We release the model weights of our best training in fp32, fp16 ckpt and safetensors format.
The model is trained on the Webvid-10M dataset on a 8 A100 node for 20h.
You can use the gradio interface on our
HuggingFace Space.
You can also use the inference script in our
Github repository to test the released model.
Please note that the model is really sensitive to the input video framerate. You should try downsampling the video to 8fps before using it if you don't get the desired results.
We are working on improving OnlyFlow and train it for other base model than AnimateDiff.
Obvious Research is an Artificial Intelligence research laboratory dedicated to creating new AI artistic tools, initiated by the artists’ trio
Obvious, in partnership with La Sorbonne Université.
1@inproceedings{koroglu2025onlyflow,
2 title={Onlyflow: Optical flow based motion conditioning for video diffusion models},
3 author={Koroglu, Mathis and Caselles-Dupr{\'e}, Hugo and Jeanneret, Guillaume and Cord, Matthieu},
4 booktitle={2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
5 pages={6216--6226},
6 year={2025},
7 organization={IEEE}
8}
