search

MyNiuuu / MOFA-Video

[ECCV 2024] MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model.
https://myniuuu.github.io/MOFA_Video
Other
640 stars 39 forks source link

只能得到25帧? #24

Open zdyshine opened 5 months ago

zdyshine commented 5 months ago

which means that the first 25 frames of the generated landmark sequences are used to obtain the result.

最终的结果只有25帧吗？可以获取更多帧吗？

YunjieYu commented 5 months ago

I have implemented a gradio that supports full video generation.

zdyshine commented 5 months ago

I have implemented a gradio that supports full video generation.

Is it modify here？ DragNUWA_net = Drag("cuda:0", target_size, target_size, 25)