nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[self-forcing][8/n] Self-Forcing For Wan2.2-A14B + torch.compile training and distillation support (#818)

Browse Source 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
RandNMR73
2025-10-02 15:01:45 -07:00
committed by GitHub
co-authored by SolitaryThinker gemini-code-assist[bot]
parent 335afa4457
commit dc7596b973
32 changed files with 1679 additions and 495 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/distill/v1_distill_dmd_wan.sh
+2
View File
@@ -12,6 +12,8 @@ export TOKENIZERS_PARALLELISM=false
torchrun --nnodes 1 --nproc_per_node $NUM_GPUS \
fastvideo/training/wan_distillation_pipeline.py \
--model_path Wan-AI/Wan2.1-T2V-1.3B-Diffusers \
--real_score_model_path Wan-AI/Wan2.1-T2V-1.3B-Diffusers \
--fake_score_model_path Wan-AI/Wan2.1-T2V-1.3B-Diffusers \
--inference_mode False\
--pretrained_model_name_or_path Wan-AI/Wan2.1-T2V-1.3B-Diffusers \
--cache_dir "/home/ray/.cache" \
scripts/distill/v1_distill_dmd_wan_VSA.sh
+2
View File
@@ -13,6 +13,8 @@ export TOKENIZERS_PARALLELISM=false
torchrun --nnodes 1 --nproc_per_node $NUM_GPUS \
fastvideo/training/wan_distillation_pipeline.py \
--model_path Wan-AI/Wan2.1-T2V-1.3B-Diffusers \
--real_score_model_path Wan-AI/Wan2.1-T2V-1.3B-Diffusers \
--fake_score_model_path Wan-AI/Wan2.1-T2V-1.3B-Diffusers \
--inference_mode False\
--pretrained_model_name_or_path Wan-AI/Wan2.1-T2V-1.3B-Diffusers \
--cache_dir "/home/ray/.cache" \