Will It Run AI
tencent

HunyuanVideo

Stable

by Tencent

Large-scale video generation model from Tencent. 13B parameter 3D DiT with Hunyuan-Large MLLM text encoder (~7B, not T5-based). Strong motion quality and visual fidelity up to 720p.

  • 13B params for high visual fidelity
  • Up to 720p resolution
  • Strong motion quality and temporal coherence
  • Up to 129 frames per generation

Your hardware

Detecting...

Parameters13B
Max Resolution1280×720
Max Frames129
FPS24
Architecture3D-DIT
Licensetencent-hunyuan-community

Image Quality Benchmarks

Measured quality metrics for HunyuanVideo outputs.

Human Preference Score85%

How often humans prefer this model's output (0-100%)

Aesthetic Score7.5

Visual quality and composition rating (5-9 scale)

This model requires 22+ GB VRAM for basic video generation. A GPU with 24GB+ VRAM is recommended.

VRAM by Scenario

VRAM estimates at FP16 and FP8 precision. FP8 uses ~40% less memory with minimal quality loss. Grade shows how well each GPU handles the generation workload.

FP16 (full precision)

ScenarioVRAMRTX 4090 24GBRTX 3060 12GBRTX 4060 8GBMacBook Pro M4 Pro 24GB
512×512 · 25 frames20.9 GBAFFF
768×512 · 25 frames21.9 GBAFFF
768×512 · 100 frames24.7 GBBFFF
1280×720 · 25 frames25.7 GBBFFF

FP8 (quantized — ~40% less VRAM)

ScenarioVRAMRTX 4090 24GBRTX 3060 12GBRTX 4060 8GBMacBook Pro M4 Pro 24GB
512×512 · 25 frames34.8 GBFFFF
768×512 · 25 frames37.7 GBFFFF
768×512 · 100 frames46.1 GBFFFF
1280×720 · 25 frames49.0 GBFFFF

Optimization Tips

Turbo / LCM distillation

Use distilled scheduler at 4-8 steps for faster iteration

Run with Python

Run with Python (diffusers)
from diffusers import HunyuanVideoPipeline
import torch

pipe = HunyuanVideoPipeline.from_pretrained(
    "tencent/HunyuanVideo",
    torch_dtype=torch.float16
)
pipe.to("cuda")

frames = pipe(
    prompt="your prompt here",
    num_inference_steps=50,
    guidance_scale=6.0,
    num_frames=129,
).frames[0]
# Save frames or export as video

Get started

Setup instructions for running HunyuanVideo locally

1. Download the model

Get the checkpoint from HuggingFace

2. Place in:

ComfyUI/models/checkpoints/

3. Launch ComfyUI

python main.py
Note: Video generation requires video output nodes. Install ComfyUI-VideoHelperSuite from the ComfyUI Manager for SaveAnimatedWEBP or VHS_VideoCombine nodes.

Memory Breakdown

VRAM allocation for 25 frames at 768×512 on RTX 4090 24GB

Required: 21.9 GBAvailable: 24.0 GB
Weights26.0 GB
VAE0.2 GB
Text Encoder14.0 GB
Activations6.0 GB
Overhead0.5 GB

Estimated Generation Time

25 frames at 768×512, 30 steps, FP16.

RTX 4090 24GB~3m 3s
RTX 3060 12GB~11m 33s
RTX 4060 8GB~17m 25s
MacBook Pro M4 Pro 24GB~24m 45s

Sample Outputs

Available Formats & Downloads

Download HunyuanVideo in different precisions. Lower precision = less VRAM but slight quality loss.

格式精度大小提供商
safetensors推荐FP1626.0 GBofficial下载

LoRA Ecosystem

Growing Ecosystem

Growing LoRA ecosystem with character and style LoRAs.

Related Workflows

You might also like

Frequently asked questions

FAQ — HunyuanVideo

How much VRAM does HunyuanVideo need for video?

HunyuanVideo (13B parameters) requires approximately 21.9 GB of VRAM at FP16 precision for generating 25 frames at 768×512. Video generation typically requires more VRAM than image generation due to temporal attention layers.

Can I run HunyuanVideo on RTX 4090?

Yes, the RTX 4090 (24 GB VRAM) can run HunyuanVideo at FP16. Expected generation time is around ~3m 3s for a 25-frame clip.

How long does it take to generate a video with HunyuanVideo?

On a reference GPU (RTX 4090 24GB), HunyuanVideo generates a 25-frame video at 768×512 in approximately ~3m 3s at FP16 with 30 inference steps. Faster GPUs with higher memory bandwidth will reduce generation time.

What resolution and frame count does HunyuanVideo support?

HunyuanVideo supports up to 1280×720 resolution and 129 frames per generation at 24 FPS. Higher resolutions and frame counts require proportionally more VRAM.

About HunyuanVideo

Use cases
video-generationtext-to-video
Recommended runtimes
comfyuidiffusers

See also