T2I Generation

T2I: Text-to-Image

Ask about this topic

Overview

Text-to-image generation studies how models turn natural-language instructions into images, primarily using diffusion and flow-matching models, autoregressive visual-token models, and unified multimodal systems. Researchers improve prompt following through better text and visual representations, spatial planning, reference-image conditioning, and post-training with preference or rubric-based rewards. Benchmarks test compositional alignment, counting, text rendering, world knowledge, and visual quality, while audits examine bias, privacy, and harmful outputs. A central challenge is making generations reliably match complex instructions and real-world constraints without sacrificing diversity, image quality, efficiency, or safety.

Latest papers

CardsList

302 papers45 papers in the last four weeks, up 88% on the four weeks before. 0.3% of all new papers.

Feb 24, 2026

CleanStyle: Plug-and-Play Style Conditioning Purification for Text-to-Image Stylization

Style transfer in diffusion models enables controllable visual generation by injecting the style of a reference image. However, recent encoder-based methods, while efficient and tuning-free, often suffer from content leakage, where semantic elements from the style image undesirably appear in the output, impairing prompt fidelity and stylistic consistency. In this work, we introduce CleanStyle, a plug-and-play framework that filters out content-related noise from the style embedding without retraining. Motivated by empirical analysis, we observe that such leakage predominantly stems from the tail components of the style embedding, which are isolated via Singular Value Decomposition (SVD). To address this, we propose CleanStyleSVD (CS-SVD), which dynamically suppresses tail components using a time-aware exponential schedule, providing clean, style-preserving conditional embeddings throughout the denoising process. Furthermore, we present Style-Specific Classifier-Free Guidance (SS-CFG), which reuses the suppressed tail components to construct style-aware unconditional inputs. Unlike conventional methods that use generic negative embeddings (e.g., zero vectors), SS-CFG introduces targeted negative signals that reflect style-specific but prompt-irrelevant visual elements. This enables the model to effectively suppress these distracting patterns during generation, thereby improving prompt fidelity and enhancing the overall visual quality of stylized outputs. Our approach is lightweight, interpretable, and can be seamlessly integrated into existing encoder-based diffusion models without retraining. Extensive experiments demonstrate that CleanStyle substantially reduces content leakage, improves stylization quality and improves prompt alignment across a wide range of style references and prompts.

Xiaoman Feng, Mingkun Lei, Yang Wang +2

AGI Lab, Westlake University

Image Style TransferT2I Diffusion ModelsT2I GenerationDiffusion Model Guidance
AskPDF
Feb 24, 2026

BBQ-to-Image: Numeric Bounding Box and Qolor Control in Large-Scale Text-to-Image Models

Text-to-image models have rapidly advanced in realism and controllability, with recent approaches leveraging long, detailed captions to support fine-grained generation. However, a fundamental parametric gap remains: existing models rely on descriptive language, whereas professional workflows require precise numeric control over object location, size, and color. In this work, we introduce BBQ, a large-scale text-to-image model that directly conditions on numeric bounding boxes and RGB triplets within a unified structured-text framework. We obtain precise spatial and chromatic control by training on captions enriched with parametric annotations, without architectural modifications or inference-time optimization. This also enables intuitive user interfaces such as object dragging and color pickers, replacing ambiguous iterative prompting with precise, familiar controls. Across comprehensive evaluations, BBQ achieves strong box alignment and improves RGB color fidelity over state-of-the-art baselines. More broadly, our results support a new paradigm in which user intent is translated into an intermediate structured language, consumed by a flow-based transformer acting as a renderer and naturally accommodating numeric parameters.

Eliran Kachlon, Alexander Visheratin, Nimrod Sarid +6

BRIA AI

Geometry-Conditioned Image GenerationT2I GenerationControllable Image GenerationConditional Image Generation
AskPDF
Feb 23, 2026

ConceptPrism: Concept Disentanglement in Personalized Diffusion Models via Residual Token Optimization

Personalized text-to-image (T2I) generation has emerged as a key application for creating user-specific concepts from a few reference images. The core challenge is concept disentanglement: separating the target concept from irrelevant residual information. Lacking such disentanglement, capturing high-fidelity features often incorporates undesired attributes that conflict with user prompts, compromising the trade-off between concept fidelity and text alignment. While existing methods rely on manual guidance, they often fail to represent intricate visual details and lack scalability. We introduce ConceptPrism, a framework that extracts shared features exclusively through cross-image comparison without external information. We jointly optimize a target token and image-wise residual tokens via reconstruction and exclusion losses. By suppressing shared information in residual tokens, the exclusion loss creates an information vacuum that forces the target token to capture the common concept. Extensive evaluations demonstrate that ConceptPrism achieves accurate concept disentanglement and significantly improves overall performance across diverse and complex visual concepts. The code is available at https://github.com/Minseo-Kimm/ConceptPrism.

Minseo Kim, Minchan Kwon, Dongyeun Lee +2

KAIST, South Korea · Hanbat National University, South Korea

T2I GenerationSubject-Driven Image GenerationT2I Diffusion Models
AskPDF
Feb 21, 2026

SCHEMA for Gemini 3 Pro Image: A Structured Methodology for Controlled AI Image Generation on Google's Native Multimodal Model

This paper presents SCHEMA (Structured Components for Harmonized Engineered Modular Architecture), a structured prompt engineering methodology specifically developed for Google Gemini 3 Pro Image. Unlike generic prompt guidelines or model-agnostic tips, SCHEMA is an engineered framework built on systematic professional practice encompassing 850 verified API predictions within an estimated corpus of approximately 4,800 generated images, spanning six professional domains: real estate photography, commercial product photography, editorial content, storyboards, commercial campaigns, and information design. The methodology introduces a three-tier progressive system (BASE, MEDIO, AVANZATO) that scales practitioner control from exploratory (approximately 5%) to directive (approximately 95%), a modular label architecture with 7 core and 5 optional structured components, a decision tree with explicit routing rules to alternative tools, and systematically documented model limitations with corresponding workarounds. Key findings include an observed 91% Mandatory compliance rate and 94% Prohibitions compliance rate across 621 structured prompts, a comparative batch consistency test demonstrating substantially higher inter-generation coherence for structured prompts, independent practitioner validation (n=40), and a dedicated Information Design validation demonstrating >95% first-generation compliance for spatial and typographical control across approximately 300 publicly verifiable infographics. Previously published on Zenodo (doi:10.5281/zenodo.18721380).

Luca Cazzaniga

Independent Researcher — AI-Assisted Visual Production

Prompt Optimization for T2I GenerationControllable Image GenerationT2I GenerationImage Generation Evaluation
AskPDF
Feb 20, 2026

Multi-Level Conditioning by Pairing Localized Text and Sketch for Fashion Image Generation

Sketches offer designers a concise yet expressive medium for early-stage fashion ideation by specifying structure, silhouette, and spatial relationships, while textual descriptions complement sketches to convey material, color, and stylistic details. Effectively combining textual and visual modalities requires adherence to the sketch visual structure when leveraging the guidance of localized attributes from text. We present LOcalized Text and Sketch with multi-level guidance (LOTS), a framework that enhances fashion image generation by combining global sketch guidance with multiple localized sketch-text pairs. LOTS employs a Multi-level Conditioning Stage to independently encode local features within a shared latent space while maintaining global structural coordination. Then, the Diffusion Pair Guidance stage integrates both local and global conditioning via attention-based guidance within the diffusion model's multi-step denoising process. To validate our method, we develop Sketchy, the first fashion dataset where multiple text-sketch pairs are provided per image. Sketchy provides high-quality, clean sketches with a professional look and consistent structure. To assess robustness beyond this setting, we also include an "in the wild" split with non-expert sketches, featuring higher variability and imperfections. Experiments demonstrate that our method strengthens global structural adherence while leveraging richer localized semantic guidance, achieving improvement over state-of-the-art. The dataset, platform, and code are publicly available.

Ziyue Liu, Davide Talon, Federico Girella +5

University of Verona, 37129 Verona, Italy · Polytechnic Institute of Turin, 10129 Turin, Italy · Fondazione Bruno Kessler, 38123 Povo, Italy +1

Image GenerationConditional Image GenerationControllable Image GenerationT2I GenerationDiffusion-Based Image Generation
AskPDF
Feb 20, 2026

FIGURA: A Modular Prompt Engineering Method for Artistic Figure Photography in Safety-Filtered Text-to-Image Models

Safety filters in commercial text-to-image (T2I) models systematically block legitimate artistic content involving the human figure, treating classical nude photography with the same restrictiveness as explicit material. While prior research has documented this problem extensively, no operational system exists that enables professional artists to generate artistic figure photography within the constraints of active safety filters. We present the FIGURA Method (Framework for Intelligent Generation of Unrestricted Artistic Results), a modular prompt engineering system comprising eight interconnected knowledge files, empirically validated through 200+ documented generation tests on FLUX 2 Pro (Cloud) with active safety filters at the default tolerance level. Our systematic testing reveals several previously undocumented findings: (1) safety filters primarily detect absence descriptions (references to missing clothing) rather than presence descriptions (references to body form), which we formalize as the Golden Rule; (2) artistic references to painters function simultaneously as aesthetic guides and as safety anchors that alter filter behavior; (3) spatial context operates as an independent filter variable, with documented success rate hierarchies; and (4) geometric vocabulary for body description bypasses pattern recognition in silhouette contexts. The system achieves documented success rates between 80% and 90% across five structured prompt templates, demonstrating that the artistic censorship problem identified in recent literature admits practical, systematic solutions that work with active safety mechanisms rather than circumventing them.

Luca Cazzaniga

Independent Researcher, Monza, Italy

Prompt Optimization for T2I GenerationT2I GenerationSafe T2I Generation
AskPDF
Feb 20, 2026

Morphological Addressing of Identity Basins in Text-to-Image Diffusion Models

We demonstrate that morphological pressure creates navigable gradients at multiple levels of the text-to-image generative pipeline. In Study1, identity basins in Stable Diffusion 1.5 can be navigated using morphological descriptors -- constituent features like platinum blonde,'' beauty mark,'' and 1950s glamour'' -- without the target's name or photographs. A self-distillation loop (generating synthetic images from descriptor prompts, then training a LoRA on those outputs) achieves consistent convergence toward a specific identity as measured by ArcFace similarity. The trained LoRA creates a local coordinate system shaping not only the target identity but also its inverse: maximal away-conditioning produces eldritch'' structural breakdown in base SD1.5, while the LoRA-equipped model produces ``uncanny valley'' outputs -- coherent but precisely wrong. In Study2, we extend this to prompt-level morphology. Drawing on phonestheme theory, we generate 200 novel nonsense words from English sound-symbolic clusters (e.g., cr-, sn-, -oid, -ax) and find that phonestheme-bearing candidates produce significantly more visually coherent outputs than random controls (mean Purity@1 = 0.371 vs.\ 0.209, p<0.00001p < 0.00001 p<0.00001, Cohen's d=0.55d = 0.55 d=0.55). Three candidates -- snudgeoid, crashax, and broomix -- achieve perfect visual consistency (Purity@1 = 1.0) with zero training data contamination, each generating a distinct, coherent visual identity from phonesthetic structure alone. Together, these studies establish that morphological structure -- whether in feature descriptors or prompt-level phonological form -- creates systematic navigational gradients through diffusion model latent spaces. We document phase transitions in identity basins, CFG-invariant identity stability, and novel visual concepts emerging from sub-lexical sound patterns.

Andrew Fraser

T2I GenerationT2I Diffusion ModelsSubject-Driven Image Generation
AskPDF
Feb 19, 2026

GASS: Geometry-Aware Spherical Sampling for Disentangled Diversity Enhancement in Text-to-Image Generation

Despite high semantic alignment, modern text-to-image (T2I) generative models still struggle to synthesize diverse images from a given prompt. In this work, we enhance the T2I diversity through a geometric lens. Unlike most existing methods that rely primarily on entropy-based guidance to increase sample dissimilarity, we introduce Geometry-Aware Spherical Sampling (GASS) to enhance diversity by explicitly controlling both prompt-dependent and prompt-independent sources of variation. Specifically, we decompose the diversity measure in CLIP embeddings using two orthogonal directions: the text embedding, which captures semantic variation related to the prompt, and an identified orthogonal direction that captures prompt-independent variation (e.g., backgrounds). Based on this decomposition, GASS increases the geometric projection spread of generated image embeddings along both axes and guides the T2I sampling process via expanded predictions along the generation trajectory. Our experiments on different frozen T2I backbones (U-Net and DiT, diffusion and flow) and benchmarks demonstrate the effectiveness of disentangled diversity enhancement with minimal impact on image fidelity and semantic alignment.

Ye Zhu, Kaleb S. Newman, Johannes F. Lutzeyer +3

Laboratoire d’Informatique (LIX), CNRS, École Polytechnique, IPP, France · Department of Computer Science, Princeton University, USA · FAIR at Meta - Montreal, Canada +3

T2I GenerationT2I Diffusion ModelsDiffusion Sampling
AskPDF
Feb 4, 2026

Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design

Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these tasks remain challenging because diffusion models have intractable likelihoods, which creates a barrier for directly applying popular policy-gradient type methods. Existing approaches primarily focus on crafting new objectives built on already heavily engineered LLM objectives, using ad hoc estimators for likelihood, without a thorough investigation into how such estimation affects overall algorithmic performance. In this work, we provide a systematic analysis of the RL design space by disentangling three factors: i) policy-gradient objectives, ii) likelihood estimators, and iii) rollout sampling schemes. We show that adopting an evidence lower bound (ELBO) based model likelihood estimator, computed only from the final generated sample, is the dominant factor enabling effective, efficient, and stable RL optimization, outweighing the impact of the specific policy-gradient loss functional. We validate our findings across multiple reward benchmarks using SD 3.5 Medium, and observe consistent trends across all tasks. Our method improves the GenEval score from 0.24 to 0.95 in 90 GPU hours, which is 4.6 times more efficient than FlowGRPO and 2×2\times more efficient than the SOTA method without reward hacking.

Jaemoo Choi, Yuchen Zhu, Wei Guo +6

Georgia Institute of Technology · National University of Singapore · Nanjing university.

T2I GenerationDiffusion Model Fine-TuningPolicy Gradient MethodsRL for Diffusion ModelsDiffusion Models
AskPDF
Jan 25, 2026

Uni-RS: A Spatially Faithful Unified Understanding and Generation Model for Remote Sensing

Unified remote sensing multimodal models exhibit a pronounced spatial reversal curse: Although they can accurately recognize and describe object locations in images, they often fail to faithfully execute the same spatial relations during text-to-image generation, where such relations constitute core semantic information in remote sensing. Motivated by this observation, we propose Uni-RS, the first unified multimodal model tailored for remote sensing, to explicitly address the spatial asymmetry between understanding and generation. Specifically, we first introduce explicit Spatial-Layout Planning to transform textual instructions into spatial layout plans, decoupling geometric planning from visual synthesis. We then impose Spatial-Aware Query Supervision to bias learnable queries toward spatial relations explicitly specified in the instruction. Finally, we develop Image-Caption Spatial Layout Variation to expose the model to systematic geometry-consistent spatial transformations. Extensive experiments across multiple benchmarks show that our approach substantially improves spatial faithfulness in text-to-image generation, while maintaining strong performance on multimodal understanding tasks like image captioning, visual grounding, and VQA tasks.

Weiyu Zhang, Yuan Hu, Yong Li +1

Institute of Remote Sensing and Geographic Information System, School of Earth and Space Sciences, Peking University, Beijing, 100871, China · Department of Civil and Environmental Engineering, The Hong Kong University of Science and Technology, Hong Kong

Unified Multimodal ModelsMultimodal GenerationT2I GenerationMultimodal Understanding
AskPDF
Jan 7, 2026

Unified Text-Image Generation with Weakness-Targeted Post-Training

Unified multimodal generation architectures that jointly produce text and images have recently emerged as a promising direction for text-to-image (T2I) synthesis. However, many existing systems rely on explicit modality switching, generating reasoning text before switching manually to image generation. This separate, sequential inference process limits cross-modal coupling and prohibits automatic multimodal generation. This work explores post-training to achieve fully unified text-image generation, where a model autonomously transitions from textual reasoning to visual synthesis within a single inference process. We study this on BAGEL, a 14B mixture-of-transformers model that pairs autoregressive text generation with flow-matching image synthesis. We examine the impact of joint text-image generation on T2I performance and the relative importance of each modality during post-training. We additionally explore different post-training data strategies, showing that a targeted dataset addressing specific limitations achieves superior results compared to broad image-caption corpora or benchmark-aligned data. Using offline, reward-weighted post-training with fully self-generated synthetic data, our approach enables improvements in multimodal image generation across four diverse, independent T2I benchmarks, demonstrating the effectiveness of reward-weighting both modalities and strategically designed post-training data.

Jiahui Chen, Philippe Hansen-Estruch, Xiaochuang Han +7

FAIR at Meta · University of Texas, Austin · Work done at Meta +2

Unified Multimodal ModelsT2I GenerationLLM Post-Training
AskPDF
Dec 17, 2025

GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models

The text encoder is a critical component of text-to-image and text-to-video diffusion models, fundamentally determining the semantic fidelity of the generated content. However, its development has been hindered by two major challenges: the lack of an efficient evaluation framework that reliably predicts downstream generation performance, and the difficulty of effectively adapting pretrained language models for visual synthesis. To address these issues, we introduce GRAN-TED, a paradigm to Generate Robust, Aligned, and Nuanced Text Embeddings for Diffusion models. Our contribution is twofold. First, we propose TED-6K, a novel text-only benchmark that enables efficient and robust assessment of an encoder's representational quality without requiring costly end-to-end model training. We demonstrate that performance on TED-6K, standardized via a lightweight, unified adapter, strongly correlates with an encoder's effectiveness in downstream generation tasks. Notably, under our experimental setup, compared with training a diffusion model from scratch, evaluating with TED-6K is about \textbf{750×\times faster}. Second, guided by this validated framework, we develop a superior text encoder using a novel two-stage training paradigm. This process involves an initial fine-tuning stage on a Multimodal Large Language Model for better visual representation, followed by a layer-wise weighting method to extract more nuanced and potent text features. Our experiments show that the resulting GRAN-TED encoder not only achieves state-of-the-art performance on TED-6K but also leads to demonstrable performance gains in text-to-image and text-to-video generation. Our TED-6K dataset and evaluation code are available at the following link: https://anonymous.4open.science/r/GRAN-TED-4FCC/.

Bozhou Li, Sihan Yang, Yushuo Guan +6

Peking University · Kling Team, Kuaishou Technology · Xi’an Jiaotong University +1

Text Embedding EvaluationT2I GenerationText Embedding ModelsT2I Diffusion Models
AskPDF
Dec 10, 2025

Dynamic Image Prompt Adapter for Scalable Zero-shot Personalized Text-to-Image Generation

Personalized Text-to-Image (PT2I) generation aims to produce customized images based on reference images. A prominent interest pertains to the integration of an image prompt adapter to facilitate zero-shot PT2I without test-time fine-tuning. However, current methods grapple with three fundamental challenges: 1. the elusive equilibrium between Concept Preservation (CP) and Prompt Following (PF), 2. the difficulty in retaining fine-grained concept details in reference images, and 3. the restricted scalability to extend to multi-subject personalization. To tackle these challenges, we present Dynamic Image Prompt Adapter (DynaIP), a cutting-edge plugin to enhance the fine-grained concept fidelity, CP-PF balance, and subject scalability of state-of-the-art T2I multimodal diffusion transformers (MM-DiT) for PT2I generation. Our key finding is that MM-DiT inherently exhibit decoupling learning behavior when injecting reference image features into its dual branches via cross attentions. Based on this, we design an innovative Dynamic Decoupling Strategy that removes the interference of concept-agnostic information during inference, significantly enhancing the CP-PF balance and further bolstering the scalability of multi-subject compositions. Moreover, we identify the visual encoder as a key factor affecting fine-grained CP and reveal that the hierarchical features of commonly used CLIP can capture visual information at diverse granularity levels. Therefore, we introduce a novel Hierarchical Mixture-of-Experts Feature Fusion Module to fully leverage the hierarchical features of CLIP, remarkably elevating the fine-grained concept fidelity while also providing flexible control of visual granularity. Extensive experiments across single- and multi-subject PT2I tasks verify that our DynaIP outperforms existing approaches, while requiring only single-subject training datasets.

Zhizhong Wang, Tianyi Chu, Zeyi Huang +2

Central Media Technology Institute, Huawei

Subject-Driven Image GenerationT2I GenerationCompositional T2I GenerationT2I Diffusion Models
AskPDF
Nov 27, 2025

Anchor to Expand: Semantic Anchoring for Personalized Text-to-Image Diffusion Models

Personalizing text-to-image diffusion models extends pretrained models to represent novel user-specific concepts from only a few reference images. However, learning a new concept while building on the prior knowledge of the pretrained model remains a key challenge. When personalization focuses on learning the target concept, the model tends to overfit the reference examples and degrade its general capability. In contrast, emphasizing prior preservation can hinder capturing distinctive personalized attributes. In this paper, we address this challenge by viewing a personalized concept as an underrepresented concept whose semantic counterpart is well represented in the pretrained model. Rather than treating the learning of a new concept and prior preservation as separate objectives, we reformulate them as a single anchored learning problem. We therefore introduce Semantic Anchoring Personalization (SAP), which keeps concept learning grounded in the pretrained semantic structure while capturing subject-specific attributes. The proposed objective offers a simple yet effective formulation that can be applied across different model backbones without architectural modifications or auxiliary networks. Extensive experiments across various settings demonstrate that SAP achieves a better balance between subject fidelity and text-image alignment than baseline methods. Further ablation studies validate the contribution of semantic anchoring to personalization.

Seoyun Yang, Gihoon Kim, Taesup Kim

Graduate School of Data Science, Seoul National University

Subject-Driven Image GenerationT2I GenerationDiffusion Model Fine-TuningT2I Diffusion Models
AskPDF
Nov 25, 2025

RubricRL: Simple Generalizable Rewards for Text-to-Image Generation

Reinforcement learning (RL) has recently emerged as a promising approach for aligning text-to-image generative models with human preferences. A key challenge, however, lies in designing effective and interpretable rewards. Existing methods often rely on either composite metrics (e.g., CLIP, OCR, and realism scores) with fixed weights or a single scalar reward distilled from human preference models, which can limit interpretability and flexibility. We propose RubricRL, a simple and general framework for rubric-based reward design that offers greater interpretability, composability, and user control. Instead of using a black-box scalar signal, RubricRL dynamically constructs a structured rubric for each prompt--a decomposable checklist of fine-grained visual criteria such as object correctness, attribute accuracy, OCR fidelity, and realism--tailored to the input text. Each criterion is independently evaluated by a multimodal judge (e.g., o4-mini), and a prompt-adaptive weighting mechanism emphasizes the most relevant dimensions. This design not only produces interpretable and modular supervision signals for policy optimization (e.g., GRPO or PPO), but also enables users to directly adjust which aspects to reward or penalize. Experiments with an autoregressive text-to-image model demonstrate that RubricRL improves prompt faithfulness, visual detail, and generalizability, while offering a flexible and extensible foundation for interpretable RL alignment across text-to-image architectures.

Xuelu Feng, Yunsheng Li, Ziyu Wan +4

University at Buffalo · Microsoft AI · Nikola Tesla STEM High School

Reward ModelingT2I GenerationMultimodal Reward ModelingRubric-Based RLRL for Image Generation
AskPDF
Nov 25, 2025

Diversifying Long Prompt Image Generation through Structured Prompt Embedding Space Sampling

Modern text-to-image models produce impressive visual results from richly specified prompts, yet their behavior under long prompts remains insufficiently understood. In this paper, we study a practical failure mode in which accumulated semantic constraints progressively suppress output variation, causing diversity to collapse even when many visual factors remain unspecified. We show that this phenomenon appears consistently across recent generation models as prompt length increases, and provide a theoretical motivation that connects long-prompt conditioning with reduced sampling entropy in the prompt embedding space. Based on this observation, we introduce PromptMoG, a training-free approach that samples prompt embeddings from a Mixture-of-Gaussians distribution to restore generative flexibility while maintaining semantic fidelity. To support systematic evaluation, we further present LPD-Bench, a structured benchmark of long and semantically dense prompts for measuring both fidelity and diversity under compositional text conditioning. Extensive experiments on four large-scale diffusion models, including SD3.5-Large, Flux.1-Krea-Dev, CogView4, and Qwen-Image, show that PromptMoG consistently improves diversity for long-prompt image generation. The code is publicly available at https://github.com/basiclab/PromptMoG.

Bo-Kai Ruan, Teng-Fang Hsiao, Ling Lo +2

Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan · Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan

T2I GenerationDiffusion ModelsT2I Generation Evaluation
AskPDF
Nov 25, 2025

TPSO: Training-Free Diverse Image Generation via Semantic Prompt Embedding Optimization

Image diversity remains a fundamental challenge for text-to-image diffusion models. Low-diversity generation often leads to repetitive outputs, increasing sampling redundancy and hindering both creative exploration and downstream applications. A key factor is the tendency of diffusion models to collapse toward strong modes in the learned distribution. Existing attempts to improve diversity, such as steering-based guidance, often introduce distortions that degrade image quality. To address this issue, we propose Token-Prompt Embedding Space Optimization (TPSO), a training-free and model-agnostic module. TPSO introduces learnable parameters to explore underrepresented regions of the token embedding space, reducing the tendency to repeatedly sample from strong modes of the distribution. Meanwhile, a prompt-level semantic constraint regulates distribution shifts, preventing quality degradation while preserving semantic fidelity. Extensive experiments on MS-COCO across three representative diffusion backbones demonstrate that TPSO substantially improves diversity, boosting performance from 1.10 to 4.18, while maintaining image quality with only a modest inference-time overhead of 3.6% to 8.9%. Code is available at: https://github.com/Open-Debin/TPSO.

Debin Meng, Chen Jin, Zheng Gao +3

Queen Mary University of London · Centre for AI, AstraZeneca, UK · University of Bedfordshire +1

T2I GenerationT2I Diffusion Models
AskPDF
Nov 5, 2025

Inference-Time Optimization of Prompt Embeddings in Diffusion Models: A Comparison of sep-CMA-ES and Adam

Deep diffusion models have revolutionized image generation by producing high-quality outputs. However, achieving specific objectives with these models often requires costly adaptations such as fine-tuning, which can be resource-intensive and time-consuming. An alternative approach is inference-time control, which involves optimizing the prompt embeddings to guide the generation process without altering the model weights. We explore prompt-embedding search optimization for the Stable Diffusion XL Turbo model, comparing a gradient-free evolutionary approach, the Separable Covariance Matrix Adaptation Evolution Strategy (sep-CMA-ES), against the widely used gradient-based optimizer Adaptive Moment Estimation (Adam). Candidate images are evaluated by a weighted objective that combines LAION Aesthetic Predictor V2 and CLIPScore, enabling explicit trade-offs between aesthetic quality and prompt-image alignment. On 36 prompts sampled from Parti Prompts (P2) under three weight settings (aesthetics-only, balanced, alignment-only), sep-CMA-ES consistently achieves higher objective values than Adam. We additionally analyze divergence from the unoptimized baseline using cosine similarity and SSIM and report the compute and memory footprints. These results suggest that sep-CMA-ES is an effective inference-time optimizer for prompt-embedding search, improving aesthetics-alignment trade-offs and resource usage without model fine-tuning.

Domício Pereira Neto, João Correia, Penousal Machado

University of Coimbra Coimbra, Portugal

T2I GenerationDiffusion Models
AskPDF
Oct 18, 2025

SELECT: Semantic Erasure Boundary Construction with Sibling Exclusive Counterfactuals

Concept erasure aims to suppress undesirable concepts in text-to-image diffusion models while preserving their generative capabilities. Existing methods often redirect target concepts toward predefined semantic anchors, but the influence of anchor selection on the scope of concept erasure remains insufficiently understood. Through causal tracing, we reveal that concepts with more dispersed causal effects tend to exhibit higher anchor sensitivity and lower erasure robustness. Controlled anchor interventions demonstrate that anchor selection affects target suppression and collateral damage to surrounding semantic concepts. These findings motivate us to formulate anchor selection as semantic erasure boundary construction. We propose SELECT (Selective Erasure via Local Exclusive Counterfactual Targets), a plug-and-play framework based on Sibling Exclusive Concepts (SECs), which are semantically close to the target but mutually exclusive in its defining attributes. SELECT jointly constructs a counterfactual redirection endpoint and a local retention set to balance target suppression and semantic preservation. SELECT filters candidates using contextual activation, and uses semantic coherence to identify context compatible redirection endpoints, while the remaining SECs serve as local preservation constraints. Experiments on object, celebrity, artist-style, and NSFW erasure show that SELECT strengthens target suppression over fixed general anchors and achieves suppression-preservation trade-offs, while reducing concept re-emergence and erosion.

Tong Zhang, Ru Zhang, Jianyi Liu +1

Beijing University of Posts and Telecommunications, School of Cyberspace Security, Beijing, 100876

Concept ErasureT2I Generation
AskPDF
Oct 14, 2025

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models

Recently, remarkable progress has been made in Unified Multimodal Models (UMMs), which integrate vision-language generation and understanding capabilities within a single framework. However, a model's strong visual understanding often fails to transfer to visual generation: it may correctly judge prompt-image alignment while failing to generate a faithful image from the same prompt. This raises a compelling question: Can a model improve itself by using its understanding module to reward its generation module? We introduce SRUM, a self-rewarding post-training framework directly applicable to existing UMMs of various designs. SRUM creates a feedback loop where the model's own understanding module acts as an internal ``evaluator'', providing corrective signals to improve generation without additional human-labeled data or external reward models. To provide comprehensive feedback, SRUM uses a global-local dual reward system: a global reward ensures overall visual semantics and layout, while a local reward refines fine-grained, object-level fidelity. SRUM shows strong generalization, boosting performance on T2I-CompBench from 82.18 to 88.37 and on T2I-ReasonBench from 43.82 to 46.75. Overall, our work establishes a powerful paradigm for enabling a UMM's understanding module to guide and enhance its own generation via self-rewarding.

Weiyang Jin, Yuwei Niu, Jiaqi Liao +4

HKU MMLab · The University of Hong Kong · Shenzhen Loop Area Institute +2

Unified Multimodal ModelsT2I GenerationGenerative ModelingMultimodal Reward ModelingRL for Image GenerationMultimodal Foundation Models
AskPDF
Sep 29, 2025

Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models

Reinforcement Learning (RL) has emerged as a central paradigm for advancing Large Language Models (LLMs), where both pre-training and RL post-training stages are grounded in the same log-likelihood formulation. In contrast, recent RL approaches for diffusion models, most notably Denoising Diffusion Policy Optimization (DDPO), optimize an objective different from the pretraining objectives--score/flow matching loss. In this work, we establish a novel theoretical analysis: DDPO is an implicit form of score/flow matching with noisy targets, which increases variance and slows convergence. Building on this analysis, we introduce Advantage Weighted Matching (AWM), a policy-gradient method for diffusion. It uses the score/flow-matching loss and reweights each sample by its advantage. In effect, AWM raises the influence of high-reward samples and suppresses low-reward ones while keeping the modeling objective identical to pretraining. This simple yet effective design yields substantial benefits: on the GenEval, OCR, and PickScore benchmarks, AWM delivers up to a 34×34\times speedup over Flow-GRPO (which builds on DDPO), when applied to Stable Diffusion 3.5 Medium and FLUX, without compromising generation quality. Code is available at https://github.com/scxue/advantage_weighted_matching

Shuchen Xue, Chongjian Ge, Shilong Zhang +2

UCAS · Adobe Research · HKU +1

Score MatchingDiffusion Model AlignmentT2I GenerationRL for Image GenerationRL for Diffusion Models
AskPDF
Sep 28, 2025

Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance

Autoregressive (AR) models based on next-scale prediction have emerged as a powerful tool for image generation, but they face a critical weakness: information inconsistencies between patches across timesteps introduced by progressive resolution scaling. These inconsistencies scatter guidance signals, causing them to drift away from salient regions within the image and leaving behind ambiguous, unfaithful features during sampling. We tackle this challenge with Information-Grounding Guidance (IGG), a novel framework that anchors guidance to semantically important tokens via an attention-based dynamic weighting formulation, consequently ensuring that guidance and semantic contents remain tightly aligned. Across both class-conditioned and text-to-image generation tasks, IGG delivers sharper, more coherent, and semantically grounded images, demonstrating its efficacy for correcting AR-based methods. Our code is available at https://github.com/dnngky/infoground-guidance.

Ky Dan Nguyen, Hoang Lam Tran, Anh-Dung Dinh +4

The University of Sydney, Sydney, New South Wales, Australia · The University of Western Australia, Perth, Western Australia, Australia

Visual Autoregressive ModelsConditional Image GenerationT2I GenerationAutoregressive Image Generation
AskPDF
Jul 22, 2025

Test-time Prompt Refinement for Text-to-Image Models

Text-to-image (T2I) generation models have made significant strides but still struggle with prompt sensitivity: even minor changes in prompt wording can yield inconsistent or inaccurate outputs. To address this challenge, we introduce a closed-loop, test-time prompt refinement framework that requires no additional training of the underlying T2I model, termed TIR. In our approach, each generation step is followed by a refinement step, where a pretrained multimodal large language model (MLLM) analyzes the output image and the user's prompt. The MLLM detects misalignments (e.g., missing objects, incorrect attributes) and produces a refined and physically grounded prompt for the next round of image generation. By iteratively refining the prompt and verifying alignment between the prompt and the image, TIR corrects errors, mirroring the iterative refinement process of human artists. We demonstrate that this closed-loop strategy improves alignment and visual coherence across multiple benchmark datasets, all while maintaining plug-and-play integration with black-box T2I models. Code is available at https://github.com/hafeezkhan909/Test-time-Image-Refinement.

Mohammad Abdul Hafeez Khan, Yash Jain, Siddhartha Bhattacharyya +1

Florida Institute of Technology, USA · Microsoft Research, USA

Text-Image AlignmentT2I GenerationPrompt Optimization for T2I Generation
AskPDF
Jun 20, 2025

AI's Blind Spots: Geographic Knowledge and Diversity Deficit in Generated Urban Scenario

Diffusion-based text-to-image models are increasingly used for urban analysis and scenario generation, but their geographic knowledge and representational biases remain poorly understood. We evaluate FLUX 1-schnell and Stable Diffusion 3.5-Large in the United States by generating 150 street-view images for each state, each state capital, and a generic "USA" prompt. Images are embedded with DINO-v2 ViT-S/14 and compared with Fréchet Inception Distance (FID). Pairwise FID clustering shows that geographically proximate states and capitals often group together, indicating implicit geographic structure. However, the generic ``USA'' prompt collapses this diversity into a metropolitan stereotype: frontier, desert, tropical, rural, and small-city environments are underrepresented or distant in FID space. These results show that diffusion models can encode fine-grained geography while still reproducing narrow national-scale visual stereotypes.

Ciro Beneduce, Massimiliano Luca, Bruno Lepri

* Bruno Kessler Foundation · **University of Trento

T2I GenerationT2I Generation EvaluationT2I Diffusion Models
AskPDF
Jun 4, 2025

Mitigating Task Objective Conflicts for Continual Learning in Unified Multimodal Models

Recent advances in unified autoregressive (AR) models have enabled multimodal understanding (MMU) and text-to-image generation (T2I) within a single architecture. However, in continual learning settings, their divergent objectives can induce task interference, hindering knowledge preservation and adaptation to new tasks. In this work, we investigate Task Objective Conflict (TOC) through theoretical and empirical analyses, revealing conflicting optimization directions at the task level but complementary interactions at the token level. These findings suggest that continual adaptation requires mitigating task interference while preserving beneficial cross-task knowledge sharing. To this end, we propose UniDecouple, a selective decoupling framework based on a Task-Aware Mixture-of-Experts (TA-MoE) architecture. Specifically, UniDecouple retains shared attention layers to preserve common contextual dependencies while introducing task-specific feed-forward network (FFN) experts to mitigate optimization conflicts. Furthermore, hierarchical expert routing enables adaptive expert selection, while hybrid expert collaboration leverages shared experts to facilitate cross-task knowledge transfer. A two-stage training strategy further balances task specialization and coordinated adaptation. Extensive experiments and ablation studies demonstrate that UniDecouple improves both multimodal understanding and image generation performance under a comparable per-token activation budget, achieving a favorable balance between knowledge preservation and task adaptation in continual learning.

Jiaxing Zhang, Hao Tang

Sichuan University, Chengdu, China · Peking University, Beijing, China

Task InterferenceUnified Multimodal ModelsMultimodal UnderstandingT2I GenerationMixture of Experts
AskPDF
May 27, 2025

ISAC: Training-Free Instance-to-Semantic Attention Control for Multi-Instance Generation

Recent open-weight text-to-image (T2I) diffusion models still struggle with multi-instance prompts, often omitting or merging instances and mixing semantics among similar objects. We trace these failures to early denoising steps, before instance boundaries are reliably stabilized. Existing training-free guidance is largely driven by cross-attention or other token-conditioned semantic signals. Such guidance can separate concepts at the token level, but largely assumes that distinct instance regions have already emerged. In early denoising steps, it cannot reliably carve out these regions, so count failures and semantic mixing persist. By contrast, self-attention exposes class-agnostic instance layouts during early denoising. To exploit this asymmetry, we propose ISAC\textbf{ISAC} (I\textbf{I}nstance-to-S\textbf{S}emantic A\textbf{A}ttention C\textbf{C}ontrol), a training-free, model-agnostic objective that first stabilizes self-attention layouts and then binds cross-attention semantics within them, without fine-tuning or external vision models. Across T2I-CompBench, HRS-Bench, and our newly curated IntraCompBench, ISAC consistently outperforms prior training-free methods. Furthermore, ISAC enhances layout-to-image controllers by refining coarse, overlapping bounding boxes into dense instance masks. Code and IntraCompBench are available at https://shjo-april.github.io/ISAC.

Sanghyun Jo, Wooyeol Lee, Ziseok Lee +3

OGQ, Seoul, Korea · Seoul National University, Seoul, Korea

Controllable Image GenerationT2I GenerationAttention Control in Diffusion ModelsDiffusion Model GuidanceCompositional T2I GenerationAttention Mechanisms+1
AskPDF
May 2, 2025

WorldGenBench: A World-Knowledge-Integrated Benchmark for Reasoning-Driven Text-to-Image Generation

Recent text-to-image (T2I) models achieve high visual fidelity and accurate explicit grounding from input prompts. However, image generation is fundamentally a process of semantic expansion. Beyond surface-level descriptions, generating authentic visual content requires supplementing prompts with unstated cues, a crucial step that current models frequently overlook. In response, we introduce WorldGenBench, a benchmark designed to evaluate how well T2I systems integrate factual grounding with contextual inference. Unlike prior work that isolates these abilities, WorldGenBench emphasizes their synergy, recognizing that true understanding requires both knowing and reasoning. To enable interpretable evaluation, we propose the Knowledge Checklist Score, which assesses whether generated images faithfully reflect key explicit and implicit semantic elements. Evaluating 24 models reveals persistent gaps: proprietary models like GPT-4o show strong integration, while most open-source systems lag, particularly in culturally diverse and scientific scenarios. Our analysis further identifies common failure modes, including semantic hallucination and the underrepresentation of non-Western knowledge, underscoring the limitations of current models in achieving real-world readiness. These findings highlight the need to guide future T2I models toward deeper, knowledge-aware generation. Project Page: https://dwanzhang-ai.github.io/WorldGenBench/

Ruoshi Xu, Daoan Zhang, Che Jiang +7

Southern University of Science and Technology · University of Rochester · New York University +2

T2I GenerationT2I Generation Evaluation
AskPDF
Mar 9, 2025

PixelPonder: Dynamic Patch Adaptation for Enhanced Multi-Conditional Text-to-Image Generation

Recent advances in diffusion-based text-to-image generation have demonstrated promising results through visual condition control. However, existing ControlNet-like methods struggle with compositional visual conditioning - simultaneously preserving semantic fidelity across multiple heterogeneous control signals while maintaining high visual quality, where they employ separate control branches that often introduce conflicting guidance during the denoising process, leading to structural distortions and artifacts in generated images. To address this issue, we present PixelPonder, a novel unified control framework, which allows for effective control of multiple visual conditions under a single control structure. Specifically, we design a patch-level adaptive condition selection mechanism that dynamically prioritizes spatially relevant control signals at the sub-region level, enabling precise local guidance without global interference. Additionally, a time-aware control injection scheme is deployed to modulate condition influence according to denoising timesteps, progressively transitioning from structural preservation to texture refinement and fully utilizing the control information from different categories to promote more harmonious image generation. Extensive experiments demonstrate that PixelPonder surpasses previous methods across different benchmark datasets, showing superior improvement in spatial alignment accuracy while maintaining high textual semantic consistency.

Yanjie Pan, Qingdong He, Zhengkai Jiang +9

Fudan University · Tencent Youtu Lab · Western University +1

T2I GenerationControllable Image GenerationT2I Diffusion ModelsCompositional T2I GenerationDiffusion Guidance
AskPDF
Feb 22, 2025

PersGuard: Preventing Malicious Personalization in Text-to-Image Diffusion Models via Model Backdoors

Diffusion models (DMs) have advanced text-to-image (T2I) synthesis, yet their personalization capabilities raise serious privacy and copyright concerns. Malicious actors can misuse these models to generate unauthorized portraits or artistic style replicas. Existing proactive defenses primarily rely on applying adversarial perturbations to reference images to disrupt training. However, these approaches face limitations: they assume all training images are pre-perturbed and are prone to failure when datasets contain unperturbed images or undergo minor data transformations. In this paper, we introduce PersGuard, a novel backdoor-based framework designed to prevent unauthorized personalization of pre-trained T2I diffusion models. Unlike perturbation-based methods, we assume protectors can embed protective backdoors into the models before their release. This mechanism ensures that if a downstream user fine-tunes the model on protected images, the model retains the backdoor and generates predefined protective outputs; conversely, for unprotected images, the backdoor is effectively removed during fine-tuning to ensure normal model utility. We formulate the backdoor injection as a unified optimization problem incorporating three objectives: a backdoor behavior loss to activate protection, a prior preservation loss to maintain standard generation capabilities, and a novel backdoor retention loss. The retention loss is specifically designed to mirror personalization loss, ensuring the backdoor remains robust during downstream fine-tuning. Extensive experiments across gray-box and black-box settings, multi-object protection, and facial identity protection demonstrate that PersGuard provides superior privacy protection compared to existing perturbation-based methods.

Xinwei Liu, Xiaojun Jia, Yuan Xun +2

Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing 100049, China · BraneMatrix AI, Shanghai 201203, China +1

T2I GenerationT2I Diffusion ModelsDiffusion Models
AskPDF
Feb 18, 2025

Comprehensive Assessment and Analysis for NSFW Content Erasure in Text-to-Image Diffusion Models

Text-to-image diffusion models have gained widespread application across various domains, demonstrating remarkable creative potential. However, the strong generalization capabilities of diffusion models can inadvertently lead to the generation of not-safe-for-work (NSFW) content, posing significant risks to their safe deployment. While several concept erasure methods have been proposed to mitigate the issue associated with NSFW content, a comprehensive evaluation of their effectiveness across various scenarios remains absent. To bridge this gap, we introduce a full-pipeline toolkit specifically designed for concept erasure and conduct the first systematic study of NSFW concept erasure methods. By examining the interplay between the underlying mechanisms and empirical observations, we provide in-depth insights and practical guidance for the effective application of concept erasure methods in various real-world scenarios, with the aim of advancing the understanding of content safety in diffusion models and establishing a solid foundation for future research and development in this critical area.

Die Chen, Zhiwen Li, Cen Chen +5

East China Normal University

T2I GenerationConcept ErasureT2I Generation EvaluationT2I Diffusion Models
AskPDF