WHY DON'T USE SVD AS YOUR BASE I2V MODEL

[GlTeee]

can we use SVD (https://github.com/Stability-AI/generative-models) as base i2v model?

[vinesmsuic]

There is a follow-up work (very similar to AnyV2V) that uses SVD as the base model.

I2VEdit: First-Frame-Guided Video Editing via Image-to-Video Diffusion Models

[vinesmsuic]

We encourage the community to submit a PR on SVD implementation of AnyV2V :)

[somuchtome]

We encourage the community to submit a PR on SVD implementation of AnyV2V :)

Hi~ Is there AnyV2V solution based on "animatediff"? I am not sure which layers' features should be extracted and at which timesteps the feature should be injected.