# SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model

arXiv: https://arxiv.org/abs/2212.05034 · HTML: https://mlsanity.com/paper/2212.05034/

## Key facts

- Cited by 278 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 28 of its 32 references that are in the map.
- First posted on arXiv 9 Dec 2022.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Blended Diffusion for Text-driven Editing of Natural Images](https://mlsanity.com/paper/2111.14818/) (2021)
- [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://mlsanity.com/paper/2202.09778/) (2022)
- [DiffEdit: Diffusion-based semantic image editing with mask guidance](https://mlsanity.com/paper/2210.11427/) (2022)
- [Blended Latent Diffusion](https://mlsanity.com/paper/2206.02779/) (2022)
- [EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations](https://mlsanity.com/paper/2207.06635/) (2022)
- [Pretraining is All You Need for Image-to-Image Translation](https://mlsanity.com/paper/2205.12952/) (2022)
- [Paint by Word](https://mlsanity.com/paper/2103.10951/) (2021)
- [Shape-guided Object Inpainting](https://mlsanity.com/paper/2204.07845/) (2022)

## Built on by (most cited first, 30 of 278)

- [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024)
- [VideoComposer: Compositional Video Synthesis with Motion Controllability](https://mlsanity.com/paper/2306.02018/) (2023)
- [AnyDoor: Zero-shot Object-level Image Customization](https://mlsanity.com/paper/2307.09481/) (2023)
- [Emu Edit: Precise Image Editing via Recognition and Generation Tasks](https://mlsanity.com/paper/2311.10089/) (2023)
- [Composer: Creative and Controllable Image Synthesis with Composable Conditions](https://mlsanity.com/paper/2302.09778/) (2023)
- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model](https://mlsanity.com/paper/2311.09217/) (2023)
- [Diffusion Model-Based Image Editing: A Survey](https://mlsanity.com/paper/2402.17525/) (2024)
- [BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion](https://mlsanity.com/paper/2403.06976/) (2024)
- [A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting](https://mlsanity.com/paper/2312.03594/) (2023)
- [Stable Flow: Vital Layers for Training-Free Image Editing](https://mlsanity.com/paper/2411.14430/) (2024)
- [Adaptive Caching for Faster Video Generation with Diffusion Transformers](https://mlsanity.com/paper/2411.02397/) (2024)
- [Diffusion Models for Imperceptible and Transferable Adversarial Attack](https://mlsanity.com/paper/2305.08192/) (2023)
- [AVID: Any-Length Video Inpainting with Diffusion Model](https://mlsanity.com/paper/2312.03816/) (2023)
- [Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion Models](https://mlsanity.com/paper/2306.00973/) (2023)
- [Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following](https://mlsanity.com/paper/2311.17002/) (2023)
- [FocalDreamer: Text-driven 3D Editing via Focal-fusion Assembly](https://mlsanity.com/paper/2308.10608/) (2023)
- [LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models](https://mlsanity.com/paper/2407.08939/) (2024)
- [LooseControl: Lifting ControlNet for Generalized Depth Conditioning](https://mlsanity.com/paper/2312.03079/) (2023)
- [Causal Representation Learning from Multiple Distributions: A General Setting](https://mlsanity.com/paper/2402.05052/) (2024)
- [HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models](https://mlsanity.com/paper/2312.14091/) (2023)
- [Zero-shot Image Editing with Reference Imitation](https://mlsanity.com/paper/2406.07547/) (2024)
- [IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation](https://mlsanity.com/paper/2403.10701/) (2024)
- [Attentive Eraser: Unleashing Diffusion Model's Object Removal Potential via Self-Attention Redirection Guidance](https://mlsanity.com/paper/2412.12974/) (2024)
- [Insert Anything: Image Insertion via In-Context Editing in DiT](https://mlsanity.com/paper/2504.15009/) (2025)
- [Uni-paint: A Unified Framework for Multimodal Image Inpainting with Pretrained Diffusion Model](https://mlsanity.com/paper/2310.07222/) (2023)
- [Relightful Harmonization: Lighting-aware Portrait Background Replacement](https://mlsanity.com/paper/2312.06886/) (2023)
- [Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis](https://mlsanity.com/paper/2306.08645/) (2023)
- [ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer](https://mlsanity.com/paper/2410.00086/) (2024)
- [Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis](https://mlsanity.com/paper/2304.03869/) (2023)

## Abstract (arXiv)

Generic image inpainting aims to complete a corrupted image by borrowing surrounding information, which barely generates novel content. By contrast, multi-modal inpainting provides more flexible and useful controls on the inpainted content, eg, a text prompt can be used to describe an object with richer attributes, and a mask can be used to constrain the shape of the inpainted object rather than being only considered as a missing area. We propose a new diffusion-based model named SmartBrush for completing a missing region with an object using both text and shape-guidance. While previous work such as DALLE-2 and Stable Diffusion can do text-guided inapinting they do not support shape guidance and tend to modify background texture surrounding the generated object. Our model incorporates both text and shape guidance with precision control. To preserve the background better, we propose a novel training and sampling strategy by augmenting the diffusion U-net with object-mask prediction. Lastly, we introduce a multi-task training strategy by jointly training inpainting with text-to-image generation to leverage more training data. We conduct extensive experiments showing that our model outperforms all baselines in terms of visual quality, mask controllability, and background preservation.