Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-20 01:31:13 +02:00
Code Issues Packages Projects Releases Wiki Activity

add wan-2.2-sdnq pre-quant to video models

Browse Source 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
This commit is contained in:
Vladimir Mandic
2025-10-28 11:12:42 -04:00
parent 46876060ab
commit df4571588b
2 changed files with 15 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+1
View File
@@ -16,6 +16,7 @@
- **Reference** networks section is now split into actual *Base* models plus:
- **Quantized**: pre-quantized variants of the base models using SDNQ-SVD quantization for optimal quality and smallest possible resource usage
examples: *FLUX.1-Dev/Krea/Kontext/Schnell, Qwen-Image/Edit/2509, Chroma1-HD, WAN-2.2-A44B, etc.*
*note*: pre-quantized *WAN-2.2-14B* is also available in video models and runs with only 12GB VRAM!
- **Distilled**: distilled variants of base models
examples: *Turbo, Lightning, Lite, SRPO, Distill, Pruning, etc.*
- **Community**: community highlights
modules/video_models/models_def.py
+14
View File
@@ -179,6 +179,20 @@ try:
te_cls=getattr(transformers, 'UMT5EncoderModel', None),
dit_cls=getattr(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),
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),
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',