frames
 import numpy as np
 from PIL import Image, ImageOps, ImageFilter, ImageEnhance, ImageChops, UnidentifiedImageError
 import modules.scripts
-from modules import sd_samplers, shared, processing, images
+from modules import shared, processing, images
 from modules.generation_parameters_copypaste import create_override_settings_dict
 from modules.ui import plaintext_to_html
 from modules.memstats import memory_stats
@@ -212,8 +212,8 @@ def img2img(id_task: str, mode: int,
         seed_resize_from_h=seed_resize_from_h,
         seed_resize_from_w=seed_resize_from_w,
         seed_enable_extras=True,
-        sampler_name=sd_samplers.samplers_for_img2img[sampler_index].name,
-        latent_sampler=sd_samplers.samplers[latent_index].name,
+        sampler_name = processing.get_sampler_name(sampler_index, img=True),
+        latent_sampler = processing.get_sampler_name(latent_index, img=True),
         batch_size=batch_size,
         n_iter=n_iter,
         steps=steps,

modules/processing.py

@@ -120,6 +120,16 @@ def txt2img_image_conditioning(sd_model, x, width, height):
         return x.new_zeros(x.shape[0], 5, 1, 1, dtype=x.dtype, device=x.device)
 
 
+def get_sampler_name(sampler_index: int, img: bool = False) -> str:
+    samplers = modules.sd_samplers.samplers if not img else modules.sd_samplers.samplers_for_img2img
+    if len(samplers) > sampler_index:
+        sampler_name = samplers[sampler_index].name
+    else:
+        sampler_name = "UniPC"
+        shared.log.warning(f'Sampler not found: index={sampler_index} available={[s.name for s in samplers]} fallback={sampler_name}')
+    return sampler_name
+
+
 @dataclass(repr=False)
 class StableDiffusionProcessing:
     """

modules/processing_diffusers.py

@@ -350,7 +350,6 @@ def process_diffusers(p: StableDiffusionProcessing):
 
     def update_sampler(sd_model, second_pass=False):
         sampler_selection = p.latent_sampler if second_pass else p.sampler_name
-        # is_karras_compatible = sd_model.__class__.__init__.__annotations__.get("scheduler", None) == diffusers.schedulers.scheduling_utils.KarrasDiffusionSchedulers
         if sd_model.__class__.__name__ in ['AmusedPipeline']:
             return # models with their own schedulers
         if hasattr(sd_model, 'scheduler') and sampler_selection != 'Default':

modules/textual_inversion/textual_inversion.py

@@ -9,7 +9,7 @@ import safetensors.torch
 import numpy as np
 from PIL import Image, PngImagePlugin
 from torch.utils.tensorboard import SummaryWriter
-from modules import shared, devices, sd_hijack, processing, sd_models, images, sd_samplers, sd_hijack_checkpoint, errors
+from modules import shared, devices, sd_hijack, processing, sd_models, images, sd_hijack_checkpoint, errors
 import modules.textual_inversion.dataset
 from modules.textual_inversion.learn_schedule import LearnRateScheduler
 from modules.textual_inversion.image_embedding import embedding_to_b64, embedding_from_b64, insert_image_data_embed, extract_image_data_embed, caption_image_overlay
@@ -599,7 +599,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st
                         p.prompt = preview_prompt
                         p.negative_prompt = preview_negative_prompt
                         p.steps = preview_steps
-                        p.sampler_name = sd_samplers.samplers[preview_sampler_index].name
+                        p.sampler_name = processing.get_sampler_name(preview_sampler_index)
                         p.cfg_scale = preview_cfg_scale
                         p.seed = preview_seed
                         p.width = preview_width

modules/txt2img.py

@@ -1,6 +1,6 @@
 import os
 import modules.scripts
-from modules import sd_samplers, shared, processing
+from modules import shared, processing
 from modules.generation_parameters_copypaste import create_override_settings_dict
 from modules.ui import plaintext_to_html
 
@@ -50,8 +50,8 @@ def txt2img(id_task,
         seed_resize_from_h=seed_resize_from_h,
         seed_resize_from_w=seed_resize_from_w,
         seed_enable_extras=True,
-        sampler_name=sd_samplers.samplers[sampler_index].name,
-        latent_sampler=sd_samplers.samplers[latent_index].name,
+        sampler_name = processing.get_sampler_name(sampler_index),
+        latent_sampler = processing.get_sampler_name(latent_index),
         batch_size=batch_size,
         n_iter=n_iter,
         steps=steps,

modules/ui.py

@@ -183,10 +183,10 @@ def create_advanced_inputs(tab):
     with gr.Accordion(open=False, label="Advanced", elem_id=f"{tab}_advanced", elem_classes=["small-accordion"]):
         with gr.Group():
             with FormRow():
-                cfg_scale = gr.Slider(minimum=0.0, maximum=30.0, step=0.1, label='CFG scale', value=4.0, elem_id=f"{tab}_cfg_scale")
+                cfg_scale = gr.Slider(minimum=0.0, maximum=30.0, step=0.1, label='CFG scale', value=6.0, elem_id=f"{tab}_cfg_scale")
                 clip_skip = gr.Slider(label='CLIP skip', value=1, minimum=1, maximum=14, step=1, elem_id=f"{tab}_clip_skip", interactive=True)
             with FormRow():
-                image_cfg_scale = gr.Slider(minimum=0.0, maximum=30.0, step=0.1, label='Secondary CFG scale', value=4.0, elem_id=f"{tab}_image_cfg_scale")
+                image_cfg_scale = gr.Slider(minimum=0.0, maximum=30.0, step=0.1, label='Secondary CFG scale', value=6.0, elem_id=f"{tab}_image_cfg_scale")
                 diffusers_guidance_rescale = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Guidance rescale', value=0.7, elem_id=f"{tab}_image_cfg_rescale", visible=shared.backend == shared.Backend.DIFFUSERS)
         with gr.Group():
             with FormRow():