search

pixeli99 / SVD_Xtend

Stable Video Diffusion Training Code and Extensions.
574 stars 55 forks source link

Support more conditional inputs, such as layout #10

Closed zhw-zhang closed 9 months ago

zhw-zhang commented 9 months ago

Hello, I saw a "Support more conditional inputs, such as layout" in the to-do list. What does this mean. Is it that the first frame + the BB trajectory of the subsequent frames are given to guide video generation? When will it probably be online?

pixeli99 commented 9 months ago

Yes, you are right, I plan to support this feature, to enable trajectory to video controlled generation, just like what layout2image does. If everything goes smoothly, a usable model should be released before New Year's Day.

zhw-zhang commented 9 months ago

ok, looking forward to your work.

zhw-zhang commented 9 months ago

Hi, I haven't seen the update of this project. Have you encountered any problems? Maybe we can solve it together.