HunyuanVideo-Avatar

▶ See it at the source

What they did

Tencent's audio-driven human animation model: give it an avatar image (any style or scale) and an audio track, and it produces dynamic, emotion-controllable talking or multi-character dialogue video.

Worth knowing

• Price: Open weights on Hugging Face
• Status: sourced. We have not run this ourselves yet (no "Tested" badge).
• Quality bar (computed by code): 5/5 (primary source ✓, reproducible ✓, new ✓, example output ✓, safe ✓)

Related

model▶ example at source

HunyuanVideo on fal

Tencent's open HunyuanVideo on fal, at a flat per-video price. fal notes it's free for commercial use.

HunyuanVideofal✓ vendor-checked

model▶ demo at source

HunyuanVideo-1.5

HunyuanVideo 1.5, Tencent's lighter open video model aimed at running on more accessible hardware.

Demo by Tencent-Hunyuan

HunyuanVideo★ 4,576● sourced

prompt▶ example at source

lanshu-awesome-ai-video-kit

A Chinese-language kit from enterprise video projects: hundreds of prompts across 15 models, Claude skills and methodology notes.

SeedanceKlingVeo★ 415● sourced

tool▶ example at source

LightX2V

A lightweight inference framework for text-to-video, image-to-video and image generation that supports several open models. There's also a hosted demo studio.

WanLTX VideoHunyuanVideo★ 2,897● sourced

workflow▶ demo at source

ComfyUI-HunyuanVideoWrapper

Kijai's ComfyUI wrapper for Tencent's HunyuanVideo, an early way to run it locally with memory optimisations.

Demo by kijai

ComfyUIHunyuanVideo★ 2,589● sourced

workflow▶ demo at source

ComfyUI-HunyuanLoom

Nodes for editing existing videos with HunyuanVideo (video-to-video) in ComfyUI.

Demo by logtd

ComfyUIHunyuanVideo★ 492● sourced