# Tencent-Hunyuan/HunyuanDiT

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

Repository: https://github.com/Tencent-Hunyuan/HunyuanDiT
Canonical: https://ross.abutalabs.com/products/hunyuandit
Homepage: https://dit.hunyuan.tencent.com/
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Last push: 2025-11-27T06:37:00+00:00

## Health v2 (maintenance only)
Score: 49/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 54, release rhythm 35, longevity 60
- inputs: {"age_days": 845, "days_push": 279, "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 4291, forks 363 (observed 2026-08-28T04:08:41.424407+00:00)

## What it is
Hunyuan-DiT is Tencent's open-source diffusion transformer model for text-to-image generation with fine-grained Chinese language understanding. The repository provides PyTorch model definitions, pre-trained weights, inference code, and LoRA/ControlNet fine-tuning tooling.

## Use cases
- generate images from Chinese text prompts
- run a diffusion transformer text-to-image model locally
- train LoRA adapters for a text-to-image model
- use ControlNet with a Chinese-aware image generator
- integrate text-to-image generation into ComfyUI workflows
- fine-tune a diffusion model on custom image datasets

## When to choose
- you need high-quality text-to-image generation with strong Chinese prompt understanding
- you want to fine-tune or train LoRA/ControlNet variants of a diffusion model
- you want ComfyUI-compatible image generation weights and workflows

## When to avoid
- you only need English-centric image generation where other models may fit better
- you lack a GPU or cannot run large PyTorch models
- you need a hosted API rather than self-hosted model weights

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, llm-inference
- domain: artificial-intelligence, deep-learning, image-processing
- platform: python
- tags: text-to-image, diffusion-transformer, chinese-language, stable-diffusion, comfyui, lora, controlnet, pytorch, natural-language-processing, gpu, docker, linux

## Member repositories
- Tencent-Hunyuan/HunyuanDiT (main) score 49

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:41.424407+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 2026-08-29T18:21:53.694747+00:00, confidence not recorded.
  - readme: https://github.com/Tencent-Hunyuan/HunyuanDiT (fetched 2026-08-28T04:08:41.424407+00:00, sha b8787b08e100)
  - homepage: https://dit.hunyuan.tencent.com/ (fetched 2026-08-29T09:11:09.788241+00:00, sha 44136fa355b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.