LocalLLaMA

3 readers

1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago

MODERATORS

communick@poweruser.forum

Stable Diffusion - Video - New models ! (alien.top)

submitted 11 months ago by super-helper@alien.top to c/localllama@poweruser.forum

2 comments fedilink hide all child comments

Stable Video Diffusion Image-to-Video Model

(SVD) Image-to-Video is a latent diffusion model trained to generate short video clips from an image conditioning. This model was trained to generate 25 frames at resolution 576x1024 given a context frame of the same size, finetuned from SVD Image-to-Video [14 frames]. We also finetune the widely used f8-decoder for temporal consistency. For convenience, we additionally provide the model with the standard frame-wise decoder here.

https://stability.ai/news/stable-video-diffusion-open-ai-video-model

top 2 comments

sorted by: hot top controversial new old

[–] a_beautiful_rhind@alien.top 1 points 11 months ago

I can make stuff like that with deforum. The real deal video models have all been terrible resolution or paid API :(

So here is hoping.

[–] paryska99@alien.top 1 points 11 months ago

Oh wow, I know the results are probably cherry picked, but this still seems like such a step-up.