The files include MagicTime temporal lora merged into the animatediff v3 motion model, as well as their spatial lora converted to .safetensors format. Used together they work in ComfyUI and AnimatediffEvolved. Original sources:
https://huggingface.co/guoyww/animatediff/blob/main/v3_sd15_mm.ckpt
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.