Video generation

HunyuanVideo-Avatar

Name: HunyuanVideo-Avatar
Author: Tencent Hunyuan

Audio-driven human animation built on HunyuanVideo.

A video generation model by Tencent Hunyuan · read 2026-08-14 · sourcing low

Resolution: 704x768 (documented; card states arbitrary scales supported)
Weights: Downloadable
API: No
Commercial use: Permitted subject to conditions

Given a character image and an audio track it generates emotion-controllable dialogue video, and supports multi-character scenes and non-photoreal styles such as cartoon and 3D-rendered avatars. Documented at scales including 704x768 and 129 frames.

Commercial use — Permitted subject to conditions

The repository ships a LICENSE.txt that was not opened during research. The HunyuanVideo family convention is the Tencent community licence, so treat these terms as inferred from the family rather than read.

Not licensed in: European Union, United Kingdom, South Korea

Terms inferred from the model family, not read directly. This repository's licence text was not independently opened during the research pass, so the exact terms are family convention rather than directly verified.
The licence does not apply in some territories. The family licence does not apply in the EU, UK or South Korea.
Permission required above a user threshold. Permission required above 100M MAU.

This entry was written by hand from the licence wording quoted above, because the source dataset's yes/no field was misleading here. Read the licence before you rely on any of this. Nothing on this page is legal advice, and this site does not tell you a model is cleared for commercial use.

Specification

Vendor figures, read 2026-08-14Read from Tencent Hunyuan's own documentation on 2026-08-14. Vendors change these between model versions without announcing it, so check theirs before you commit a shot to a number. Sourcing for this entry is thin. Treat it as a starting point and verify before relying on any figure. Check the vendor's current documentation

What it takes in: image, audio, text
What it makes: video
Maximum duration: not established
Maximum resolution: 704x768 (documented; card states arbitrary scales supported)
Aspect ratios: not established
Controls: character image, driving audio, emotion control, multi-character input, text prompt, TeaCache acceleration, single-GPU low-memory mode
Weights: Downloadable
API: No
Pricing: Free open weights. Self-hosting: minimum about 24GB for 704x768 at 129 frames, about 96GB recommended for best quality, and as low as roughly 10GB in single-GPU mode with TeaCache optimization per the README. apiAvailable is set false because a first-party Tencent Cloud API endpoint serving this specific open checkpoint was not verified; third-party hosts (Replicate, fal) offer it, which does not count as a first-party API.
Released or updated: 2025-05-28

Maximum duration and supported aspect ratios are not established here. That means no page we could retrieve stated them, not that the model lacks them.

Strengths

Emotion-controllable audio-driven avatars, including multi-character scenes
Works on stylized and non-photoreal characters, not just photographs
Runs from about 10-24GB with optimizations, unusually light for the family

Weaknesses

License terms inherited by convention rather than clearly stated on the repo landing page
Territorial exclusion applies if the family license holds
Obvious deepfake misuse surface with no consent mechanism
Frame rate and hard duration limits undocumented

Best for

Self-hosted talking-head, dubbing and virtual-presenter pipelines outside the excluded territories.

Where the sources disagree

Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.

License file not directly read for this repository; assumed to match the Tencent Hunyuan Community License used across the family. Flagged as the weakest license verification in this dataset.

What to understand before using it

Explainers naming the mechanisms this model's own documentation mentions.

Character and set consistency: the weakest link names “character”
Camera control: a move without a camera names “control”
Conditioning and control: everything you hand the model besides noise names “control”

MCP servers that front Tencent Hunyuan

Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.

3daistudio 3D and animation
MCP server for 3D AI Studio, generate 3D models from text or images using Hunyuan and TRELLIS.
Corent Image generation
Generate images and videos via the Corent API, auto model routing with provider fallback.
PicoBerry 3D and animation
Generate game-ready 3D models, images, and animations. Multi-engine, one API.
Picsart GenAI Image generation
Generate and edit images, videos and audio with 150+ AI models.
Replicate Image generation
Replicate MCP server - image, video, audio, speech, LLM, vision, upscale, 3D, training. 36 tools.
Shortgenius Video generation
Generate AI short-form videos and auto-publish them to TikTok, YouTube, Instagram, Facebook and X.

See it from the vendor

Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.

Nearby in the directory

HunyuanVideo 1.5

An 8.3B-parameter video model covering both text-to-video and image-to-video, released with 480p and 720p checkpoints plus a super-resolution stage th

Video generation

HunyuanVideo (13B)

Tencent's original open video foundation model, with over 13 billion parameters - the largest open-weights video model at its December 2024 release. G

Video generation

HunyuanVideo-I2V

An image-to-video adaptation of HunyuanVideo that uses a token-replace technique to condition on a reference image, emphasizing first-frame consistenc

Video generation

Sources

Read on 2026-08-14. A source that has changed since then will not be reflected here until the next pass.