Video generation

HunyuanVideo-I2V

Name: HunyuanVideo-I2V
Author: Tencent Hunyuan

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

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

Resolution: 720p
Weights: Downloadable
API: No
Commercial use: Permitted subject to conditions

Supports up to 720p and up to 129 frames, and includes a customizable-effects path via LoRA training. Offers stable and dynamic motion modes through a flow-shift parameter.

Commercial use — Permitted subject to conditions

Tencent Hunyuan Community License Agreement, same terms as the rest of the family.

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

The licence does not apply in some territories. The licence does not apply in the EU, UK or South Korea.
Permission required above a user threshold. Permission required above 100M MAU.
Output may not be used to train AI. The works may not be used to improve other AI models.

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 mixed. Some fields came from pages we retrieved, others could not be confirmed and are left blank. Check the vendor's current documentation

What it takes in: image, text
What it makes: video
Maximum duration: not established
Maximum resolution: 720p
Aspect ratios: not established
Controls: reference image, text prompt, flow-shift stable (7.0) vs dynamic (17.0) mode, video length up to 129 frames, inference steps, seed, LoRA effect training
Weights: Downloadable
API: No
Pricing: Free open weights under the Tencent Hunyuan Community License. Self-hosting needs about 60GB VRAM minimum with 80GB recommended for inference per the README; LoRA training at 360p is documented at about 79GB. 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: 2025-03-06

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

Strong first-frame fidelity via token-replace conditioning
Explicit stable vs dynamic motion control
LoRA path for custom effects
Tencent waives output rights

Weaknesses

60-80GB VRAM makes local use impractical
EU/UK/South Korea exclusion
129-frame cap with undocumented fps
Superseded by HunyuanVideo 1.5's I2V checkpoints

Best for

Self-hosted image-to-video with tight first-frame consistency, outside the excluded territories.

What to understand before using it

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

Conditioning and control: everything you hand the model besides noise names “conditioning”
Text encoders and conditioning: how a prompt steers the picture names “conditioning”
Character and set consistency: the weakest link names “consistency”
Temporal consistency: flicker, drift and morphing names “consistency”

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-Avatar

Audio-driven human animation built on HunyuanVideo. Given a character image and an audio track it generates emotion-controllable dialogue video, and s

Video generation

Sources

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