# Tencent-Hunyuan/HunyuanVideo-1.5

HunyuanVideo-1.5: A leading lightweight video generation model

Repository: https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5
Canonical: https://ross.abutalabs.com/products/hunyuanvideo-15
Homepage: https://hunyuan.tencent.com/video/zh?tabIndex=0
Language: Python
License: NOASSERTION
License Family: other
Topics: image-to-video, text-to-video, video-generation
Last push: 2026-04-10T06:14:59+00:00

## Health v2 (maintenance only)
Score: 50/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 76, release rhythm 35, longevity 20
- inputs: {"age_days": 286, "days_push": 145, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4534, forks 218 (observed 2026-08-28T04:08:53.014959+00:00)

## What it is
HunyuanVideo-1.5 is Tencent's lightweight 8.3B-parameter video generation model supporting text-to-video and image-to-video synthesis. The repository provides inference code, step-distilled checkpoints, and ComfyUI integration so videos can be generated on consumer-grade GPUs like a single RTX 4090.

## Use cases
- generate videos from text prompts
- convert an image into a video
- run video generation on a consumer GPU
- create AI videos with ComfyUI workflows
- fast video generation with distilled few-step models
- self-host an open-source video generation model

## When to choose
- you need high-quality text-to-video or image-to-video generation on limited GPU hardware
- you want ComfyUI or step-distilled fast inference workflows
- you need a self-hosted alternative to closed video generation APIs

## When to avoid
- you need real-time video streaming or video editing rather than generation
- you lack a capable GPU and cannot use cloud inference
- you require a permissive license - the license is custom, not standard open source

## Facets
- artifact type: library
- maturity: active
- function: video-processing, machine-learning, deep-learning, llm-inference
- domain: artificial-intelligence, deep-learning, media
- platform: python
- tags: video-generation, text-to-video, image-to-video, diffusion-model, comfyui, consumer-gpu, step-distillation, tencent-hunyuan, video, gpu, linux, docker

## Member repositories
- Tencent-Hunyuan/HunyuanVideo-1.5 (main) score 50

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:53.014959+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:20:11.866503+00:00, confidence not recorded.
  - readme: https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5 (fetched 2026-08-28T04:08:53.014959+00:00, sha bd89641e01c4)
  - homepage: https://hunyuan.tencent.com/video/zh?tabIndex=0 (fetched 2026-08-29T09:05:55.171006+00:00, sha e9ec7b1723ad)
- Data as of 2026-08-30T08:39:29.467469+00:00.