Towards Enhanced Image Generation Via Multi-modal Chain of Thought in Unified Generative Models

• URL: http://arxiv.org/abs/2503.01298v2
• Date: Wed, 22 Oct 2025 08:54:46 GMT
• Title: Towards Enhanced Image Generation Via Multi-modal Chain of Thought in Unified Generative Models
• Authors: Yi Wang, Mushui Liu, Wanggui He, Hanyang Yuan, Longxiang Zhang, Ziwei Huang, Guanghao Zhang, Wenkai Fang, Haoze Jiang, Shengxuming Zhang, Dong She, Jinlong Liu, Weilong Dai, Mingli Song, Hao Jiang, Jie Song,
• Abstract summary: Unified generative models have shown remarkable performance in text and image generation.<n>We introduce Chain of Thought (CoT) into unified generative models to address the challenges of complex image generation.<n>Experiments show that FoX consistently outperforms existing unified models on various T2I benchmarks.
• Score: 52.84391764467939
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Unified generative models have shown remarkable performance in text and image generation. For image synthesis tasks, they adopt straightforward text-to-image (T2I) generation. However, direct T2I generation limits the models in handling complex compositional instructions, which frequently occur in real-world scenarios. Although this issue is vital, existing works mainly focus on improving the basic image generation capability of the models. While such improvements help to some extent, they still fail to adequately resolve the problem. Inspired by Chain of Thought (CoT) solving complex problems step by step, this work aims to introduce CoT into unified generative models to address the challenges of complex image generation that direct T2I generation cannot effectively solve, thereby endowing models with enhanced image generation ability. To achieve this, we first propose Functionality-oriented eXperts (FoXperts), an expert-parallel architecture in our model FoX, which assigns experts by function. FoXperts disentangles potential conflicts in mainstream modality-oriented designs and provides a solid foundation for CoT. When introducing CoT, the first question is how to design it for complex image generation. To this end, we emulate a human-like artistic workflow -- planning, acting, reflection, and correction -- and propose the Multimodal Chain of Thought (MCoT) approach, as the data involves both text and image. To address the subsequent challenge -- designing an effective MCoT training paradigm -- we develop a multi-task joint training scheme that equips the model with all capabilities required for each MCoT step in a disentangled manner. This paradigm avoids the difficulty of collecting consistent multi-step data tuples. Extensive experiments show that FoX consistently outperforms existing unified models on various T2I benchmarks, delivering notable improvements in complex image generation.

Related papers

• CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation [52.0601996237501]
  Chain-of-Frame (CoF) reasoning enables frame-by-frame visual inference.<n>CoF-T2I integrates CoF reasoning into text-to-image (T2I) generation via progressive visual refinement.<n>Experiments show that CoF-T2I significantly outperforms the base video model.
  arXiv  Detail & Related papers  (2026-01-15T04:33:06Z)
• Can Generated Images Serve as a Viable Modality for Text-Centric Multimodal Learning? [3.966028515034415]
  This work systematically investigates whether images generated on-the-fly by Text-to-Image (T2I) models can serve as a valuable complementary modality for text-centric tasks.
  arXiv  Detail & Related papers  (2025-06-21T07:32:09Z)
• Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model [87.23753533733046]
  We introduce Muddit, a unified discrete diffusion transformer that enables fast and parallel generation across both text and image modalities.<n>Unlike prior unified diffusion models trained from scratch, Muddit integrates strong visual priors from a pretrained text-to-image backbone with a lightweight text decoder.
  arXiv  Detail & Related papers  (2025-05-29T16:15:48Z)
• Policy Optimized Text-to-Image Pipeline Design [73.9633527029941]
  We introduce a novel reinforcement learning-based framework for text-to-image generation.<n>Our approach first trains an ensemble of reward models capable of predicting image quality scores directly from prompt-workflow combinations.<n>We then implement a two-phase training strategy: initial vocabulary training followed by GRPO-based optimization.
  arXiv  Detail & Related papers  (2025-05-27T17:50:47Z)
• Conditional Panoramic Image Generation via Masked Autoregressive Modeling [35.624070746282186]
  We propose a unified framework, Panoramic AutoRegressive model (PAR), which leverages masked autoregressive modeling to address these challenges.<n>To address the inherent discontinuity in existing generative models, we introduce circular padding to enhance spatial coherence.<n>Experiments demonstrate competitive performance in text-to-image generation and panorama outpainting tasks.
  arXiv  Detail & Related papers  (2025-05-22T16:20:12Z)
• Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation [54.588082888166504]
  We present Mogao, a unified framework that enables interleaved multi-modal generation through a causal approach.<n>Mogoo integrates a set of key technical improvements in architecture design, including a deep-fusion design, dual vision encoders, interleaved rotary position embeddings, and multi-modal classifier-free guidance.<n>Experiments show that Mogao achieves state-of-the-art performance in multi-modal understanding and text-to-image generation, but also excels in producing high-quality, coherent interleaved outputs.
  arXiv  Detail & Related papers  (2025-05-08T17:58:57Z)
• Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step [86.69947123512836]
  Chain-of-Thought (CoT) reasoning has been extensively explored in large models to tackle complex understanding tasks.<n>We provide the first comprehensive investigation of the potential of CoT reasoning to enhance autoregressive image generation.<n>We propose the Potential Assessment Reward Model (PARM) and PARM++, specialized for autoregressive image generation.
  arXiv  Detail & Related papers  (2025-01-23T18:59:43Z)
• UNIC-Adapter: Unified Image-instruction Adapter with Multi-modal Transformer for Image Generation [64.8341372591993]
  We propose a new approach to unify controllable generation within a single framework.<n>Specifically, we propose the unified image-instruction adapter (UNIC-Adapter) built on the Multi-Modal-Diffusion Transformer architecture.<n>Our UNIC-Adapter effectively extracts multi-modal instruction information by incorporating both conditional images and task instructions.
  arXiv  Detail & Related papers  (2024-12-25T15:19:02Z)
• Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models [54.052963634384945]
  We introduce the Image Regeneration task to assess text-to-image models. We use GPT4V to bridge the gap between the reference image and the text input for the T2I model. We also present ImageRepainter framework to enhance the quality of generated images.
  arXiv  Detail & Related papers  (2024-11-14T13:52:43Z)
• Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining [48.98105914356609]
  Lumina-mGPT is a family of multimodal autoregressive models capable of various vision and language tasks. We introduce Ominiponent Supervised Finetuning, transforming Lumina-mGPT into a foundation model that seamlessly achieves omnipotent task unification.
  arXiv  Detail & Related papers  (2024-08-05T17:46:53Z)
• Modality-Specialized Synergizers for Interleaved Vision-Language Generalists [45.800383191637785]
  Vision-Language Generalists (VLGs) capable of understanding and generating both text and images.<n>One primary limitation lies in applying a unified architecture and the same set of parameters to simultaneously model discrete text tokens and continuous image features.<n>Recent works attempt to tackle this fundamental problem by introducing modality-aware expert models.<n>We introduce MODALITY-SPECIALIZED SYNERGIZERS (MOSS), a novel design that efficiently optimize existing unified architectures of VLGs.
  arXiv  Detail & Related papers  (2024-07-04T03:28:22Z)
• EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal Prompts [48.214475133206385]
  EMMA is a novel image generation model accepting multi-modal prompts built upon the state-of-the-art text-to-image (T2I) diffusion model, ELLA. By freezing all parameters in the original T2I diffusion model and only adjusting some additional layers, we reveal an interesting finding that the pre-trained T2I diffusion model can secretly accept multi-modal prompts.
  arXiv  Detail & Related papers  (2024-06-13T14:26:43Z)
• Unified Text-to-Image Generation and Retrieval [96.72318842152148]
  We propose a unified framework in the context of Multimodal Large Language Models (MLLMs) We first explore the intrinsic discrimi abilities of MLLMs and introduce a generative retrieval method to perform retrieval in a training-free manner. We then unify generation and retrieval in an autoregressive generation way and propose an autonomous decision module to choose the best-matched one between generated and retrieved images.
  arXiv  Detail & Related papers  (2024-06-09T15:00:28Z)
• DialogGen: Multi-modal Interactive Dialogue System for Multi-turn Text-to-Image Generation [46.085482021301516]
  We propose DialogGen to align off-the-shelf MLLMs and T2I models to build a Multi-modal Interactive Dialogue System. It is composed of drawing prompt alignment, careful training data curation, and error correction. Our experiments on DialogGen and user study demonstrate the effectiveness of DialogGen compared with other State-of-the-Art models.
  arXiv  Detail & Related papers  (2024-03-13T18:00:01Z)
• UNIMO-G: Unified Image Generation through Multimodal Conditional Diffusion [36.06457895469353]
  UNIMO-G is a conditional diffusion framework that operates on multimodal prompts with interleaved textual and visual inputs. It excels in both text-to-image generation and zero-shot subject-driven synthesis.
  arXiv  Detail & Related papers  (2024-01-24T11:36:44Z)
• Instruct-Imagen: Image Generation with Multi-modal Instruction [90.04481955523514]
  instruct-imagen is a model that tackles heterogeneous image generation tasks and generalizes across unseen tasks. We introduce *multi-modal instruction* for image generation, a task representation articulating a range of generation intents with precision. Human evaluation on various image generation datasets reveals that instruct-imagen matches or surpasses prior task-specific models in-domain.
  arXiv  Detail & Related papers  (2024-01-03T19:31:58Z)
• Jointly Training Large Autoregressive Multimodal Models [37.32912103934043]
  We present the Joint Autoregressive Mixture (JAM) framework, a modular approach that systematically fuses existing text and image generation models. We also introduce a specialized, data-efficient instruction-tuning strategy, tailored for mixed-modal generation tasks. Our final instruct-tuned model demonstrates unparalleled performance in generating high-quality multimodal outputs.
  arXiv  Detail & Related papers  (2023-09-27T10:40:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.