# Images Talk Back: Guiding MMDiTs by Suppressing Image-to-Text Feedback

arXiv: https://arxiv.org/abs/2610.13941 · HTML: https://mlsanity.com/paper/2610.13941/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 30 of its 32 references that are in the map.
- First posted on arXiv 9 Oct 2026.

## 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 30)

- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [Guiding a Diffusion Model with a Bad Version of Itself](https://mlsanity.com/paper/2406.02507/) (2024)
- [T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation](https://mlsanity.com/paper/2307.06350/) (2023)
- [Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models](https://mlsanity.com/paper/2404.07724/) (2024)
- [Improving Sample Quality of Diffusion Models Using Self-Attention Guidance](https://mlsanity.com/paper/2210.00939/) (2022)
- [CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models](https://mlsanity.com/paper/2406.08070/) (2024)
- [Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models](https://mlsanity.com/paper/2409.10695/) (2024)
- [Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance](https://mlsanity.com/paper/2403.17377/) (2024)
- [Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention](https://mlsanity.com/paper/2408.00760/) (2024)
- [CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models](https://mlsanity.com/paper/2503.18886/) (2025)
- [Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models](https://mlsanity.com/paper/2508.12880/) (2025)
- [3DIS-FLUX: simple and efficient multi-instance generation with DiT rendering](https://mlsanity.com/paper/2501.05131/) (2025)
- [Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers](https://mlsanity.com/paper/2506.07986/) (2025)
- [Exploring Multimodal Diffusion Transformers for Enhanced Prompt-based Image Editing](https://mlsanity.com/paper/2508.07519/) (2025)
- [Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis](https://mlsanity.com/paper/2505.10046/) (2025)
- [Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models](https://mlsanity.com/paper/2501.06751/) (2025)
- [Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers](https://mlsanity.com/paper/2607.19139/) (2026)
- [Guiding a Diffusion Model by Swapping Its Tokens](https://mlsanity.com/paper/2604.08048/) (2026)
- [DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing](https://mlsanity.com/paper/2606.15796/) (2026)
- [Diagnosing and Correcting Concept Omission in Multimodal Diffusion Transformers](https://mlsanity.com/paper/2605.14270/) (2026)
- [GuidedBridge: Training-freely Improving Bridge Models with Prior Guidance](https://mlsanity.com/paper/2606.03119/) (2026)
- [Prompt Reinjection: Alleviating Prompt Forgetting in Multimodal Diffusion Transformers for Text-to-Image Generation](https://mlsanity.com/paper/2602.06886/) (2026)
- [Vision-Language Binding in In-Context Image Generation](https://mlsanity.com/paper/2605.24624/) (2026)

## Abstract (arXiv)

Multimodal diffusion transformers (MMDiTs) allow the evolving image to update internal text representations through joint attention. These representations then guide subsequent image updates, raising a question: does this feedback help correct deviations from the prompt, or preserve them? We find that image-to-text (I2T) feedback can preserve the objects and attributes already represented in the evolving image, including errors. Transplanting I2T messages can rescue failures or disrupt successes. At matched intervention strengths, suppressing the influence of I2T feedback improves generation, whereas opposite controls degrade it. These findings motivate Semantic Feedback Guidance (SFG), which suppresses the influence of I2T feedback by guiding away from an auxiliary branch that strengthens this feedback and weakens text-to-image conditioning. The in-place variant, iSFG, directly suppresses I2T feedback and strengthens text-to-image conditioning, requiring no extra model evaluations. Temporal interventions motivate running the SFG branch during the first 20% of image sampling steps, requiring about 1.2× the base NFE without classifier-free guidance (CFG). Experiments across three image-generation backbones show gains in alignment and preference-model scores. On FLUX, adding SFG to CFG raises GenEval from 0.6661 to 0.7479; on SD3.5M, iSFG adds +1.33 HPSv2.1 over CFG at zero extra NFE. The control also transfers to text-to-video and image-to-video generation, improving VBench scores. Code is available at https://github.com/yyc1215lll-creator/SFG.