# instantX-research/InstantStyle

InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation 🔥

Repository: https://github.com/instantX-research/InstantStyle
Canonical: https://ross.abutalabs.com/products/instantstyle
Homepage: https://instantstyle.github.io/
Language: Jupyter Notebook
License Family: other
Last push: 2024-09-18T09:33:36+00:00

## Health v2 (maintenance only)
Score: 26/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 70
- inputs: {"age_days": 985, "days_push": 714, "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 2018, forks 125 (observed 2026-08-28T04:06:06.115114+00:00)

## What it is
InstantStyle is a framework for style-preserving text-to-image generation that disentangles style and content from reference images using feature-space subtraction and style-block-only injection into diffusion models. It is supported natively in Hugging Face diffusers and targets tuning-free image personalization.

## Use cases
- transfer the style of a reference image to new generated images
- generate images in a specific artistic style without training
- apply a style to text-to-image output without content leakage
- stylize photos with stable diffusion and sdxl
- avoid weight tuning when using ip-adapter style transfer

## When to choose
- you want tuning-free style transfer with diffusion models
- you need style and content disentanglement from a reference image
- you already use diffusers and want native style injection

## When to avoid
- you need a production system with a maintained license
- you want non-diffusion image stylization
- you need guaranteed long-term support

## Facets
- artifact type: library
- maturity: active
- function: image-processing, machine-learning, stable-diffusion
- domain: artificial-intelligence, image-processing, deep-learning
- platform: python, cross-platform
- tags: text-to-image, style-transfer, diffusion-models, tuning-free, research, gpu

## Member repositories
- instantX-research/InstantStyle (main) score 26

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:06.115114+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 2026-08-30T03:00:28.134668+00:00, confidence not recorded.
  - readme: https://github.com/instantX-research/InstantStyle (fetched 2026-08-28T04:06:06.115114+00:00, sha 509e027426af)
  - homepage: https://instantstyle.github.io/ (fetched 2026-08-29T10:40:24.207718+00:00, sha e5d602cf4aa1)
- Data as of 2026-08-30T08:39:29.467469+00:00.