WorkflowPublicadoExterno

HunyuanVideo 12GB VRAM Workflow — v1.0

With the native comfy implementation of Hunyuan I have tweaked the workflow to work for 12GB VRAM cards. It looks like you can get at least to 73 frames and probably a bit more. It takes about 8 minutes for a 4070Ti...

Fuentecivitai.com/models/1048302

TareaTexto a vídeoFamiliaHunyuanVRAM estimadaNot yet characterizedBcalidad

Perfil de ejecución

Acceso: Flujo externo
Estado: Publicado
Fuente: Civitai
Actualizado: 5 sept 2026

Descripción de la fuente

Do make sure to update your comfy and to get the exact result above the guidance I put up to 10 (I reduced it for the base workflow as it caused some burning for some prompts).

As its not as complete as the wrapper node there is a few less features than that for now. But there is also no crazy special installations that you need to do.

Links to model downloads here:

Comentario generado por IA

Explicación generada por IA basada en los detalles de la fuente y la configuración. Las sugerencias están claramente identificadas.

Propósito

This ComfyUI workflow is for generating Hunyuan Video clips: it takes text-conditioning input and the listed Hunyuan Video model files, then produces a combined video described as at least 73 frames, possibly more.

Flujo

The workflow stages named in the listing include text encoding, Hunyuan latent-video setup, advanced sampling, tiled VAE decoding, and video combining.

Entradas y salidas

The workflow is described as tweaked for graphics cards with 12GB VRAM.
The listing reports about 8 minutes for a 4070Ti to run 20 steps.

Configuración inicial

The listing advises updating ComfyUI before use.
Sugerencia · sin verificar
The description says this native ComfyUI implementation needs no special installations.

Dependencias

Listed model files include 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.
Other named nodes include RandomNoise, SamplerCustomAdvanced, UNETLoader, VAEDecodeTiled, VAELoader, and VHS_VideoCombine.

Configuración

For the result described in the listing, it advises guidance up to 10; the base workflow uses lower guidance because some prompts caused burning.
Sugerencia · sin verificar

Precauciones

Before use, verify that the listed model files and nodes are available in your ComfyUI setup.
Sugerencia · sin verificar
The description says this implementation has fewer features than the wrapper node, and no license is specified.

¿Es necesario editarlo?

Inicia sesión para solicitar una edición.

Fuentes

1 fuente

CivitaiPrincipal

civitai.com/models/1048302

Verificado 20 jul

Extractos de fuentes

1 extracto

Note20 julcivitai.com/models/1048302

Source context: 16736 downloads · Type Workflows · Base model Hunyuan Video