ACE++: Instruction-Based Image Creation and Editing via Context-Aware Content Filling
Authors:
Top Cited Papers
- 19 October 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1979-1987
Abstract
We report ACE++, an instruction-based diffusion framework that tackles various image generation and editing tasks. Inspired by the input format for the inpainting task proposed by FLUX.1-Fill-dev, we improve the Long-context Condition Unit (LCU) introduced in ACE and extend this input paradigm to any editing and generation tasks. To take full advantage of image generative priors, we develop a two-stage training scheme to minimize the efforts of finetuning powerful text-to-image diffusion models like FLUX.1-dev. In the first stage, we pre-train the model using task data with the 0-ref tasks from the text-to-image model. There are many models in the community based on the post-training of text-to-image foundational models that meet this training paradigm of the first stage. For example, FLUX.1-Fill-dev deals primarily with painting tasks and can be used as an initialization to accelerate the training process. In the second stage, we finetune the above model to support the general instructions using all tasks defined in ACE. To promote the widespread application of ACE++ in different scenarios, we provide a comprehensive set of models that cover both full finetuning and lightweight finetuning, while considering general applicability and applicability in vertical scenarios. The qualitative analysis showcases the superiority of ACE++ in terms of generating image quality and prompt following ability. Our code and models are available at https://ali-vilab.github.io/ACE_plus_page.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics2025
- OmniGen: Unified Image Generation2025
- BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion2024
- A Task Is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting2024
- AnyDoor: Zero-shot Object-level Image Customization2024
- Emu Edit: Precise Image Editing via Recognition and Generation Tasks2024
- SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing2024
- Adding Conditional Control to Text-to-Image Diffusion Models2023
- InstructPix2Pix: Learning to Follow Image Editing Instructions2023
- High-Resolution Image Synthesis with Latent Diffusion Models2022