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

[LoRA] Support v1 LoRA training (#576)

Browse Source
This commit is contained in:
Wenxuan Tan
2025-07-17 15:52:09 -05:00
committed by GitHub
parent 576c214f28
commit bb8c769c8e
38 changed files with 757 additions and 140 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/source/training/data_preprocess.md
+1 -1
View File
@@ -7,7 +7,7 @@ To save GPU memory, we precompute text embeddings and VAE latents to eliminate t
We provide a sample dataset to help you get started. Download the source media using the following command:
```bash
python scripts/huggingface/download_hf.py --repo_id=FastVideo/mini_i2v_dataset --local_dir=FastVideo/mini_i2v_dataset --repo_type=dataset
python scripts/huggingface/download_hf.py --repo_id=FastVideo/mini_i2v_dataset --local_dir=data/mini_i2v_dataset --repo_type=dataset
```
The folder `crush-smol_raw/` contains raw videos and captions for testing preprocessing, while `crush-smol_preprocessed/` contains latents prepared for testing training.