mlsanityData to 7 Oct 2026

ACE++: Instruction-Based Image Creation and Editing via Context-Aware Content Filling

arXiv 2501.02487 ↗First posted 5 Jan 2025cs.CVcited by 95

Not on the map. Why?

Cited by 28 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

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. Code and models will be available on the project page: https://ali-vilab. github.io/ACE_plus_page/.

Key facts. Cited by 95 papers in the map (data through 7 Oct 2026). Builds on 23 of its 34 references that are in the map. First posted on arXiv 5 Jan 2025.

Builds on

23 of 34 references.

References · 23

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  3. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  4. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  5. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  6. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  7. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 854
  8. 2023MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editingcited by 615
  9. 2024InstantID: Zero-shot Identity-Preserving Generation in Secondscited by 431
  10. 2023AnyDoor: Zero-shot Object-level Image Customizationcited by 411
  11. 2024OmniGen: Unified Image Generationcited by 388
  12. 2024OminiControl: Minimal and Universal Control for Diffusion Transformercited by 334
11 more
  1. 2023Emu Edit: Precise Image Editing via Recognition and Generation Taskscited by 321
  2. 2024Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understandingcited by 294
  3. 2024BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusioncited by 200
  4. 2023StyleDrop: Text-to-Image Generation in Any Stylecited by 197
  5. 2023A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpaintingcited by 168
  6. 2023Make-Your-Video: Customized Video Generation Using Textual and Structural Guidancecited by 129
  7. 2024UniReal: Universal Image Generation and Editing via Learning Real-world Dynamicscited by 100
  8. 2024ACE: All-round Creator and Editor Following Instructions via Diffusion Transformercited by 56
  9. 2021ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language Generationcited by 41
  10. 2023SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editingcited by 37
  11. 2024StyleBooth: Image Style Editing with Multimodal Instructioncited by 28

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 60; 2026: 35.

95 papers.

Sort:

By area:

  1. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  2. 2025VACE: All-in-One Video Creation and Editingcited by 467
  3. 2025Step1X-Edit: A Practical Framework for General Image Editingcited by 417
  4. 2025OmniGen2: Towards Instruction-Aligned Multimodal Generationcited by 241
  5. 2025In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformercited by 199
  6. 2025Insert Anything: Image Insertion via In-Context Editing in DiTcited by 61
  7. 2025Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editingcited by 58
  8. 2025OminiControl2: Efficient Conditioning for Diffusion Transformerscited by 56
  9. 2025VisualCloze: A Universal Image Generation Framework via Visual In-Context Learningcited by 39
  10. 2025Does FLUX Already Know How to Perform Physically Plausible Image Composition?cited by 30
  11. 2025LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuningcited by 27
  12. 2025X2Edit: Revisiting Arbitrary-Instruction Image Editing through Self-Constructed Data and Task-Aware Representation Learningcited by 24
38 more
  1. 2025ReasonEdit: Towards Reasoning-Enhanced Image Editing Modelscited by 24
  2. 2025ICE-Bench: A Unified and Comprehensive Benchmark for Image Creating and Editingcited by 23
  3. 2025Visual Autoregressive Modeling for Instruction-Guided Image Editingcited by 21
  4. 2025UniVG: A Generalist Diffusion Model for Unified Image Generation and Editingcited by 19
  5. 2025LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object Integrationcited by 19
  6. 2025InstantCharacter: Personalize Any Characters with a Scalable Diffusion Transformer Frameworkcited by 19
  7. 2025ComfyMind: Toward General-Purpose Generation via Tree-Based Planning and Reactive Feedbackcited by 15
  8. 2025Cut2Next: Generating Next Shot via In-Context Tuningcited by 15
  9. 2025Query-Kontext: An Unified Multimodal Model for Image Generation and Editingcited by 15
  10. 2025Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Visioncited by 14
  11. 2025OmniTry: Virtual Try-On Anything without Maskscited by 13
  12. 2025X2I: Seamless Integration of Multimodal Understanding into Diffusion Transformer via Attention Distillationcited by 11
  13. 2025MUSAR: Exploring Multi-Subject Customization from Single-Subject Dataset via Attention Routingcited by 11
  14. 2025HBridge: H-Shape Bridging of Heterogeneous Experts for Unified Multimodal Understanding and Generationcited by 11
  15. 2025Image Editing As Programs with Diffusion Modelscited by 10
  16. 2025IC-Custom: Diverse Image Customization via In-Context Learningcited by 10
  17. 2025PairEdit: Learning Semantic Variations for Exemplar-based Image Editingcited by 8
  18. 2025MultiHuman-Testbench: Benchmarking Image Generation for Multiple Humanscited by 8
  19. 2025Identity-Preserving Text-to-Video Generation via Training-Free Prompt, Image, and Guidance Enhancementcited by 8
  20. 2025RepText: Rendering Visual Text via Replicatingcited by 7
  21. 2026From Scale to Speed: Adaptive Test-Time Scaling for Image Editingcited by 7
  22. 2025Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesiscited by 6
  23. 2025Beyond Textual CoT: Interleaved Text-Image Chains with Deep Confidence Reasoning for Image Editingcited by 6
  24. 2025iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generationcited by 6
  25. 2026TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Expertscited by 6
  26. 2025Dreamland: Controllable World Creation with Simulator and Generative Modelscited by 5
  27. 2025UniVid: Unifying Vision Tasks with Pre-trained Video Generation Modelscited by 5
  28. 2025Taming Flow-based I2V Models for Creative Video Editingcited by 5
  29. 2025ManipShield: A Unified Framework for Image Manipulation Detection, Localization and Explanationcited by 5
  30. 2025OmniRefiner: Reinforcement-Guided Local Diffusion Refinementcited by 5
  31. 2025TextEditBench: Evaluating Reasoning-aware Text Editing Beyond Renderingcited by 5
  32. 2026HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Imagescited by 5
  33. 2026UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priorscited by 5
  34. 2025Neural-Driven Image Editingcited by 4
  35. 2025Scale Your Instructions: Enhance the Instruction-Following Fidelity of Unified Image Generation Model by Self-Adaptive Attention Scalingcited by 4
  36. 2025Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editingcited by 4
  37. 2025MagicQuillV2: Precise and Interactive Image Editing with Layered Visual Cuescited by 4
  38. 2026TP-Blend: Textual-Prompt Attention Pairing for Precise Object-Style Blending in Diffusion Modelscited by 4

50 most cited of 95 All 95 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Editing on the Generative Manifold: A Theoretical and Empirical Study of General Diffusion-Based Image Editing Trade-offs
  2. 2022The Stable Artist: Steering Semantics in Diffusion Latent Space
  3. 2024Image Inpainting Models are Effective Tools for Instruction-guided Image Editing
  4. 2025ACE: Concept Editing in Diffusion Models without Performance Degradation
  5. 2025MADI: Masking-Augmented Diffusion with Inference-Time Scaling for Visual Editing
  6. 2024PainterNet: Adaptive Image Inpainting with Actual-Token Attention and Diverse Mask Control
  7. 2024Paint by Inpaint: Learning to Add Image Objects by Removing Them First
  8. 2026Overpainting: Localized Context-aware Diffusion Image Editing