theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-18 22:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

vram optimization

Browse Source
This commit is contained in:
Artiprocher
2025-03-10 17:47:14 +08:00
parent a05f647633
commit e757013a14
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/wanvideo/README.md
View File

@@ -155,6 +155,10 @@ CUDA_VISIBLE_DEVICES="0" python examples/wanvideo/train_wan_t2v.py \
--use_gradient_checkpointing
```
If you wish to train the 14B model, please separate the safetensor files with a comma. For example: `models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00001-of-00006.safetensors,models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00002-of-00006.safetensors,models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00003-of-00006.safetensors,models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00004-of-00006.safetensors,models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00005-of-00006.safetensors,models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00006-of-00006.safetensors`.
For LoRA training, the Wan-1.3B-T2V model requires 16G of VRAM for processing 81 frames at 480P, while the Wan-14B-T2V model requires 60G of VRAM for the same configuration. To further reduce VRAM requirements by 20%-30%, you can include the parameter `--use_gradient_checkpointing_offload`.
Step 5: Test
Test LoRA: