# ali-vilab/ACE_plus

Repository: https://github.com/ali-vilab/ACE_plus
Canonical: https://ross.abutalabs.com/products/ace_plus
Language: Python
License Family: other
Last push: 2025-04-21T06:36:02+00:00

## Health v2 (maintenance only)
Score: 28/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 17, release rhythm 35, longevity 43
- inputs: {"age_days": 608, "days_push": 499, "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 1364, forks 92 (observed 2026-08-28T04:04:31.015515+00:00)

## What it is
ACE++ is a Python library and model release from Alibaba's Tongyi Lab for instruction-based image creation and editing via context-aware content filling, unifying reference image generation, local editing, and controllable generation in one framework. It ships LoRA and fully fine-tuned models built on FLUX, with training code and ComfyUI workflows.

## Use cases
- edit images with text instructions
- generate images using a reference image
- inpaint or fill regions of an image contextually
- train a custom LoRA for image editing
- run image editing workflows in ComfyUI
- unified controllable image generation model

## When to choose
- you need instruction-driven image editing or reference-based generation with open weights
- you want to fine-tune or train LoRAs for custom image editing tasks
- you use ComfyUI and want ready-made editing workflows

## When to avoid
- you need active development or timely issue support - the project has stalled due to FLUX post-training challenges
- you need a production image editing API rather than research models
- you lack a GPU or don't want to self-host diffusion models

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning
- domain: image-processing, artificial-intelligence, computer-vision
- platform: python
- tags: image-generation, image-editing, diffusion-models, lora, flux, comfyui, instruction-based-editing, stable-diffusion, gpu, docker

## Member repositories
- ali-vilab/ACE_plus (main) score 28

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:31.015515+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 2026-08-30T04:41:19.280452+00:00, confidence not recorded.
  - readme: https://github.com/ali-vilab/ACE_plus (fetched 2026-08-28T04:04:31.015515+00:00, sha b308bde24e4a)
- Data as of 2026-08-30T08:39:29.467469+00:00.