Converted weights from diffusers to original format compatible with ComfyUI SVD Original weights from: https://huggingface.co/wangfuyun/AnimateLCM-SVD-xt
转载地址:https://huggingface.co/Kijai/AnimateLCM-SVD-Comfy/tree/main ,由@Kijai大佬转制权重。
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.
评论