# Tencent-Hunyuan/HunyuanVideo-I2V

HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo

Repository: https://github.com/Tencent-Hunyuan/HunyuanVideo-I2V
Canonical: https://ross.abutalabs.com/products/hunyuanvideo-i2v
Homepage: https://video.hunyuan.tencent.com/
Language: Python
License: NOASSERTION
License Family: other
Topics: diffusion-models, image-to-video, image-to-video-generation, videogeneration
Last push: 2026-04-07T06:13:09+00:00

## Health v2 (maintenance only)
Score: 54/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 76, release rhythm 35, longevity 39
- inputs: {"age_days": 547, "days_push": 148, "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 1840, forks 196 (observed 2026-08-28T04:05:42.983570+00:00)

## What it is
HunyuanVideo-I2V is Tencent's open-source image-to-video generation framework built on the HunyuanVideo diffusion model, providing PyTorch model definitions, pre-trained weights, and inference code. It also includes LoRA training code for creating customizable video special effects.

## Use cases
- generate a video from a single still image
- animate photos with a text prompt
- train a LoRA for custom video special effects
- run image-to-video diffusion inference on GPUs
- speed up video generation with parallel inference
- create AI video effects from custom images

## When to choose
- you need state-of-the-art open-source image-to-video generation
- you want to fine-tune video effects with LoRA training
- you have GPU resources for large diffusion model inference
- you want customizable, prompt-driven video animation from images

## When to avoid
- you need lightweight or CPU-only video generation
- you want a polished end-user app rather than model code
- you cannot meet the high GPU/VRAM requirements
- you need a permissively licensed model for commercial use without review

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, video-processing, image-processing, llm-inference
- domain: deep-learning, artificial-intelligence, image-processing, media
- platform: python
- tags: diffusion-models, image-to-video, video-generation, lora-training, pytorch, generative-ai, video, gpu, linux

## Member repositories
- Tencent-Hunyuan/HunyuanVideo-I2V (main) score 54

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:42.983570+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 2026-08-30T03:18:02.975197+00:00, confidence not recorded.
  - readme: https://github.com/Tencent-Hunyuan/HunyuanVideo-I2V (fetched 2026-08-28T04:05:42.983570+00:00, sha 776f531651fe)
- Data as of 2026-08-30T08:39:29.467469+00:00.