Shotcraft
Video generation

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 that upscales to 1080p.

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

Up to
5 seconds
Resolution
1080p via super-resolution (480p/720p native)
Weights
Downloadable
API
Yes
Commercial use
Permitted subject to conditions

Native generation is 121 frames at 24 fps (about 5 seconds), with longer output via progressive generation. Distilled, step-distilled and sparse-attention variants are published for faster inference.

Commercial use — Permitted subject to conditions

Tencent Hunyuan Community License Agreement, not Apache-2.0 despite many blog posts saying otherwise. Commercial use is permitted, but not in the EU, UK or South Korea.

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

  • The licence does not apply in some territories. The licence states in capitals that it does not apply in the European Union, United Kingdom and South Korea.
  • Permission required above a user threshold. Tencent's explicit permission is required above 100 million monthly active users.
  • Output may not be used to train AI. The works may not be used to improve any other AI model.

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 strong: the figures came from pages we retrieved and read. Check the vendor's current documentation

What it takes in
text, image
What it makes
video
Maximum duration
5 seconds
Maximum resolution
1080p via super-resolution (480p/720p native)
Aspect ratios
not established
Controls
text prompt, reference image, resolution tier, super-resolution stage toggle, CFG-distilled and step-distilled modes, sparse attention, model offloading, fp8 GEMM inference, seed
Weights
Downloadable
API
Yes
Pricing
Free open weights under the Tencent Hunyuan Community License. Self-hosting is unusually accessible for the quality: minimum about 14GB GPU memory with model offloading enabled, and the step-distilled model generates within roughly 75 seconds on an RTX 4090. Tencent also sells hosted access through Tencent Cloud.
Released or updated
2025-11-20

Supported aspect ratios is not established here. That means no page we could retrieve stated it, not that the model lacks one.

Strengths

  • Best quality-per-parameter in open video; 8.3B with 480p/720p native and 1080p upscale
  • Runs from about 14GB VRAM with offloading, so genuinely consumer-viable
  • Training code published, not just inference
  • Official distilled and sparse-attention variants
  • Both T2V and I2V in one family

Weaknesses

  • License excludes the EU, UK and South Korea entirely - a hard blocker for European deployment
  • 100M MAU ceiling requires Tencent permission
  • Cannot be used to improve other models, which restricts distillation and synthetic-data work
  • Native clips are only ~5 seconds
  • Widely misreported as Apache-2.0, creating compliance risk

Best for

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.

What to understand before using it

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

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.

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 (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

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.