# MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis

arXiv: https://arxiv.org/abs/2407.07614 · HTML: https://mlsanity.com/paper/2407.07614/

## Key facts

- Cited by 44 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 48 of its 58 references that are in the map.
- First posted on arXiv 10 Jul 2024.

## 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 48)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (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)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (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)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [Improved Techniques for Training Score-Based Generative Models](https://mlsanity.com/paper/2006.09011/) (2020)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)

## Built on by (most cited first, 30 of 44)

- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models](https://mlsanity.com/paper/2411.04996/) (2024)
- [LMFusion: Adapting Pretrained Language Models for Multimodal Generation](https://mlsanity.com/paper/2412.15188/) (2024)
- [Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models](https://mlsanity.com/paper/2409.10695/) (2024)
- [ImageFolder: Autoregressive Image Generation with Folded Tokens](https://mlsanity.com/paper/2410.01756/) (2024)
- [Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding](https://mlsanity.com/paper/2410.01699/) (2024)
- [ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance](https://mlsanity.com/paper/2412.06673/) (2024)
- [Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model](https://mlsanity.com/paper/2501.00895/) (2025)
- [Autoregressive Models in Vision: A Survey](https://mlsanity.com/paper/2411.05902/) (2024)
- [Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient](https://mlsanity.com/paper/2411.17787/) (2024)
- [A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications](https://mlsanity.com/paper/2410.15595/) (2024)
- [FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction](https://mlsanity.com/paper/2502.20313/) (2025)
- [MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic Modeling](https://mlsanity.com/paper/2410.10798/) (2024)
- [FARMER: Flow AutoRegressive Transformer over Pixels](https://mlsanity.com/paper/2510.23588/) (2025)
- [Scaling Properties of Diffusion Models for Perceptual Tasks](https://mlsanity.com/paper/2411.08034/) (2024)
- [STAGE: Stable and Generalizable GRPO for Autoregressive Image Generation](https://mlsanity.com/paper/2509.25027/) (2025)
- [OmniCLIP: Adapting CLIP for Video Recognition with Spatial-Temporal Omni-Scale Feature Learning](https://mlsanity.com/paper/2408.06158/) (2024)
- [T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts](https://mlsanity.com/paper/2412.04300/) (2024)
- [Towards Enhanced Image Generation Via Multi-modal Chain of Thought in Unified Generative Models](https://mlsanity.com/paper/2503.01298/) (2025)
- [Progressive Compositionality in Text-to-Image Generative Models](https://mlsanity.com/paper/2410.16719/) (2024)
- [XQ-GAN: An Open-source Image Tokenization Framework for Autoregressive Generation](https://mlsanity.com/paper/2412.01762/) (2024)
- [Image Tokenizer Needs Post-Training](https://mlsanity.com/paper/2509.12474/) (2025)
- [Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy](https://mlsanity.com/paper/2510.09012/) (2025)
- [CustomVideoX: 3D Reference Attention Driven Dynamic Adaptation for Zero-Shot Customized Video Diffusion Transformers](https://mlsanity.com/paper/2502.06527/) (2025)
- [Towards Unifying Understanding and Generation in the Era of Vision Foundation Models: A Survey from the Autoregression Perspective](https://mlsanity.com/paper/2410.22217/) (2024)
- [Robust Latent Matters: Boosting Image Generation with Sampling Error Synthesis](https://mlsanity.com/paper/2503.08354/) (2025)
- [A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation](https://mlsanity.com/paper/2506.08210/) (2025)
- [Text-to-Image Synthesis: A Decade Survey](https://mlsanity.com/paper/2411.16164/) (2024)
- [Hierarchical Masked Autoregressive Models with Low-Resolution Token Pivots](https://mlsanity.com/paper/2505.20288/) (2025)
- [Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey](https://mlsanity.com/paper/2507.22920/) (2025)

## Abstract (arXiv)

Auto-regressive models have made significant progress in the realm of language generation, yet they do not perform on par with diffusion models in the domain of image synthesis. In this work, we introduce MARS, a novel framework for T2I generation that incorporates a specially designed Semantic Vision-Language Integration Expert (SemVIE). This innovative component integrates pre-trained LLMs by independently processing linguistic and visual information, freezing the textual component while fine-tuning the visual component. This methodology preserves the NLP capabilities of LLMs while imbuing them with exceptional visual understanding. Building upon the powerful base of the pre-trained Qwen-7B, MARS stands out with its bilingual generative capabilities corresponding to both English and Chinese language prompts and the capacity for joint image and text generation. The flexibility of this framework lends itself to migration towards any-to-any task adaptability. Furthermore, MARS employs a multi-stage training strategy that first establishes robust image-text alignment through complementary bidirectional tasks and subsequently concentrates on refining the T2I generation process, significantly augmenting text-image synchrony and the granularity of image details. Notably, MARS requires only 9% of the GPU days needed by SD1.5, yet it achieves remarkable results across a variety of benchmarks, illustrating the training efficiency and the potential for swift deployment in various applications.