Diffusers
Safetensors
WanPipeline
PY007 commited on
Commit
3646c57
·
verified ·
1 Parent(s): 9664edc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -37,7 +37,7 @@ python setup_vsa.py install
37
  num_gpus=1
38
  export FASTVIDEO_ATTENTION_BACKEND=VIDEO_SPARSE_ATTN
39
  # change model path to local dir if you want to inference using your checkpoint
40
- export MODEL_BASE=Wan-AI/Wan2.1-T2V-1.3B-Diffusers
41
  # export MODEL_BASE=hunyuanvideo-community/HunyuanVideo
42
  fastvideo generate \
43
  --model-path $MODEL_BASE \
@@ -55,7 +55,7 @@ fastvideo generate \
55
  --prompt "A beautiful woman in a red dress walking down a street" \
56
  --negative-prompt "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards" \
57
  --seed 1024 \
58
- --output-path outputs_video_1.3B_VSA/sparsity_0.9/
59
  ```
60
  - Try it out on **FastVideo** — we support a wide range of GPUs from **H100** to **4090**
61
  - We use [FastVideo 720P Synthetic Wan dataset](https://huggingface.co/datasets/FastVideo/Wan-Syn_77x768x1280_250k) for training.
 
37
  num_gpus=1
38
  export FASTVIDEO_ATTENTION_BACKEND=VIDEO_SPARSE_ATTN
39
  # change model path to local dir if you want to inference using your checkpoint
40
+ export MODEL_BASE=FastVideo/Wan2.1-VSA-T2V-14B-720P-Diffusers
41
  # export MODEL_BASE=hunyuanvideo-community/HunyuanVideo
42
  fastvideo generate \
43
  --model-path $MODEL_BASE \
 
55
  --prompt "A beautiful woman in a red dress walking down a street" \
56
  --negative-prompt "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards" \
57
  --seed 1024 \
58
+ --output-path VSA-DMD/sparsity_0.9/
59
  ```
60
  - Try it out on **FastVideo** — we support a wide range of GPUs from **H100** to **4090**
61
  - We use [FastVideo 720P Synthetic Wan dataset](https://huggingface.co/datasets/FastVideo/Wan-Syn_77x768x1280_250k) for training.