# MaGIC: Multi-modality Guided Image Completion

arXiv: https://arxiv.org/abs/2305.11818 · HTML: https://mlsanity.com/paper/2305.11818/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 53 references that are in the map.
- First posted on arXiv 19 May 2023.

## Builds on (most cited first, 30 of 43)

- [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)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [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)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [Blended Diffusion for Text-driven Editing of Natural Images](https://mlsanity.com/paper/2111.14818/) (2021)
- [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://mlsanity.com/paper/2111.14822/) (2021)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation](https://mlsanity.com/paper/2110.02711/) (2021)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Universal Guidance for Diffusion Models](https://mlsanity.com/paper/2302.07121/) (2023)
- [Blended Latent Diffusion](https://mlsanity.com/paper/2206.02779/) (2022)
- [Training-Free Layout Control with Cross-Attention Guidance](https://mlsanity.com/paper/2304.03373/) (2023)
- [FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model](https://mlsanity.com/paper/2303.09833/) (2023)
- [SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model](https://mlsanity.com/paper/2212.05034/) (2022)
- [Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting](https://mlsanity.com/paper/2212.06909/) (2022)
- [Large Scale Image Completion via Co-Modulated Generative Adversarial Networks](https://mlsanity.com/paper/2103.10428/) (2021)

## Built on by (most cited first, 14 of 14)

- [Controllable Generation with Text-to-Image Diffusion Models: A Survey](https://mlsanity.com/paper/2403.04279/) (2024)
- [PromptFix: You Prompt and We Fix the Photo](https://mlsanity.com/paper/2405.16785/) (2024)
- [OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting](https://mlsanity.com/paper/2503.08677/) (2025)
- [HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting](https://mlsanity.com/paper/2405.15125/) (2024)
- [DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling](https://mlsanity.com/paper/2412.00759/) (2024)
- [Flow-Guided Diffusion for Video Inpainting](https://mlsanity.com/paper/2311.15368/) (2023)
- [Deficiency-Aware Masked Transformer for Video Inpainting](https://mlsanity.com/paper/2307.08629/) (2023)
- [Coherent and Multi-modality Image Inpainting via Latent Space Optimization](https://mlsanity.com/paper/2407.08019/) (2024)
- [Test-time Conditional Text-to-Image Synthesis Using Diffusion Models](https://mlsanity.com/paper/2411.10800/) (2024)
- [VIPaint: Image Inpainting with Pre-Trained Diffusion Models via Variational Inference](https://mlsanity.com/paper/2411.18929/) (2024)
- [Understanding Trade offs When Conditioning Synthetic Data](https://mlsanity.com/paper/2507.02217/) (2025)
- [Recovering Partially Corrupted Objects via Sketch-Guided Bidirectional Feature Interaction](https://mlsanity.com/paper/2503.07047/) (2025)
- [InstantHDR: Single-forward Gaussian Splatting Initialization for HDR 3D Reconstruction](https://mlsanity.com/paper/2603.11298/) (2026)
- [SketchSense: Learning to Interpret Imperfect Sketch Guidance for Image Inpainting](https://mlsanity.com/paper/2608.13186/) (2026)

## Abstract (arXiv)

Vanilla image completion approaches exhibit sensitivity to large missing regions, attributed to the limited availability of reference information for plausible generation. To mitigate this, existing methods incorporate the extra cue as a guidance for image completion. Despite improvements, these approaches are often restricted to employing a single modality (e.g., segmentation or sketch maps), which lacks scalability in leveraging multi-modality for more plausible completion. In this paper, we propose a novel, simple yet effective method for Multi-modal Guided Image Completion, dubbed MaGIC, which not only supports a wide range of single modality as the guidance (e.g., text, canny edge, sketch, segmentation, depth, and pose), but also adapts to arbitrarily customized combination of these modalities (i.e., arbitrary multi-modality) for image completion. For building MaGIC, we first introduce a modality-specific conditional U-Net (MCU-Net) that injects single-modal signal into a U-Net denoiser for single-modal guided image completion. Then, we devise a consistent modality blending (CMB) method to leverage modality signals encoded in multiple learned MCU-Nets through gradient guidance in latent space. Our CMB is training-free, thereby avoids the cumbersome joint re-training of different modalities, which is the secret of MaGIC to achieve exceptional flexibility in accommodating new modalities for completion. Experiments show the superiority of MaGIC over state-of-the-art methods and its generalization to various completion tasks. Our project with code and models is available at yeates.github.io/MaGIC-Page/.