AnimateLCM-I2V for Fast Image-conditioned Video Generation in 4 steps.

AnimateLCM-I2V is a latent image-to-video consistency model finetuned with AnimateLCM following the strategy proposed in AnimateLCM-paper without requiring teacher models.

AnimateLCM: Accelerating the Animation of Personalized Diffusion Models and Adapters with Decoupled Consistency Learning by Fu-Yun Wang et al.

Example-Video

For more details, please refer to our [paper] | [code] | [proj-page] | [civitai].