theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-24 01:48:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #41 from modelscope/ExVideo

Browse Source 
update ExVideo doc
This commit is contained in:
Artiprocher
2024-06-21 12:48:50 +08:00
committed by GitHub
parent 7d33082d70 0c94dfc4a3
commit 2c549598d0
1 changed files with 1 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/ExVideo/README.md
View File

@@ -3,7 +3,6 @@
ExVideo is a post-tuning technique aimed at enhancing the capability of video generation models. We have extended Stable Video Diffusion to achieve the generation of long videos up to 128 frames. ExVideo is a post-tuning technique aimed at enhancing the capability of video generation models. We have extended Stable Video Diffusion to achieve the generation of long videos up to 128 frames.
* [Project Page](https://ecnu-cilab.github.io/ExVideoProjectPage/) * [Project Page](https://ecnu-cilab.github.io/ExVideoProjectPage/)
* [Source Code](https://github.com/modelscope/DiffSynth-Studio)
* [Technical report](https://arxiv.org/abs/2406.14130) * [Technical report](https://arxiv.org/abs/2406.14130)
* Extended models * Extended models
* [HuggingFace](https://huggingface.co/ECNU-CILab/ExVideo-SVD-128f-v1) * [HuggingFace](https://huggingface.co/ECNU-CILab/ExVideo-SVD-128f-v1)
@@ -78,4 +77,4 @@ python ExVideo_ema.py --output_path "path/to/save/models/lightning_logs/version_
* Step 6: Enjoy your model * Step 6: Enjoy your model
The EMA model is at `path/to/save/models/lightning_logs/version_xx/checkpoints/epoch=0-step=25-ema.safetensors`. Load it in [ExVideo_svd_test.py](./ExVideo_svd_test.py) and then enjoy your model. The EMA model is at `path/to/save/models/lightning_logs/version_xx/checkpoints/epoch=xx-step=yyy-ema.safetensors`. Load it in [ExVideo_svd_test.py](./ExVideo_svd_test.py) and then enjoy your model.