# MMGen: Unified Multi-modal Image Generation and Understanding in One Go

arXiv: https://arxiv.org/abs/2503.20644 · HTML: https://mlsanity.com/paper/2503.20644/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 38 of its 47 references that are in the map.
- First posted on arXiv 26 Mar 2025.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 38)

- [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)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (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)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers](https://mlsanity.com/paper/2401.08740/) (2024)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks](https://mlsanity.com/paper/2206.08916/) (2022)
- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (2024)
- [Analyzing and Improving the Training Dynamics of Diffusion Models](https://mlsanity.com/paper/2312.02696/) (2023)
- [Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action](https://mlsanity.com/paper/2312.17172/) (2023)
- [MultiMAE: Multi-modal Multi-task Masked Autoencoders](https://mlsanity.com/paper/2204.01678/) (2022)
- [GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image](https://mlsanity.com/paper/2403.12013/) (2024)
- [BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion](https://mlsanity.com/paper/2307.10816/) (2023)
- [Generating Images with Sparse Representations](https://mlsanity.com/paper/2103.03841/) (2021)
- [LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation](https://mlsanity.com/paper/2303.17189/) (2023)
- [Sapiens: Foundation for Human Vision Models](https://mlsanity.com/paper/2408.12569/) (2024)
- [Semantic-SAM: Segment and Recognize Anything at Any Granularity](https://mlsanity.com/paper/2307.04767/) (2023)
- [Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction](https://mlsanity.com/paper/2409.18124/) (2024)
- [StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal](https://mlsanity.com/paper/2406.16864/) (2024)
- [4M: Massively Multimodal Masked Modeling](https://mlsanity.com/paper/2312.06647/) (2023)
- [UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics](https://mlsanity.com/paper/2412.07774/) (2024)
- [Depth Any Video with Scalable Synthetic Data](https://mlsanity.com/paper/2410.10815/) (2024)

## Built on by (most cited first, 11 of 11)

- [OmniVDiff: Omni Controllable Video Diffusion for Generation and Understanding](https://mlsanity.com/paper/2504.10825/) (2025)
- [NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching](https://mlsanity.com/paper/2510.13721/) (2025)
- [When Safety Collides: Resolving Multi-Category Harmful Conflicts in Text-to-Image Diffusion via Adaptive Safety Guidance](https://mlsanity.com/paper/2602.20880/) (2026)
- [Taming Camera-Controlled Video Generation with Verifiable Geometry Reward](https://mlsanity.com/paper/2512.02870/) (2025)
- [CtrlVDiff: Controllable Video Generation via Unified Multimodal Video Diffusion](https://mlsanity.com/paper/2511.21129/) (2025)
- [CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos](https://mlsanity.com/paper/2601.10632/) (2026)
- [Jodi: Unification of Visual Generation and Understanding via Joint Modeling](https://mlsanity.com/paper/2505.19084/) (2025)
- [OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving](https://mlsanity.com/paper/2512.14225/) (2025)
- [VideoMaMa: Mask-Guided Video Matting via Generative Prior](https://mlsanity.com/paper/2601.14255/) (2026)
- [PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space](https://mlsanity.com/paper/2607.05373/) (2026)
- [MMOE: Modernizing Diffusion Transformers with Efficient Expert Design](https://mlsanity.com/paper/2607.24665/) (2026)

## Abstract (arXiv)

A unified diffusion framework for multi-modal generation and understanding has the transformative potential to achieve seamless and controllable image diffusion and other cross-modal tasks. In this paper, we introduce MMGen, a unified framework that integrates multiple generative tasks into a single diffusion model. This includes: (1) multi-modal category-conditioned generation, where multi-modal outputs are generated simultaneously through a single inference process, given category information; (2) multi-modal visual understanding, which accurately predicts depth, surface normals, and segmentation maps from RGB images; and (3) multi-modal conditioned generation, which produces corresponding RGB images based on specific modality conditions and other aligned modalities. Our approach develops a novel diffusion transformer that flexibly supports multi-modal output, along with a simple modality-decoupling strategy to unify various tasks. Extensive experiments and applications demonstrate the effectiveness and superiority of MMGen across diverse tasks and conditions, highlighting its potential for applications that require simultaneous generation and understanding.