|
|
--- |
|
|
pipeline_tag: image-to-video |
|
|
--- |
|
|
|
|
|
## Introduction |
|
|
Consistency Distilled [Stable Video Diffusion Image2Video-XT (SVD-xt)](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt) following the strategy proposed in [AnimateLCM-paper](https://arxiv.org/abs/2402.00769). |
|
|
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 |
|
|
|
|
|
|
|
|
|
|
|
Please contact Fu-Yun Wang ([email protected]) for the inference code and the scheduler design. |
