Simple GGUF Hunyuan text2video workflow — v1.0

This ComfyUI workflow is for text-to-video generation: it encodes text with CLIPTextEncode, uses Hunyuan Video with a GGUF model, and saves animated WEBP output.

The named stages include text encoding, Hunyuan latent-video setup, advanced sampling, GGUF loading, VAE decoding, and animated WEBP saving.

The workflow names CLIPTextEncode for text encoding and SaveAnimatedWEBP for animated WEBP output.

It uses Hunyuan Video as its base model and names hunyuan-video-t2v-720p-Q4_1.gguf as its GGUF model file.

If ComfyUI reports a missing-node error, check that ComfyUI/nodes.py, ComfyUI/comfy_extras/nodes_hunyuan.py, and the GGUF node are updated.

Suggestion · non vérifié

The workflow description links to GGUF files at https://huggingface.co/city96/HunyuanVideo-gguf.

Named model files include clip_l.safetensors, hunyuan_video_vae_bf16.safetensors, hunyuan-video-t2v-720p-Q4_1.gguf, and llava_llama3_fp8_scaled.safetensors.

Named node types include CLIPTextEncode, DualCLIPLoader, EmptyHunyuanLatentVideo, KSamplerAdvanced, SaveAnimatedWEBP, UnetLoaderGGUF, VAEDecodeTiled, and VAELoader.

For GGUF loading, look for UnetLoaderGGUF and hunyuan-video-t2v-720p-Q4_1.gguf.

Suggestion · non vérifié

For text encoding, look for CLIPTextEncode, DualCLIPLoader, clip_l.safetensors, and llava_llama3_fp8_scaled.safetensors.

Suggestion · non vérifié

For VAE handling, look for VAELoader, VAEDecodeTiled, and hunyuan_video_vae_bf16.safetensors.

Suggestion · non vérifié

Before use, verify that the named model files and node types are present in your ComfyUI installation.

Suggestion · non vérifié

Verify the exact VAE and text-encoder files locally, including hunyuan_video_vae_bf16.safetensors, clip_l.safetensors, and llava_llama3_fp8_scaled.safetensors.

Suggestion · non vérifié