# TencentARC/T2I-Adapter

T2I-Adapter

Repository: https://github.com/TencentARC/T2I-Adapter
Canonical: https://ross.abutalabs.com/products/t2i-adapter
Language: Python
License Family: other
Last push: 2024-06-21T20:51:36+00:00

## Health v2 (maintenance only)
Score: 31/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 92
- inputs: {"age_days": 1295, "days_push": 803, "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 3801, forks 226 (observed 2026-08-28T04:08:20.157989+00:00)

## What it is
Official implementation of T2I-Adapter, lightweight adapter models that add controllable conditioning (sketch, canny, lineart, depth, pose) to text-to-image diffusion models like Stable Diffusion XL. It integrates with Hugging Face diffusers and provides pretrained adapter checkpoints and demos.

## Use cases
- control stable diffusion image generation with a sketch
- generate images guided by depth maps or canny edges
- add pose conditioning to SDXL text-to-image generation
- use lightweight adapters for controllable diffusion models in diffusers
- turn line art into fully rendered images with AI

## When to choose
- you need lightweight, efficient conditioning adapters for SD 1.4/1.5 or SDXL
- you already use Hugging Face diffusers and want T2I-Adapter support
- you want sketch, edge, depth, or pose control over text-to-image generation

## When to avoid
- you need actively developed features or guaranteed support (no license file, limited maintenance)
- you prefer ControlNet-style heavier conditioning with broader community tooling
- you need non-Python or production-served inference out of the box

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, stable-diffusion
- domain: artificial-intelligence, deep-learning, image-processing, computer-vision
- platform: python
- tags: text-to-image, diffusion-models, controllable-generation, adapters, sdxl, stable-diffusion, sketch-to-image, research, gpu

## Member repositories
- TencentARC/T2I-Adapter (main) score 31

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:20.157989+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 2026-08-29T18:26:52.592855+00:00, confidence not recorded.
  - readme: https://github.com/TencentARC/T2I-Adapter (fetched 2026-08-28T04:08:20.157989+00:00, sha 4cf051dd2e34)
- Data as of 2026-08-30T08:39:29.467469+00:00.