# tencent-ailab/IP-Adapter

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

Repository: https://github.com/tencent-ailab/IP-Adapter
Canonical: https://ross.abutalabs.com/products/ip-adapter
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Last push: 2024-06-28T02:47:03+00:00

## Health v2 (maintenance only)
Score: 28/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 79
- inputs: {"age_days": 1113, "days_push": 796, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6677, forks 428 (observed 2026-08-28T04:09:47.572044+00:00)

## What it is
IP-Adapter is a lightweight (22M parameter) adapter that adds image prompt capability to pretrained text-to-image diffusion models like Stable Diffusion and SDXL. It enables multimodal generation combining image and text prompts, including face-ID variants, and is integrated into Diffusers, WebUI, and ComfyUI.

## Use cases
- generate images conditioned on a reference image instead of text
- combine image and text prompts for multimodal image generation
- transfer style or content from a reference image to new generations
- generate portraits preserving a face identity with IP-Adapter-FaceID
- use image prompting with SDXL and custom fine-tuned models
- integrate image prompt control into ComfyUI or WebUI workflows

## When to choose
- you want image-conditioned generation without fine-tuning the whole diffusion model
- you need a lightweight adapter compatible with existing Stable Diffusion checkpoints and ControlNet tools
- you want face identity preservation in generated portraits

## When to avoid
- you need pure text-to-image generation with no reference image
- you use diffusion models other than the supported SD/SDXL family
- you need a maintained product with recent updates - the repo's last release was mid-2024

## Facets
- artifact type: library
- maturity: stable
- function: image-processing, machine-learning, deep-learning
- domain: image-processing, artificial-intelligence, deep-learning
- platform: python
- tags: diffusion-models, text-to-image, image-prompt, stable-diffusion, adapter, faceid, sdxl, huggingface-diffusers, gpu

## Member repositories
- tencent-ailab/IP-Adapter (main) score 28

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:47.572044+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 2026-08-29T17:43:00.842592+00:00, confidence not recorded.
  - readme: https://github.com/tencent-ailab/IP-Adapter (fetched 2026-08-28T04:09:47.572044+00:00, sha 93b22cd0cc5f)
- Data as of 2026-08-30T08:39:29.467469+00:00.