HunyuanVideo 12GB VRAM Workflow

This ComfyUI workflow is for generating Hunyuan Video clips from a text prompt: it encodes the text and outputs a combined video, and it is described as tweaked for cards with 12GB of VRAM.

The graph encodes text, creates an empty Hunyuan latent video, samples it, decodes it with tiled VAE processing, and combines the result into a video.

The description says the output can reach at least 73 frames, possibly more.

The listing reports about 8 minutes for a 4070Ti to run 20 steps.

Before using it, update ComfyUI, as the description instructs.

Sugestão · não verificado

The native ComfyUI implementation is described as not requiring special installations.

Named model files are clip_l.safetensors, hunyuan_video_t2v_720p_bf16.safetensors, hunyuan_video_vae_bf16.safetensors, and llava_llama3_fp8_scaled.safetensors.

Named nodes include BasicGuider, BasicScheduler, CLIPTextEncode, DualCLIPLoader, EmptyHunyuanLatentVideo, FluxGuidance, KSamplerSelect, and ModelSamplingSD3.

It also names RandomNoise, SamplerCustomAdvanced, UNETLoader, VAEDecodeTiled, VAELoader, and VHS_VideoCombine.

If you are following the described setup, set guidance up to 10; the base workflow uses lower guidance because some prompts caused burning.

Sugestão · não verificado

Before use, verify that the listed model files and nodes are available in your ComfyUI setup.

Sugestão · não verificado

The description notes that this implementation has fewer features than the wrapper node.