wangfuyun/AnimateLCM-SVD-xt

Samples generated by AnimateLCM-SVD-xt

Introduction

Consistency Distilled Stable Video Diffusion Image2Video-XT (SVD-xt) following the strategy proposed in AnimateLCM-paper. AnimateLCM-SVD-xt can generate good quality image-conditioned videos with 25 frames in 2~8 steps with 576x1024 resolutions.

Computation comparsion

AnimateLCM-SVD-xt can generally produces demos with good quality in 4 steps without requiring the classifier-free guidance, and therefore can save 25 x 2 / 4 = 12.5 times compuation resources compared with normal SVD models.

Demos

2 steps, cfg=1	4 steps, cfg=1	8 steps, cfg=1
2 steps, cfg=1	4 steps, cfg=1	8 steps, cfg=1
2 steps, cfg=1	4 steps, cfg=1	8 steps, cfg=1
2 steps, cfg=1	4 steps, cfg=1	8 steps, cfg=1
2 steps, cfg=1	4 steps, cfg=1	8 steps, cfg=1

I have launched a gradio demo at AnimateLCM SVD space. Should you have any questions, please contact Fu-Yun Wang (fywang@link.cuhk.edu.hk). I might respond a bit later. Thank you!