Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-19 17:24:32 +02:00
Code Issues Packages Projects Releases Wiki Activity

update transformers/diffusers and enhanced tests

Browse Source 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
This commit is contained in:
Vladimir Mandic
2026-06-12 14:15:22 +02:00
parent 2a632920e1
commit 469428b502
8 changed files with 309 additions and 284 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+4 -3
View File
@@ -1,8 +1,8 @@
# Change Log for SD.Next
## Update for 2026-06-11
## Update for 2026-06-12
### Highlights for 2026-06-11
### Highlights for 2026-06-12
*What's New?*
- **Ideogram-4** released, Microsoft joins the game with **Lens** and **Anima** made it to release version
@@ -18,7 +18,7 @@ And we have a new modular LoRA loader, new native Transformers loader and improv
[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 2026-06-11
### Details for 2026-06-12
- **Models**
- [CircleStone Anima 1.0](https://huggingface.co/circlestone-labs/Anima) in *Base* and *Turbo* (distilled) variants
@@ -148,6 +148,7 @@ And we have a new modular LoRA loader, new native Transformers loader and improv
- `xpu` generator on non-cpu
- `compel` compatibility with *transformers==5*
- `mixture-tiling` fix for non-square images, thanks @QualiaRain
- `prompts-from-file` fix metadata handling, thanks @QualiaRain
## Update for 2026-05-13
installer.py
+2 -2
View File
@@ -534,7 +534,7 @@ def check_diffusers():
t_start = time.time()
if args.skip_all:
return
target_commit = "f8090807648bdcd8a5a9e0e28528e4ce10bc277b" # diffusers commit hash == 0.39.0.dev0 == 06-10-2026
target_commit = "a50ade492678dd105f3df1b3d3e0df35c4e0740e" # diffusers commit hash == 0.39.0.dev0 == 06-12-2026
# if args.use_rocm or args.use_zluda or args.use_directml:
# sha = '043ab2520f6a19fce78e6e060a68dbc947edb9f9' # lock diffusers versions for now
pkg = package_spec('diffusers')
@@ -564,7 +564,7 @@ def check_transformers():
pkg_tokenizers = package_spec('tokenizers')
# target_commit = '753d61104116eefc8ffc977327b441ee0c8d599f' # transformers commit hash == 4.57.6
# target_commit = "380e3cc5d59912a48508cb6d4959a31cd460e12e" # transformers commit hash == 5.5.0.dev-0409
target_commit = "d20946079fd422335fbae3eeb98b7cd88334612f" # transformers commit hash == 5.10.0.dev0 == 06-10-2026
target_commit = "a14eae2b54c19cb427c919a99c75db07afbeb7a0" # transformers commit hash == 5.10.0.dev0 == 06-12-2026
if args.use_directml:
target_transformers = '4.52.4'
target_tokenizers = '0.21.4'
launch.py
+1
View File
@@ -219,6 +219,7 @@ def start_server(immediate=True, server=None):
test_pipelines()
log.info("Test only: exiting...")
server.wants_restart = False
uvicorn = server.webui(restart=not immediate, _exit=True)
else:
uvicorn = server.webui(restart=not immediate)
if args.profile:
modules/video_models/models_def.py
+275 -255
View File
@@ -1,7 +1,10 @@
from dataclasses import dataclass
import sys
import time
import types
import diffusers
import transformers
from modules import errors
from modules.logger import log
@@ -30,8 +33,25 @@ class Model:
return f'name="{self.name}" url="{self.url}" repo="{self.repo}" repo_cls="{self.repo_cls}" dit="{self.dit}" dit_cls="{self.dit_cls}" dit_folder="{self.dit_folder}" te="{self.te}" te_cls="{self.te_cls}" te_folder="{self.te_folder}" te_hijack={self.te_hijack} vae_hijack={self.vae_hijack} vae_remote={self.vae_remote}'
def getpipe(package, name, _default=None):
if package is None:
return None
try:
cls = getattr(package, name, _default)
return cls
except Exception as e:
log.error(f'Video load: error loading class "{name}" from package "{package.__name__}": {e}')
return None
def init_overrides():
from pipelines.cosmos import safety_checker
sys.modules['cosmos_guardrail'] = safety_checker
try:
t0 = time.time()
init_overrides()
models = {
'None': [],
'Hunyuan Video': [
@@ -40,91 +60,91 @@ try:
url='https://huggingface.co/tencent/HunyuanVideo-1.5',
vae_remote=False,
repo='hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v',
repo_cls=getattr(diffusers, 'HunyuanVideo15Pipeline', None),
te_cls=getattr(transformers, 'Qwen2_5_VLTextModel', None),
dit_cls=getattr(diffusers, 'HunyuanVideo15Transformer3DModel', None)),
repo_cls=getpipe(diffusers, 'HunyuanVideo15Pipeline', None),
te_cls=getpipe(transformers, 'Qwen2_5_VLTextModel', None),
dit_cls=getpipe(diffusers, 'HunyuanVideo15Transformer3DModel', None)),
Model(name='Hunyuan Video 1.5 I2V 720p',
url='https://huggingface.co/tencent/HunyuanVideo-1.5',
vae_remote=False,
repo='hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_i2v',
repo_cls=getattr(diffusers, 'HunyuanVideo15ImageToVideoPipeline', None),
te_cls=getattr(transformers, 'Qwen2_5_VLTextModel', None),
dit_cls=getattr(diffusers, 'HunyuanVideo15Transformer3DModel', None)),
repo_cls=getpipe(diffusers, 'HunyuanVideo15ImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'Qwen2_5_VLTextModel', None),
dit_cls=getpipe(diffusers, 'HunyuanVideo15Transformer3DModel', None)),
Model(name='Hunyuan Video 1.5 I2V 720p Distilled',
url='https://huggingface.co/tencent/HunyuanVideo-1.5',
vae_remote=False,
repo='hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_i2v_distilled',
repo_cls=getattr(diffusers, 'HunyuanVideo15ImageToVideoPipeline', None),
te_cls=getattr(transformers, 'Qwen2_5_VLTextModel', None),
dit_cls=getattr(diffusers, 'HunyuanVideo15Transformer3DModel', None)),
repo_cls=getpipe(diffusers, 'HunyuanVideo15ImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'Qwen2_5_VLTextModel', None),
dit_cls=getpipe(diffusers, 'HunyuanVideo15Transformer3DModel', None)),
Model(name='Hunyuan Video 1.5 T2V 480p',
url='https://huggingface.co/tencent/HunyuanVideo-1.5',
vae_remote=False,
repo='hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v',
repo_cls=getattr(diffusers, 'HunyuanVideo15Pipeline', None),
te_cls=getattr(transformers, 'Qwen2_5_VLTextModel', None),
dit_cls=getattr(diffusers, 'HunyuanVideo15Transformer3DModel', None)),
repo_cls=getpipe(diffusers, 'HunyuanVideo15Pipeline', None),
te_cls=getpipe(transformers, 'Qwen2_5_VLTextModel', None),
dit_cls=getpipe(diffusers, 'HunyuanVideo15Transformer3DModel', None)),
Model(name='Hunyuan Video 1.5 T2V 480p Distilled',
url='https://huggingface.co/tencent/HunyuanVideo-1.5',
vae_remote=False,
repo='hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v_distilled',
repo_cls=getattr(diffusers, 'HunyuanVideo15Pipeline', None),
te_cls=getattr(transformers, 'Qwen2_5_VLTextModel', None),
dit_cls=getattr(diffusers, 'HunyuanVideo15Transformer3DModel', None)),
repo_cls=getpipe(diffusers, 'HunyuanVideo15Pipeline', None),
te_cls=getpipe(transformers, 'Qwen2_5_VLTextModel', None),
dit_cls=getpipe(diffusers, 'HunyuanVideo15Transformer3DModel', None)),
Model(name='Hunyuan Video 1.5 I2V 480p',
url='https://huggingface.co/tencent/HunyuanVideo-1.5',
vae_remote=False,
repo='hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_i2v',
repo_cls=getattr(diffusers, 'HunyuanVideo15ImageToVideoPipeline', None),
te_cls=getattr(transformers, 'Qwen2_5_VLTextModel', None),
dit_cls=getattr(diffusers, 'HunyuanVideo15Transformer3DModel', None)),
repo_cls=getpipe(diffusers, 'HunyuanVideo15ImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'Qwen2_5_VLTextModel', None),
dit_cls=getpipe(diffusers, 'HunyuanVideo15Transformer3DModel', None)),
Model(name='Hunyuan Video 1.5 I2V 480p Distilled',
url='https://huggingface.co/tencent/HunyuanVideo-1.5',
vae_remote=False,
repo='hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_i2v_distilled',
repo_cls=getattr(diffusers, 'HunyuanVideo15ImageToVideoPipeline', None),
te_cls=getattr(transformers, 'Qwen2_5_VLTextModel', None),
dit_cls=getattr(diffusers, 'HunyuanVideo15Transformer3DModel', None)),
repo_cls=getpipe(diffusers, 'HunyuanVideo15ImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'Qwen2_5_VLTextModel', None),
dit_cls=getpipe(diffusers, 'HunyuanVideo15Transformer3DModel', None)),
Model(name='Hunyuan Video 1.0 T2V',
url='https://huggingface.co/tencent/HunyuanVideo',
vae_remote=True,
repo='hunyuanvideo-community/HunyuanVideo',
repo_cls=getattr(diffusers, 'HunyuanVideoPipeline', None),
te_cls=getattr(transformers, 'LlamaModel', None),
dit_cls=getattr(diffusers, 'HunyuanVideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'HunyuanVideoPipeline', None),
te_cls=getpipe(transformers, 'LlamaModel', None),
dit_cls=getpipe(diffusers, 'HunyuanVideoTransformer3DModel', None)),
Model(name='Hunyuan Video 1.0 I2V', # https://github.com/huggingface/diffusers/pull/10983
url='https://huggingface.co/tencent/HunyuanVideo-I2V',
vae_remote=True,
repo='hunyuanvideo-community/HunyuanVideo-I2V',
repo_cls=getattr(diffusers, 'HunyuanVideoImageToVideoPipeline', None),
te_cls=getattr(transformers, 'LlavaForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'HunyuanVideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'HunyuanVideoImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'LlavaForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'HunyuanVideoTransformer3DModel', None)),
Model(name='SkyReels Hunyuan 1.0 T2V', # https://github.com/huggingface/diffusers/pull/10837
url='https://huggingface.co/Skywork/SkyReels-V1-Hunyuan-T2V',
vae_remote=True,
repo='hunyuanvideo-community/HunyuanVideo',
repo_cls=getattr(diffusers, 'HunyuanVideoPipeline', None),
te_cls=getattr(transformers, 'LlamaModel', None),
repo_cls=getpipe(diffusers, 'HunyuanVideoPipeline', None),
te_cls=getpipe(transformers, 'LlamaModel', None),
dit='Skywork/SkyReels-V1-Hunyuan-T2V',
dit_folder=None,
dit_cls=getattr(diffusers, 'HunyuanVideoTransformer3DModel', None)),
dit_cls=getpipe(diffusers, 'HunyuanVideoTransformer3DModel', None)),
Model(name='SkyReels Hunyuan 1.0 I2V', # https://github.com/huggingface/diffusers/pull/10837
url='https://huggingface.co/Skywork/SkyReels-V1-Hunyuan-I2V',
vae_remote=True,
repo='hunyuanvideo-community/HunyuanVideo',
repo_cls=getattr(diffusers, 'HunyuanSkyreelsImageToVideoPipeline', None),
te_cls=getattr(transformers, 'LlamaModel', None),
repo_cls=getpipe(diffusers, 'HunyuanSkyreelsImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'LlamaModel', None),
dit='Skywork/SkyReels-V1-Hunyuan-I2V',
dit_folder=None,
dit_cls=getattr(diffusers, 'HunyuanVideoTransformer3DModel', None)),
dit_cls=getpipe(diffusers, 'HunyuanVideoTransformer3DModel', None)),
Model(name='Fast Hunyuan 1.0 T2V', # https://github.com/hao-ai-lab/FastVideo/blob/8a77cf22c9b9e7f931f42bc4b35d21fd91d24e45/fastvideo/models/hunyuan/inference.py#L213
url='https://huggingface.co/FastVideo/FastHunyuan',
vae_remote=True,
repo='hunyuanvideo-community/HunyuanVideo',
repo_cls=getattr(diffusers, 'HunyuanVideoPipeline', None),
te_cls=getattr(transformers, 'LlamaModel', None),
repo_cls=getpipe(diffusers, 'HunyuanVideoPipeline', None),
te_cls=getpipe(transformers, 'LlamaModel', None),
dit='FastVideo/FastHunyuan-diffusers',
dit_cls=getattr(diffusers, 'HunyuanVideoTransformer3DModel', None)),
dit_cls=getpipe(diffusers, 'HunyuanVideoTransformer3DModel', None)),
],
'LTX Video': [
Model(name='None'),
@@ -133,485 +153,485 @@ try:
Model(name='LTXVideo 2.3-1.1 22B T2V Distilled',
url='https://huggingface.co/Lightricks/LTX-2.3',
repo='OzzyGT/LTX-2.3-Distilled-1.1',
repo_cls=getattr(diffusers, 'LTX2Pipeline', None),
te_cls=getattr(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'LTX2VideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTX2Pipeline', None),
te_cls=getpipe(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'LTX2VideoTransformer3DModel', None)),
Model(name='LTXVideo 2.3-1.1 22B I2V Distilled',
url='https://huggingface.co/Lightricks/LTX-2.3',
repo='OzzyGT/LTX-2.3-Distilled-1.1',
repo_cls=getattr(diffusers, 'LTX2ImageToVideoPipeline', None),
te_cls=getattr(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'LTX2VideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTX2ImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'LTX2VideoTransformer3DModel', None)),
Model(name='LTXVideo 2.3-1.1 22B T2V Distilled SDNQ-4Bit',
url='https://huggingface.co/Lightricks/LTX-2.3',
repo='OzzyGT/LTX-2.3-Distilled-1.1-sdnq-dynamic-int4',
repo_cls=getattr(diffusers, 'LTX2Pipeline', None),
te_cls=getattr(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'LTX2VideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTX2Pipeline', None),
te_cls=getpipe(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'LTX2VideoTransformer3DModel', None)),
Model(name='LTXVideo 2.3-1.1 22B I2V Distilled SDNQ-4Bit',
url='https://huggingface.co/Lightricks/LTX-2.3',
repo='OzzyGT/LTX-2.3-Distilled-1.1-sdnq-dynamic-int4',
repo_cls=getattr(diffusers, 'LTX2ImageToVideoPipeline', None),
te_cls=getattr(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'LTX2VideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTX2ImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'LTX2VideoTransformer3DModel', None)),
Model(name='─────── LTX-2.3 v1.0 ───────'),
Model(name='─── Base ───'),
Model(name='LTXVideo 2.3 22B T2V',
url='https://huggingface.co/Lightricks/LTX-2.3',
repo='OzzyGT/LTX-2.3',
repo_cls=getattr(diffusers, 'LTX2Pipeline', None),
te_cls=getattr(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'LTX2VideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTX2Pipeline', None),
te_cls=getpipe(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'LTX2VideoTransformer3DModel', None)),
Model(name='LTXVideo 2.3 22B I2V',
url='https://huggingface.co/Lightricks/LTX-2.3',
repo='OzzyGT/LTX-2.3',
repo_cls=getattr(diffusers, 'LTX2ImageToVideoPipeline', None),
te_cls=getattr(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'LTX2VideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTX2ImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'LTX2VideoTransformer3DModel', None)),
Model(name='LTXVideo 2.3 22B Condition',
url='https://huggingface.co/Lightricks/LTX-2.3',
repo='OzzyGT/LTX-2.3',
repo_cls=getattr(diffusers, 'LTX2ConditionPipeline', None),
te_cls=getattr(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'LTX2VideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTX2ConditionPipeline', None),
te_cls=getpipe(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'LTX2VideoTransformer3DModel', None)),
Model(name='LTXVideo 2.3 22B T2V SDNQ-4Bit',
url='https://huggingface.co/Lightricks/LTX-2.3',
repo='OzzyGT/LTX-2.3-sdnq-dynamic-int4',
repo_cls=getattr(diffusers, 'LTX2Pipeline', None),
te_cls=getattr(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'LTX2VideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTX2Pipeline', None),
te_cls=getpipe(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'LTX2VideoTransformer3DModel', None)),
Model(name='LTXVideo 2.3 22B I2V SDNQ-4Bit',
url='https://huggingface.co/Lightricks/LTX-2.3',
repo='OzzyGT/LTX-2.3-sdnq-dynamic-int4',
repo_cls=getattr(diffusers, 'LTX2ImageToVideoPipeline', None),
te_cls=getattr(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'LTX2VideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTX2ImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'LTX2VideoTransformer3DModel', None)),
Model(name='LTXVideo 2.3 22B Condition SDNQ-4Bit',
url='https://huggingface.co/Lightricks/LTX-2.3',
repo='OzzyGT/LTX-2.3-sdnq-dynamic-int4',
repo_cls=getattr(diffusers, 'LTX2ConditionPipeline', None),
te_cls=getattr(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'LTX2VideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTX2ConditionPipeline', None),
te_cls=getpipe(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'LTX2VideoTransformer3DModel', None)),
Model(name='─── Distilled ───'),
Model(name='LTXVideo 2.3 22B T2V Distilled',
url='https://huggingface.co/Lightricks/LTX-2.3',
repo='OzzyGT/LTX-2.3-Distilled',
repo_cls=getattr(diffusers, 'LTX2Pipeline', None),
te_cls=getattr(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'LTX2VideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTX2Pipeline', None),
te_cls=getpipe(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'LTX2VideoTransformer3DModel', None)),
Model(name='LTXVideo 2.3 22B I2V Distilled',
url='https://huggingface.co/Lightricks/LTX-2.3',
repo='OzzyGT/LTX-2.3-Distilled',
repo_cls=getattr(diffusers, 'LTX2ImageToVideoPipeline', None),
te_cls=getattr(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'LTX2VideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTX2ImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'LTX2VideoTransformer3DModel', None)),
Model(name='LTXVideo 2.3 22B Condition Distilled',
url='https://huggingface.co/Lightricks/LTX-2.3',
repo='OzzyGT/LTX-2.3-Distilled',
repo_cls=getattr(diffusers, 'LTX2ConditionPipeline', None),
te_cls=getattr(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'LTX2VideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTX2ConditionPipeline', None),
te_cls=getpipe(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'LTX2VideoTransformer3DModel', None)),
Model(name='LTXVideo 2.3 22B T2V Distilled SDNQ-4Bit',
url='https://huggingface.co/Lightricks/LTX-2.3',
repo='OzzyGT/LTX-2.3-Distilled-sdnq-dynamic-int4',
repo_cls=getattr(diffusers, 'LTX2Pipeline', None),
te_cls=getattr(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'LTX2VideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTX2Pipeline', None),
te_cls=getpipe(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'LTX2VideoTransformer3DModel', None)),
Model(name='LTXVideo 2.3 22B I2V Distilled SDNQ-4Bit',
url='https://huggingface.co/Lightricks/LTX-2.3',
repo='OzzyGT/LTX-2.3-Distilled-sdnq-dynamic-int4',
repo_cls=getattr(diffusers, 'LTX2ImageToVideoPipeline', None),
te_cls=getattr(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'LTX2VideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTX2ImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'LTX2VideoTransformer3DModel', None)),
Model(name='LTXVideo 2.3 22B Condition Distilled SDNQ-4Bit',
url='https://huggingface.co/Lightricks/LTX-2.3',
repo='OzzyGT/LTX-2.3-Distilled-sdnq-dynamic-int4',
repo_cls=getattr(diffusers, 'LTX2ConditionPipeline', None),
te_cls=getattr(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'LTX2VideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTX2ConditionPipeline', None),
te_cls=getpipe(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'LTX2VideoTransformer3DModel', None)),
Model(name='─────── LTX-2.0 ───────'),
Model(name='LTXVideo 2.0 19B T2V Dev',
url='https://huggingface.co/Lightricks/LTX-2',
repo='Lightricks/LTX-2',
repo_cls=getattr(diffusers, 'LTX2Pipeline', None),
te_cls=getattr(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'LTX2VideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTX2Pipeline', None),
te_cls=getpipe(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'LTX2VideoTransformer3DModel', None)),
Model(name='LTXVideo 2.0 19B I2V Dev',
url='https://huggingface.co/Lightricks/LTX-2',
repo='Lightricks/LTX-2',
repo_cls=getattr(diffusers, 'LTX2ImageToVideoPipeline', None),
te_cls=getattr(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'LTX2VideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTX2ImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'LTX2VideoTransformer3DModel', None)),
Model(name='LTXVideo 2.0 19B T2V Dev SDNQ-4Bit',
url='https://huggingface.co/Disty0/LTX-2-SDNQ-4bit-dynamic',
repo='Disty0/LTX-2-SDNQ-4bit-dynamic',
repo_cls=getattr(diffusers, 'LTX2Pipeline', None),
te_cls=getattr(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'LTX2VideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTX2Pipeline', None),
te_cls=getpipe(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'LTX2VideoTransformer3DModel', None)),
Model(name='LTXVideo 2.0 19B I2V Dev SDNQ-4Bit',
url='https://huggingface.co/Disty0/LTX-2-SDNQ-4bit-dynamic',
repo='Disty0/LTX-2-SDNQ-4bit-dynamic',
repo_cls=getattr(diffusers, 'LTX2ImageToVideoPipeline', None),
te_cls=getattr(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'LTX2VideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTX2ImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'Gemma3ForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'LTX2VideoTransformer3DModel', None)),
Model(name='─────── LTX-0.9.x ───────'),
Model(name='─── Base ───'),
Model(name='LTXVideo 0.9.7 13B Dev',
url='https://huggingface.co/Lightricks/LTX-Video-0.9.7-dev',
repo='a-r-r-o-w/LTX-Video-0.9.7-diffusers',
repo_cls=getattr(diffusers, 'LTXConditionPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'LTXVideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTXConditionPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'LTXVideoTransformer3DModel', None)),
Model(name='LTXVideo 0.9.6 2B T2V',
url='https://huggingface.co/Lightricks/LTX-Video',
repo='Lightricks/LTX-Video',
repo_cls=getattr(diffusers, 'LTXConditionPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'LTXVideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTXConditionPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'LTXVideoTransformer3DModel', None)),
Model(name='LTXVideo 0.9.6 2B I2V',
url='https://huggingface.co/Lightricks/LTX-Video',
repo='Lightricks/LTX-Video',
repo_cls=getattr(diffusers, 'LTXConditionPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'LTXVideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTXConditionPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'LTXVideoTransformer3DModel', None)),
Model(name='LTXVideo 0.9.5 T2V', # https://github.com/huggingface/diffusers/pull/10968
url='https://huggingface.co/Lightricks/LTX-Video-0.9.5',
repo='Lightricks/LTX-Video-0.9.5',
repo_cls=getattr(diffusers, 'LTXConditionPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'LTXVideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTXConditionPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'LTXVideoTransformer3DModel', None)),
Model(name='LTXVideo 0.9.5 I2V',
url='https://huggingface.co/Lightricks/LTX-Video-0.9.5',
repo='Lightricks/LTX-Video-0.9.5',
repo_cls=getattr(diffusers, 'LTXConditionPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'LTXVideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTXConditionPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'LTXVideoTransformer3DModel', None)),
Model(name='LTXVideo 0.9.1 T2V',
url='https://huggingface.co/a-r-r-o-w/LTX-Video-0.9.1-diffusers',
repo='a-r-r-o-w/LTX-Video-0.9.1-diffusers',
repo_cls=getattr(diffusers, 'LTXPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'LTXVideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTXPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'LTXVideoTransformer3DModel', None)),
Model(name='LTXVideo 0.9.1 I2V',
url='https://huggingface.co/a-r-r-o-w/LTX-Video-0.9.1-diffusers',
repo='a-r-r-o-w/LTX-Video-0.9.1-diffusers',
repo_cls=getattr(diffusers, 'LTXImageToVideoPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'LTXVideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTXImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'LTXVideoTransformer3DModel', None)),
Model(name='LTXVideo 0.9.0 T2V',
url='https://huggingface.co/a-r-r-o-w/LTX-Video-diffusers',
repo='a-r-r-o-w/LTX-Video-diffusers',
repo_cls=getattr(diffusers, 'LTXPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'LTXVideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTXPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'LTXVideoTransformer3DModel', None)),
Model(name='LTXVideo 0.9.0 I2V',
url='https://huggingface.co/a-r-r-o-w/LTX-Video-diffusers',
repo='a-r-r-o-w/LTX-Video-diffusers',
repo_cls=getattr(diffusers, 'LTXImageToVideoPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'LTXVideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTXImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'LTXVideoTransformer3DModel', None)),
Model(name='─── Distilled ───'),
Model(name='LTXVideo 0.9.8 13B Distilled',
url='https://huggingface.co/Lightricks/LTX-Video-0.9.8-13B-distilled',
repo='Lightricks/LTX-Video-0.9.8-13B-distilled',
repo_cls=getattr(diffusers, 'LTXConditionPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'LTXVideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTXConditionPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'LTXVideoTransformer3DModel', None)),
Model(name='LTXVideo 0.9.6 2B T2V Distilled',
url='https://huggingface.co/Lightricks/LTX-Video-2B-0.9.6-Distilled-04-25',
repo='Lightricks/LTX-Video-2B-0.9.6-Distilled-04-25',
repo_cls=getattr(diffusers, 'LTXConditionPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'LTXVideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTXConditionPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'LTXVideoTransformer3DModel', None)),
Model(name='LTXVideo 0.9.6 2B I2V Distilled',
url='https://huggingface.co/Lightricks/LTX-Video-2B-0.9.6-Distilled-04-25',
repo='Lightricks/LTX-Video-2B-0.9.6-Distilled-04-25',
repo_cls=getattr(diffusers, 'LTXConditionPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'LTXVideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LTXConditionPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'LTXVideoTransformer3DModel', None)),
],
'WAN Video': [
Model(name='None'),
Model(name='WAN 2.2 5B T2V',
url='https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B-Diffusers',
repo='Wan-AI/Wan2.2-TI2V-5B-Diffusers',
repo_cls=getattr(diffusers, 'WanPipeline', None),
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(diffusers, 'WanTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'WanPipeline', None),
te_cls=getpipe(transformers, 'UMT5EncoderModel', None),
dit_cls=getpipe(diffusers, 'WanTransformer3DModel', None)),
Model(name='WAN 2.2 5B I2V',
url='https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B-Diffusers',
repo='Wan-AI/Wan2.2-TI2V-5B-Diffusers',
repo_cls=getattr(diffusers, 'WanImageToVideoPipeline', None),
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(diffusers, 'WanTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'WanImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'UMT5EncoderModel', None),
dit_cls=getpipe(diffusers, 'WanTransformer3DModel', None)),
Model(name='WAN 2.2 A14B T2V',
url='https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B-Diffusers',
repo='Wan-AI/Wan2.2-T2V-A14B-Diffusers',
repo_cls=getattr(diffusers, 'WanPipeline', None),
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(diffusers, 'WanTransformer3DModel', None),
repo_cls=getpipe(diffusers, 'WanPipeline', None),
te_cls=getpipe(transformers, 'UMT5EncoderModel', None),
dit_cls=getpipe(diffusers, 'WanTransformer3DModel', None),
dit_folder=("transformer", "transformer_2")),
Model(name='WAN 2.2 A14B I2V',
url='https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers',
repo='Wan-AI/Wan2.2-I2V-A14B-Diffusers',
repo_cls=getattr(diffusers, 'WanImageToVideoPipeline', None),
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(diffusers, 'WanTransformer3DModel', None),
repo_cls=getpipe(diffusers, 'WanImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'UMT5EncoderModel', None),
dit_cls=getpipe(diffusers, 'WanTransformer3DModel', None),
dit_folder=("transformer", "transformer_2")),
Model(name='WAN 2.2 A14B SDNQ T2V',
url='https://huggingface.co/Disty0/Wan2.2-T2V-A14B-SDNQ-uint4-svd-r32',
repo='Disty0/Wan2.2-T2V-A14B-SDNQ-uint4-svd-r32',
repo_cls=getattr(diffusers, 'WanPipeline', None),
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(diffusers, 'WanTransformer3DModel', None),
repo_cls=getpipe(diffusers, 'WanPipeline', None),
te_cls=getpipe(transformers, 'UMT5EncoderModel', None),
dit_cls=getpipe(diffusers, 'WanTransformer3DModel', None),
dit_folder=("transformer", "transformer_2")),
Model(name='WAN 2.2 A14B SDNQ I2V',
url='https://huggingface.co/Disty0/Wan2.2-I2V-A14B-SDNQ-uint4-svd-r32',
repo='Disty0/Wan2.2-I2V-A14B-SDNQ-uint4-svd-r32',
repo_cls=getattr(diffusers, 'WanImageToVideoPipeline', None),
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(diffusers, 'WanTransformer3DModel', None),
repo_cls=getpipe(diffusers, 'WanImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'UMT5EncoderModel', None),
dit_cls=getpipe(diffusers, 'WanTransformer3DModel', None),
dit_folder=("transformer", "transformer_2")),
Model(name='WAN 2.2 14B VACE',
url='https://huggingface.co/linoyts/Wan2.2-VACE-Fun-14B-diffusers',
repo='linoyts/Wan2.2-VACE-Fun-14B-diffusers',
repo_cls=getattr(diffusers, 'WanVACEPipeline', None),
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(diffusers, 'WanVACETransformer3DModel', None),
repo_cls=getpipe(diffusers, 'WanVACEPipeline', None),
te_cls=getpipe(transformers, 'UMT5EncoderModel', None),
dit_cls=getpipe(diffusers, 'WanVACETransformer3DModel', None),
dit_folder=("transformer", "transformer_2")),
Model(name='WAN 2.1 1.3B T2V',
url='https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B-Diffusers',
repo='Wan-AI/Wan2.1-T2V-1.3B-Diffusers',
repo_cls=getattr(diffusers, 'WanPipeline', None),
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(diffusers, 'WanTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'WanPipeline', None),
te_cls=getpipe(transformers, 'UMT5EncoderModel', None),
dit_cls=getpipe(diffusers, 'WanTransformer3DModel', None)),
Model(name='WAN 2.1 14B T2V',
url='https://huggingface.co/Wan-AI/Wan2.1-T2V-14B-Diffusers',
repo='Wan-AI/Wan2.1-T2V-14B-Diffusers',
repo_cls=getattr(diffusers, 'WanPipeline', None),
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(diffusers, 'WanTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'WanPipeline', None),
te_cls=getpipe(transformers, 'UMT5EncoderModel', None),
dit_cls=getpipe(diffusers, 'WanTransformer3DModel', None)),
Model(name='WAN 2.1 14B I2V 480p',
url='https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-480P-Diffusers',
repo='Wan-AI/Wan2.1-I2V-14B-480P-Diffusers',
repo_cls=getattr(diffusers, 'WanImageToVideoPipeline', None),
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(diffusers, 'WanTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'WanImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'UMT5EncoderModel', None),
dit_cls=getpipe(diffusers, 'WanTransformer3DModel', None)),
Model(name='WAN 2.1 14B I2V 720p',
url='https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-720P-Diffusers',
repo='Wan-AI/Wan2.1-I2V-14B-720P-Diffusers',
repo_cls=getattr(diffusers, 'WanImageToVideoPipeline', None),
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(diffusers, 'WanTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'WanImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'UMT5EncoderModel', None),
dit_cls=getpipe(diffusers, 'WanTransformer3DModel', None)),
Model(name='WAN 2.1 14B FLF2V 720p',
url='https://huggingface.co/Wan-AI/Wan2.1-FLF2V-14B-720P',
repo='Wan-AI/Wan2.1-FLF2V-14B-720P-diffusers',
repo_cls=getattr(diffusers, 'WanImageToVideoPipeline', None),
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(diffusers, 'WanTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'WanImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'UMT5EncoderModel', None),
dit_cls=getpipe(diffusers, 'WanTransformer3DModel', None)),
Model(name='WAN 2.1 VACE 1.3B',
url='https://huggingface.co/Wan-AI/Wan2.1-VACE-1.3B-diffusers',
repo='Wan-AI/Wan2.1-VACE-1.3B-diffusers',
repo_cls=getattr(diffusers, 'WanVACEPipeline', None),
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(diffusers, 'WanVACETransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'WanVACEPipeline', None),
te_cls=getpipe(transformers, 'UMT5EncoderModel', None),
dit_cls=getpipe(diffusers, 'WanVACETransformer3DModel', None)),
Model(name='WAN 2.1 VACE 14B',
url='https://huggingface.co/Wan-AI/Wan2.1-VACE-14B-diffusers',
repo='Wan-AI/Wan2.1-VACE-14B-diffusers',
repo_cls=getattr(diffusers, 'WanVACEPipeline', None),
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(diffusers, 'WanVACETransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'WanVACEPipeline', None),
te_cls=getpipe(transformers, 'UMT5EncoderModel', None),
dit_cls=getpipe(diffusers, 'WanVACETransformer3DModel', None)),
Model(name='WAN 2.2 Animate 14B',
url='https://huggingface.co/Wan-AI/Wan2.2-Animate-14B-Diffusers',
repo='Wan-AI/Wan2.2-Animate-14B-Diffusers',
repo_cls=getattr(diffusers, 'WanAnimatePipeline', None),
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(diffusers, 'WanAnimateTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'WanAnimatePipeline', None),
te_cls=getpipe(transformers, 'UMT5EncoderModel', None),
dit_cls=getpipe(diffusers, 'WanAnimateTransformer3DModel', None)),
],
'SkyReels V2': [
Model(name='None'),
Model(name='SkyReels-V2 T2V-DF 1.3B-540P',
url='https://huggingface.co/Skywork/SkyReels-V2-DF-1.3B-540P-Diffusers',
repo='Skywork/SkyReels-V2-DF-1.3B-540P-Diffusers',
repo_cls=getattr(diffusers, 'SkyReelsV2DiffusionForcingPipeline', None),
repo_cls=getpipe(diffusers, 'SkyReelsV2DiffusionForcingPipeline', None),
repo_revision='refs/pr/1',
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(diffusers, 'SkyReelsV2Transformer3DModel', None)),
te_cls=getpipe(transformers, 'UMT5EncoderModel', None),
dit_cls=getpipe(diffusers, 'SkyReelsV2Transformer3DModel', None)),
Model(name='SkyReels-V2 T2V-DF 14B-720P',
url='https://huggingface.co/Skywork/SkyReels-V2-DF-14B-720P-Diffusers',
repo='Skywork/SkyReels-V2-DF-14B-720P-Diffusers',
repo_cls=getattr(diffusers, 'SkyReelsV2DiffusionForcingPipeline', None),
repo_cls=getpipe(diffusers, 'SkyReelsV2DiffusionForcingPipeline', None),
repo_revision='refs/pr/1',
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(diffusers, 'SkyReelsV2Transformer3DModel', None)),
te_cls=getpipe(transformers, 'UMT5EncoderModel', None),
dit_cls=getpipe(diffusers, 'SkyReelsV2Transformer3DModel', None)),
Model(name='SkyReels-V2 I2V-DF 14B-720P',
url='https://huggingface.co/Skywork/SkyReels-V2-DF-14B-720P-Diffusers',
repo='Skywork/SkyReels-V2-DF-14B-720P-Diffusers',
repo_cls=getattr(diffusers, 'SkyReelsV2DiffusionForcingImageToVideoPipeline', None),
repo_cls=getpipe(diffusers, 'SkyReelsV2DiffusionForcingImageToVideoPipeline', None),
repo_revision='refs/pr/1',
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(diffusers, 'SkyReelsV2Transformer3DModel', None)),
te_cls=getpipe(transformers, 'UMT5EncoderModel', None),
dit_cls=getpipe(diffusers, 'SkyReelsV2Transformer3DModel', None)),
Model(name='SkyReels-V2 T2V 14B-720P',
url='https://huggingface.co/Skywork/SkyReels-V2-T2V-14B-720P-Diffusers',
repo='Skywork/SkyReels-V2-T2V-14B-720P-Diffusers',
repo_cls=getattr(diffusers, 'SkyReelsV2Pipeline', None),
repo_cls=getpipe(diffusers, 'SkyReelsV2Pipeline', None),
repo_revision='refs/pr/1',
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(diffusers, 'SkyReelsV2Transformer3DModel', None)),
te_cls=getpipe(transformers, 'UMT5EncoderModel', None),
dit_cls=getpipe(diffusers, 'SkyReelsV2Transformer3DModel', None)),
Model(name='SkyReels-V2 I2V 14B-720P',
url='https://huggingface.co/Skywork/SkyReels-V2-I2V-14B-720P-Diffusers',
repo='Skywork/SkyReels-V2-I2V-14B-720P-Diffusers',
repo_cls=getattr(diffusers, 'SkyReelsV2ImageToVideoPipeline', None),
repo_cls=getpipe(diffusers, 'SkyReelsV2ImageToVideoPipeline', None),
repo_revision='refs/pr/1',
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(diffusers, 'SkyReelsV2Transformer3DModel', None)),
te_cls=getpipe(transformers, 'UMT5EncoderModel', None),
dit_cls=getpipe(diffusers, 'SkyReelsV2Transformer3DModel', None)),
],
'Mochi Video': [
Model(name='None'),
Model(name='Mochi 1 T2V',
url='https://huggingface.co/genmo/mochi-1-preview',
repo='genmo/mochi-1-preview',
repo_cls=getattr(diffusers, 'MochiPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'MochiTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'MochiPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'MochiTransformer3DModel', None)),
],
'Latte Video': [
Model(name='None'),
Model(name='Latte 1 T2V',
url='https://huggingface.co/maxin-cn/Latte-1',
repo='maxin-cn/Latte-1',
repo_cls=getattr(diffusers, 'LattePipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'LatteTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'LattePipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'LatteTransformer3DModel', None)),
],
'Allegro Video': [
Model(name='None'),
Model(name='Allegro T2V',
url='https://huggingface.co/rhymes-ai/Allegro',
repo='rhymes-ai/Allegro',
repo_cls=getattr(diffusers, 'AllegroPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'AllegroTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'AllegroPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'AllegroTransformer3DModel', None)),
],
'Cog Video': [
Model(name='None'),
Model(name='CogVideoX 1.0 2B T2V',
url='https://huggingface.co/THUDM/CogVideoX-2b',
repo='THUDM/CogVideoX-2b',
repo_cls=getattr(diffusers, 'CogVideoXPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'CogVideoXTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'CogVideoXPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'CogVideoXTransformer3DModel', None)),
Model(name='CogVideoX 1.0 5B T2V',
url='https://huggingface.co/THUDM/CogVideoX-5b',
repo='THUDM/CogVideoX-5b',
repo_cls=getattr(diffusers, 'CogVideoXPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'CogVideoXTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'CogVideoXPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'CogVideoXTransformer3DModel', None)),
Model(name='CogVideoX 1.0 5B I2V',
url='https://huggingface.co/THUDM/CogVideoX-5b-I2V',
repo='THUDM/CogVideoX-5b-I2V',
repo_cls=getattr(diffusers, 'CogVideoXImageToVideoPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'CogVideoXTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'CogVideoXImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'CogVideoXTransformer3DModel', None)),
Model(name='CogVideoX 1.5 5B T2V',
url='https://huggingface.co/THUDM/CogVideoX1.5-5B',
repo='THUDM/CogVideoX1.5-5B',
repo_cls=getattr(diffusers, 'CogVideoXPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'CogVideoXTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'CogVideoXPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'CogVideoXTransformer3DModel', None)),
Model(name='CogVideoX 1.5 5B I2V',
url='https://huggingface.co/THUDM/CogVideoX1.5-5B-I2V',
repo='THUDM/CogVideoX1.5-5B-I2V',
repo_cls=getattr(diffusers, 'CogVideoXImageToVideoPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'CogVideoXTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'CogVideoXImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'CogVideoXTransformer3DModel', None)),
Model(name='Index Anisora 1.0 5B I2V',
url='https://huggingface.co/Disty0/Index-anisora-5B-diffusers',
repo='Disty0/Index-anisora-5B-diffusers',
repo_cls=getattr(diffusers, 'CogVideoXImageToVideoPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'CogVideoXTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'CogVideoXImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'CogVideoXTransformer3DModel', None)),
Model(name='Index Anisora 1.0 5B RL I2V',
url='https://huggingface.co/Disty0/Index-anisora-5B_RL-diffusers',
repo='Disty0/Index-anisora-5B_RL-diffusers',
repo_cls=getattr(diffusers, 'CogVideoXImageToVideoPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'CogVideoXTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'CogVideoXImageToVideoPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'CogVideoXTransformer3DModel', None)),
],
'nVidia Cosmos': [
Model(name='nvidia Cosmos Predict2 2B I2V',
url='https://huggingface.co/nvidia/Cosmos-Predict2-2B-Text2Image',
repo='nvidia/Cosmos-Predict2-2B-Video2World',
repo_cls=getattr(diffusers, 'Cosmos2VideoToWorldPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'CosmosTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'Cosmos2VideoToWorldPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'CosmosTransformer3DModel', None)),
Model(name='nvidia Cosmos Predict2 2B I2V',
url='https://huggingface.co/nvidia/Cosmos-Predict2-2B-Text2Image',
repo='nvidia/Cosmos-Predict2-2B-Video2World',
repo_cls=getattr(diffusers, 'Cosmos2VideoToWorldPipeline', None),
te_cls=getattr(transformers, 'T5EncoderModel', None),
dit_cls=getattr(diffusers, 'CosmosTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'Cosmos2VideoToWorldPipeline', None),
te_cls=getpipe(transformers, 'T5EncoderModel', None),
dit_cls=getpipe(diffusers, 'CosmosTransformer3DModel', None)),
],
'nVidia SANA': [
Model(name='SANA Video 2B 480p T2V',
url='https://huggingface.co/Efficient-Large-Model/SANA-Video_2B_480p_diffusers',
repo='Efficient-Large-Model/SANA-Video_2B_480p_diffusers',
repo_cls=getattr(diffusers, 'SanaVideoPipeline', None),
te_cls=getattr(transformers, 'Gemma2Model', None),
dit_cls=getattr(diffusers, 'SanaVideoTransformer3DModel', None)),
repo_cls=getpipe(diffusers, 'SanaVideoPipeline', None),
te_cls=getpipe(transformers, 'Gemma2Model', None),
dit_cls=getpipe(diffusers, 'SanaVideoTransformer3DModel', None)),
],
'Kandinsky': [
Model(name='Kandinsky 5.0 Lite 5s SFT T2V',
url='https://huggingface.co/kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers',
repo='kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers',
repo_cls=getattr(diffusers, 'Kandinsky5T2VPipeline', None),
te_cls=getattr(transformers, 'Qwen2_5_VLForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'Kandinsky5Transformer3DModel', None)),
repo_cls=getpipe(diffusers, 'Kandinsky5T2VPipeline', None),
te_cls=getpipe(transformers, 'Qwen2_5_VLForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'Kandinsky5Transformer3DModel', None)),
Model(name='Kandinsky 5.0 Lite 5s CFG-distilled T2V',
url='https://huggingface.co/kandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-5s-Diffusers',
repo='kandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-5s-Diffusers',
repo_cls=getattr(diffusers, 'Kandinsky5T2VPipeline', None),
te_cls=getattr(transformers, 'Qwen2_5_VLForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'Kandinsky5Transformer3DModel', None)),
repo_cls=getpipe(diffusers, 'Kandinsky5T2VPipeline', None),
te_cls=getpipe(transformers, 'Qwen2_5_VLForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'Kandinsky5Transformer3DModel', None)),
Model(name='Kandinsky 5.0 Lite 5s Steps-distilled T2V',
url='https://huggingface.co/kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-5s-Diffusers',
repo='kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-5s-Diffusers',
repo_cls=getattr(diffusers, 'Kandinsky5T2VPipeline', None),
te_cls=getattr(transformers, 'Qwen2_5_VLForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'Kandinsky5Transformer3DModel', None)),
repo_cls=getpipe(diffusers, 'Kandinsky5T2VPipeline', None),
te_cls=getpipe(transformers, 'Qwen2_5_VLForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'Kandinsky5Transformer3DModel', None)),
Model(name='Kandinsky 5.0 Lite 10s SFT T2V',
url='https://huggingface.co/kandinskylab/Kandinsky-5.0-T2V-Lite-sft-10s-Diffusers',
repo='kandinskylab/Kandinsky-5.0-T2V-Lite-sft-10s-Diffusers',
repo_cls=getattr(diffusers, 'Kandinsky5T2VPipeline', None),
te_cls=getattr(transformers, 'Qwen2_5_VLForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'Kandinsky5Transformer3DModel', None)),
repo_cls=getpipe(diffusers, 'Kandinsky5T2VPipeline', None),
te_cls=getpipe(transformers, 'Qwen2_5_VLForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'Kandinsky5Transformer3DModel', None)),
Model(name='Kandinsky 5.0 Lite 10s CFG-distilled T2V',
url='https://huggingface.co/kandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-10s-Diffusers',
repo='kandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-10s-Diffusers',
repo_cls=getattr(diffusers, 'Kandinsky5T2VPipeline', None),
te_cls=getattr(transformers, 'Qwen2_5_VLForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'Kandinsky5Transformer3DModel', None)),
repo_cls=getpipe(diffusers, 'Kandinsky5T2VPipeline', None),
te_cls=getpipe(transformers, 'Qwen2_5_VLForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'Kandinsky5Transformer3DModel', None)),
Model(name='Kandinsky 5.0 Lite 10s Steps-distilled T2V',
url='https://huggingface.co/kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-10s-Diffusers',
repo='kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-10s-Diffusers',
repo_cls=getattr(diffusers, 'Kandinsky5T2VPipeline', None),
te_cls=getattr(transformers, 'Qwen2_5_VLForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'Kandinsky5Transformer3DModel', None)),
repo_cls=getpipe(diffusers, 'Kandinsky5T2VPipeline', None),
te_cls=getpipe(transformers, 'Qwen2_5_VLForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'Kandinsky5Transformer3DModel', None)),
Model(name='Kandinsky 5.0 Pro 5s SFT T2V',
url='https://huggingface.co/kandinskylab/Kandinsky-5.0-T2V-Pro-sft-5s-Diffusers',
repo='kandinskylab/Kandinsky-5.0-T2V-Pro-sft-5s-Diffusers',
repo_cls=getattr(diffusers, 'Kandinsky5T2VPipeline', None),
te_cls=getattr(transformers, 'Qwen2_5_VLForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'Kandinsky5Transformer3DModel', None)),
repo_cls=getpipe(diffusers, 'Kandinsky5T2VPipeline', None),
te_cls=getpipe(transformers, 'Qwen2_5_VLForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'Kandinsky5Transformer3DModel', None)),
Model(name='Kandinsky 5.0 Pro 5s SFT I2V',
url='https://huggingface.co/kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s-Diffusers',
repo='kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s-Diffusers',
repo_cls=getattr(diffusers, 'Kandinsky5I2VPipeline', None),
te_cls=getattr(transformers, 'Qwen2_5_VLForConditionalGeneration', None),
dit_cls=getattr(diffusers, 'Kandinsky5Transformer3DModel', None)),
repo_cls=getpipe(diffusers, 'Kandinsky5I2VPipeline', None),
te_cls=getpipe(transformers, 'Qwen2_5_VLForConditionalGeneration', None),
dit_cls=getpipe(diffusers, 'Kandinsky5Transformer3DModel', None)),
],
'Google Veo': [
Model(name='Google Veo 3.1 T2V',
pipelines/cosmos/safety_checker.py
+16
View File
@@ -0,0 +1,16 @@
class CosmosSafetyChecker:
def __init__(self):
from diffusers.utils import import_utils
import_utils._cosmos_guardrail_available = True # pylint: disable=protected-access
def __call__(self, *args, **kwargs): # pylint: disable=unused-argument
return
def to(self, _device):
pass
def check_text_safety(self, _prompt):
return True
def check_video_safety(self, vid):
return vid
pipelines/model_cosmos.py
+3 -19
View File
@@ -17,7 +17,9 @@ def load_cosmos_t2i(checkpoint_info, diffusers_load_config=None):
transformer = generic.load_transformer(repo_id, cls_name=diffusers.CosmosTransformer3DModel, load_config=diffusers_load_config, subfolder="transformer")
repo_te = 'nvidia/Cosmos-Predict2-2B-Text2Image' if 'Cosmos-Predict2-14B-Text2Image' in repo_id else repo_id
text_encoder = generic.load_text_encoder(repo_te, cls_name=transformers.T5EncoderModel, load_config=diffusers_load_config, subfolder="text_encoder", allow_shared=False) # cosmos does use standard t5
safety_checker = Fake_safety_checker()
from pipelines.cosmos.safety_checker import CosmosSafetyChecker
safety_checker = CosmosSafetyChecker()
if repo_id is None or repo_id.lower() == 'none':
return None
@@ -39,21 +41,3 @@ def load_cosmos_t2i(checkpoint_info, diffusers_load_config=None):
devices.torch_gc()
return pipe
class Fake_safety_checker:
def __init__(self):
from diffusers.utils import import_utils
import_utils._cosmos_guardrail_available = True # pylint: disable=protected-access
def __call__(self, *args, **kwargs): # pylint: disable=unused-argument
return
def to(self, _device):
pass
def check_text_safety(self, _prompt):
return True
def check_video_safety(self, vid):
return vid
requirements.txt
+4 -4
View File
@@ -23,14 +23,14 @@ ftfy
# versioned
fastapi==0.124.4
rich==15.0.0
safetensors==0.8.0rc0
safetensors==0.8.0
peft==0.19.1
httpx==0.28.1
requests==2.32.3
tqdm==4.67.3
accelerate==1.13.0
tqdm==4.68.2
accelerate==1.14.0
einops==0.8.1
huggingface_hub==1.18.0
huggingface_hub==1.19.0
hf_xet==1.5.1
numpy==2.1.2
pandas==2.3.1
webui.py
+4 -1
View File
@@ -391,7 +391,7 @@ def start_ui():
return app
def webui(restart=False):
def webui(restart=False, _exit=False):
if restart:
modules.script_callbacks.app_reload_callback()
modules.script_callbacks.script_unloaded_callback()
@@ -426,6 +426,9 @@ def webui(restart=False):
log.info(f"Startup time: {timer.startup.summary()}")
timer.startup.reset()
if _exit:
return None
if not restart:
# override all loggers to use the same handlers as the main logger
for log_item in [logging.getLogger(name) for name in logging.root.manager.loggerDict]: # pylint: disable=no-member