pipeline_tag: image-to-video | |
# AnimateLCM-I2V for Fast Image-conditioned Video Generation in 4 steps. | |
AnimateLCM-I2V is a latent image-to-video consistency model finetuned with [AnimateLCM](https://huggingface.co/wangfuyun/AnimateLCM) following the strategy proposed in [AnimateLCM-paper](https://arxiv.org/abs/2402.00769) without requiring teacher models. | |
[AnimateLCM: Accelerating the Animation of Personalized Diffusion Models and Adapters with Decoupled Consistency Learning](https://arxiv.org/abs/2402.00769) by Fu-Yun Wang et al. | |
## Example-Video | |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/63e9e92f20c109718713f5eb/P3rcJbtTKYVnBfufZ_OVg.png) | |
<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/63e9e92f20c109718713f5eb/SMZ4DAinSnrxKsVEW8dio.mp4"></video> | |
For more details, please refer to our [[paper](https://arxiv.org/abs/2402.00769)] | [[code](https://github.com/G-U-N/AnimateLCM)] | [[proj-page](https://animatelcm.github.io/)] | [[civitai](https://civitai.com/models/310920/animatelcm-i2v-fast-image-to-video-generation)]. | |
<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/63e9e92f20c109718713f5eb/KCwSoZCdxkkmtDg1LuXsP.mp4"></video> | |