# Tencent-Hunyuan/InstantCharacter

Repository: https://github.com/Tencent-Hunyuan/InstantCharacter
Canonical: https://ross.abutalabs.com/products/instantcharacter
Language: Python
License: NOASSERTION
License Family: other
Last push: 2025-05-14T03:33:35+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 21, release rhythm 35, longevity 36
- inputs: {"age_days": 504, "days_push": 476, "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 1045, forks 93 (observed 2026-08-28T04:03:21.413955+00:00)

## What it is
InstantCharacter is a tuning-free framework built on diffusion transformers that generates character-consistent images from a single reference photo, supporting style LoRAs and various downstream tasks. It is released by Tencent Hunyuan with checkpoints on Hugging Face and a ComfyUI wrapper.

## Use cases
- generate images of the same character from one reference photo
- personalize a character without training or fine-tuning
- apply art styles like Ghibli to a character while keeping identity
- run character-preserving text-to-image generation locally
- use a custom character node in ComfyUI workflows

## When to choose
- you need identity-consistent character generation from a single image without per-character training
- you want to combine character consistency with style LoRAs on Flux-class models
- you have a GPU (22GB VRAM with offloading) and want open checkpoints

## When to avoid
- you need fast inference on low-VRAM consumer GPUs
- you want a polished end-user app rather than Python inference code
- you need a permissively licensed model for commercial use without checking the custom license

## Facets
- artifact type: library
- maturity: active
- function: image-processing, machine-learning, stable-diffusion, deep-learning
- domain: image-processing, artificial-intelligence, deep-learning
- platform: python
- tags: diffusion-transformer, character-personalization, tuning-free, text-to-image, flux, comfyui, gpu, linux

## Member repositories
- Tencent-Hunyuan/InstantCharacter (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:21.413955+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 2026-08-30T07:02:02.498575+00:00, confidence not recorded.
  - readme: https://github.com/Tencent-Hunyuan/InstantCharacter (fetched 2026-08-28T04:03:21.413955+00:00, sha e6fed63de304)
- Data as of 2026-08-30T08:39:29.467469+00:00.