Hunyuan Video is a text to video model.
Download the clip_l.safetensors and llava_llama3_fp8_scaled.safetensors files from here and put them in your ComfyUI/models/text_encoders directory.
Download the hunyuan_video_vae_bf16.safetensors file and put it in your ComfyUI/models/vae folder.
Download the hunyuan_video_t2v_720p_bf16.safetensors file and put it in your ComfyUI/models/diffusion_models folder.
This model can also generate still images by setting the video length to 1.
You can download this webp animated image and load it or drag it on ComfyUI to get the workflow.
Download the llava_llama3_vision.safetensors file and put it in your ComfyUI/models/clip_vision/ folder.
There are two different models you can choose from which give different results.
This first model follows the guiding image less than the other one but might give better movement.
Download the hunyuan_video_image_to_video_720p_bf16.safetensors file and put it in your ComfyUI/models/diffusion_models/ folder.
You can download this webp animated image and load it or drag it on ComfyUI to get the workflow. The input image can be found on the flux page.
This second model follows the guiding image very closely but seems to be a bit less dynamic than the first one.
Download the hunyuan_video_v2_replace_image_to_video_720p_bf16.safetensors file and put it in your ComfyUI/models/diffusion_models/ folder.
You can download this webp animated image and load it or drag it on ComfyUI to get the workflow. The input image can be found on the flux page.