WorkflowListedExternal

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...

Sourcecivitai.com/models/1048302

TaskText to videoFamilyHunyuanEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access: External workflow
Status: Listed
Source: Civitai
Updated: Sep 5, 2026

Source description

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:

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

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.

Flow

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

Inputs and outputs

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.

Setup

The listing advises updating ComfyUI before use.
Suggestion · not verified
The description says this native ComfyUI implementation needs no special installations.

Dependencies

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.

Configuration

For the result described in the listing, it advises guidance up to 10; the base workflow uses lower guidance because some prompts caused burning.
Suggestion · not verified

Cautions

Before use, verify that the listed model files and nodes are available in your ComfyUI setup.
Suggestion · not verified
The description says this implementation has fewer features than the wrapper node, and no license is specified.

Does this need to be edited?

Sources

1 source

CivitaiPrimary

civitai.com/models/1048302

Verified Jul 20

Source excerpts

1 excerpt

NoteJul 20civitai.com/models/1048302

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