AnimateLCM-SVD-xt
AnimateLCM-SVD-xt is a consistency accelerated Stable Video Diffusion following the strategies proposed in AnimateLCM.
It can generate good image animations in 2~8 steps without requiring the classifier-free guidance (cfg).
Important Notes:
Default euler or heun might not generate good results, I have rewritten a noise scheduler to make it work. Need some extra time to integrate it into diffusers or ComfyUI.
For more details, please refer to https://github.com/G-U-N/AnimateLCM
Links
Contact: [email protected]
Description
FAQ
Comments (5)
Hi, is this a txt2gif model?
Wait for the ComfyUI Work，Thanks
I am getting an error - 'model.diffusion_model.input_blocks.0.0.weight
The resolution of the picture matches the resolution of the video im trying to generate. Not sure how to rectify
havent understood how to use this honestly, looking everywere without a clue. Swapping the SDV video model with this wont work in comfy
For those looking for a version that works on ComfyUI, Kijai released a version here: https://huggingface.co/Kijai/AnimateLCM-SVD-Comfy
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.