[jszewczyk]

Hi there!

Which method is the best and similar to Kling AI for creating video from still images?

Thanks!

[Andrew]

Hi, for local generation, we have

• SVD
• Cogvideo I2V

For online,

• Kling
• RunwayML

There are probably others I missed. Last time I test, Kling was the best.

[jszewczyk]

Yes. Kling and RunwayML are awesome for me too.

I know SVD. Does anybody know how to control the camera and objects/heros, like using a motion brush or drawing the camera path?

I will check Cogvideo I2V. I hear about it for the first time.

[jszewczyk]

or load the first frame image and the last.

[Andrew]

SVD doesn’t use a prompt so there’s no way to specify camera motion.

I think you can do that with cogvideo. This workflow uses cogvideo image-to-video. You can get rid of the flux part to only use cogvideo.

https://stable-diffusion-art.com/flux-cogvideo-text-to-video/

[Author]

Posts