T2I Generation Evaluation

Text-to-image models appear to reproduce the habits of the photographs they learned from. Analog clocks are an extreme case: in advertising, watches almost always show 10:10, and generated clocks return to 10:10 even when another time is requested. We measure this bias and test three ways of overcoming it on 52 models available on the Magnific platform, with a replication on Higgsfield. Every image shows three identical clocks that must show 2:35, 6:50 and 11:20. The description of the object is fixed and only the request about the time changes: no time (A), the time in digits (B), the hand positions described by construction relative to the dial numerals (C), or the same description plus a drawn reference dial (D). Two AI readers read all 1,799 images blind from coded copies, with a third reader and the author settling disagreements (dial-level agreement 96.0% and 97.3%). With no time requested, 67% of the images have all three clocks at 10:10. On the 20 current models, all three clocks are correct in 34% of the images with digits, 30% with the hands described in words and 75% with the reference dial (D-B: +37 points, 95% CI +28 to +45); we found no evidence that describing the hands in words beats the digits (C-B: -4 points, CI -10 to +1). The replication on the 12 models shared by both platforms gives the same picture (B 54%, C 50%, D 81%). Writing the time reduces the bias but leaves two thirds of the images of the 20 current models with at least one wrong clock; adding a drawn reference raises full accuracy to three quarters and almost eliminates images entirely at 10:10. We release all images, prompts, raw readings and a script that recomputes every result.

The reliability and accountability of image generative models (IGMs) are essential for building responsible and trustworthy AI systems. Recent IGMs, such as Nano Banana and GPT-Image, now support complex instruction following, realistic image synthesis, and controllable scene-text rendering. As these capabilities expand, safety analysis must also account for new control channels introduced by complex prompts. In this work, we study rendered-text semantic leakage, a largely overlooked phenomenon in open-domain text rendering. Although rendered text is intended to serve as a local visual constraint that should be reproduced verbatim in the generated image, it also carries linguistic semantics that may be interpreted by the model as part of the input instruction. This makes rendered text a potential semantic control channel whose safety implications remain insufficiently understood. We systematically characterize this phenomenon by decoupling the main visual prompt from the rendered text and measuring their individual and compositional effects on generated images. We quantify semantic leakage and rendering fidelity, and further analyze how leakage emerges from intermediate model evidence. We then show that harmful semantics embedded in scene text can persist through LLM-based prompt enhancement pipelines and steer non-text image regions, even when the main visual prompt remains benign. Finally, we propose a preliminary mitigation approach that reduces unsafe semantic transfer from rendered text to non-text regions while preserving the intended text-rendering behavior on FLUX-2-dev. Our findings reveal rendered text as a dual-use carrier of visible data and latent semantics, exposing a text-centric cross-modal attack surface in modern IGMs.

Image-generation models can now produce text-rich, natural-looking visual artifacts that are hard to distinguish from real-world evidence, such as news reports and textbook pages. Yet, the same capability introduces a new risk: these models can just as easily fabricate visual misinformation. Even commercial models (e.g., GPT-Image-2) readily produce it. Curiously, we find that these models can recognize a claim as false when asked, yet still render that very claim as credible visual evidence. This discrepancy points to a blind spot in current alignment: safeguards judge what an image shows, not what it asserts; however, existing red-teaming benchmarks target conventional harmful content, such as violent or explicit imagery, and say little about where the alignment boundaries lie for visual misinformation, especially in commercial models. To fill this gap, we introduce EpiReal-Bench, the first systematic benchmark for evaluating visual misinformation risks in commercial image generators, comprising 10k false-claim prompts and 10k corresponding generated images that span 10 real-world claim categories and 10 credible visual formats. We further introduce EpiReal-Attack, a skill-guided black-box optimization framework that uses Pareto-based selection and multimodal feedback to identify commands that bypass alignment safeguards while preserving visual realism, textual legibility, and semantic fidelity. Experiments on four commercial models reveal that more than 70% of false-claim prompts elicit images that faithfully depict the corresponding misinformation, and EpiReal-Attack pushes this rate to 95%. Most worryingly, these models are only a click away, and their outputs are cheap to spread yet hard to disbelieve, leaving this dimension of alignment largely unguarded.

Dense visual text requires image generators to reproduce long strings across multiple regions with correct placement and legibility. As short-string rendering improves, evaluation must test sustained performance across more demanding scenes. We introduce UltraText Bench, a bilingual benchmark for prompt-only generation of dense visual text. It contains 432 prompts spanning 24 real-world scene categories and three difficulty levels, split equally between English and Chinese. Each human-reviewed prompt supplies exact strings for four to twelve text regions, paired with structured references for their content, placement, and visual attributes. We use the Q-Judger vision-language model to assess each image against the complete reference, reporting text fidelity, text clarity, spatial quality, and scene quality. Across 24 model configurations, these dimensions reveal different strengths: Z-Image-Turbo gains 3.81 clarity points over Z-Image-Base while losing 14.76 fidelity points under the reported settings. Performance also varies with workload; Qwen-Image-2512's English composite falls from 86.50 at L1 to 42.86 at L3. Ten participants took part in human evaluation of the automatic scores. Repository: https://github.com/LINs-lab/UltraText_Bench.

Text-to-image generative models can produce highly realistic imagery but also raise concerns about harmful misuse. While safety mechanisms exist, systematic evaluations of their effectiveness against realistic attacks remain limited. We present a systematic evaluation of harmful content generation across five open text-to-image models using an automated pipeline that transforms legitimate news captions into unsafe prompts targeting sexually explicit content, violence/gore, harmful stereotypes, self-harm, and hate speech. We evaluate both standard models with built-in safety mechanisms and community fine-tuned variants that bypass content restrictions. A human evaluation of 1,500 generated images shows high harmful-content generation rates: 89.2% for gore-related prompts, 47.6% for sexually explicit content, 43.6% for harmful stereotypes, 46.0% for hate speech, and 34.5% for self-harm, predominantly through graphic violence. Models show substantial capability for generating violent and stereotypical content, while community fine-tuned variants are particularly vulnerable to sexually explicit prompts. Generation quality is largely preserved under harmful prompting, producing imagery of sufficient fidelity to pose risks for disinformation and abuse; FLUX.1-dev produces clearly realistic harmful images in 30.9% of cases. We further evaluate automated moderation systems and find substantial detection gaps that allow unsafe images to evade filtering. Finally, we assess synthetic image detectors and show that models trained only on benign datasets perform worse on explicit content, while more diverse training data improves detection, highlighting semantic distribution gaps in current approaches. These findings expose limitations in current generation safeguards, moderation systems, and synthetic image detection, highlighting the need for stronger defenses against misuse at scale.

With the rapid advancement of text-to-image (T2I) generation, robust evaluation becomes critical yet challenging, as traditional metrics fail to capture fine-grained alignment and generative artifacts. While large multimodal models (LMMs) are increasingly adopted as evaluators, existing benchmarks typically study semantic understanding, quality perception, and authenticity identification in isolation, while largely neglecting responsibility detection. This leaves a gap in unified and comprehensive validation. To bridge this gap, we introduce SQUARE-Bench, a comprehensive benchmark that systematically evaluates LMM capabilities as evaluators of AI-generated images across four aspects: Semantics, Quality, Authenticity, and Responsibility. SQUARE-Bench introduces a granular taxonomy of 38 sub-dimensions to evaluate nearly 10K AI-generated images sampled from 22 diverse models, ranging from legacy to state-of-the-art generators, complemented by over 3K real-world images. The images are annotated with curated question-answering pairs. Extensive experiments on 23 LMMs reveal that top proprietary models, such as Gemini-3-Pro, already outperform the individual human expert baseline. However, the performance gap between models remains significant, exhibiting notable disparities in fine-grained inference and domain-specific robustness. Beyond benchmarking, we conduct a proof-of-concept study of LMM-guided iterative editing, in which dimension-specific LMMs provide diagnostic feedback to fixed image editors. The resulting guided system yields selective improvements in semantics, authenticity, and responsibility, while exhibiting a consistent visual-quality trade-off. SQUARE-Bench can serve as both a diagnostic tool for characterizing LMM evaluator capabilities and studying their use in T2I generation refinement. The benchmark and dataset will be released upon publication.

Precise instruction following in image generation, such as satisfying object counts and spatial relations, remains an open challenge at least in part because it is learned using unreliable reward models such as object detectors and vision-language models. We introduce Verifiable Visual Rewards (VVR), the first framework for programmatically verifiable image rewards, and show that training on it generalizes to natural prompts. Each VVR task is a scene of geometric objects and relations among them, from which we derive both the prompt and a deterministic verifier, so tasks can be generated in any number and at any chosen complexity. We release VVRBench, with 10,000 tasks over 32 constraint types, and VVRBench-Challenge, with 720 more complex tasks; the strongest model we evaluate---GPT-Image-2.5---solves 21.4% of VVRBench-Challenge. Using VVR scores as rewards for reinforcement learning (RLVVR) raises the accuracy of Stable Diffusion 3.5 Medium on VVRBench from 2.8% to 28.3% and demonstrates consistent easy-to-hard generalization. These gains extend to out-of-domain benchmarks, and mixing VVR into existing objectives further improves overall performance and human preference, motivating the adoption of VVR into standard image generation post-training recipes.

The rising number of concept unlearning techniques for text-to-image (T2I) diffusion models has produced a fragmented evaluation landscape. Methods are assessed under heterogeneous experimental conditions making principled cross-method comparison difficult. We present eval-unlearn, an open-source Python library providing a unified, reproducible benchmarking framework for concept unlearning in T2I Diffusion models. eval-unlearn integrates twelve published unlearning techniques spanning fine-tuning, closed-form model editing, and inference-time intervention, alongside nine complementary evaluation metrics covering erasure efficacy, adversarial robustness, generative quality, and concept retention. Its plugin architecture lets third-party techniques and metrics self-register without modifying the core framework, and its streaming, batched pipeline supports efficient evaluation of both standard NSFW concepts and arbitrary general concepts. As a further contribution, we release a public leaderboard on HuggingFace along with an interactive tool for real-time evaluation of unlearning techniques. The leaderboard compares nudity concept erasure case study across all twelve techniques, exposing significant accuracy-quality trade-offs that are obscured by heterogeneous evaluation. eval-unlearn is released under the MIT license; the package, code, leaderboard, and documentation are all available at https://eval-unlearn.readthedocs.io.

On modern production text-to-image systems, successful policy violations are rare, and previously effective human-written seeds are often patched out. Current automated red-teamers are poorly matched to this regime in two ways: unreliable success measurement and poor exploration. First, we find that judges widely used in prior T2I red-teaming work are unreliable under vague unsafe-content targets: they either miss true violations or reward benign borderline images on hardened APIs. We therefore define strict category-specific success criteria and calibrate strong VLM judges against human labels. Second, we show that broadly used prompt-modification pipelines do not solve the exploration problem: on harder guardrail settings they remain tied to seed prompts, fail to transfer, or cannot bootstrap positive examples. We introduce RISE, which evolves reusable strategies used to generate prompts rather than rewriting them one by one. The best discovered strategies are then reused to generate attacks across new scenarios. On DALL-E 3, Nano Banana 2 (Google) and GPT-Image-2, RISE reaches up to 13% human-verified ASR; under the same calibrated evaluation, prior methods with reported ASR as high as roughly 30% fall to near zero.

Modern text-to-image (T2I) models generate high-quality images from arbitrary user prompts, yet they can just as easily produce not-safe-for-work (NSFW) content. Conventional outer guardrails consist of two components: a prompt classifier that checks for risk before generation, and a post-hoc image classifier that checks the fully generated image. In this design, both classifiers operate outside the generation pipeline and do not use the model's own representations. This separation can limit prompt-screening accuracy, while the image-side check runs only after the full generation cost has been spent. Moreover, a flagged prompt can only be rejected, even when it could be adjusted to produce a safe image. In this work, we propose the Inner Guardrail (InGuard), a safety framework that works inside the pipeline on the model's own representations, leaving base-model parameters untouched. First, a risk classifier grades each prompt as unsafe, risky, or benign based on the text encoder's embeddings, with no external language model. Second, SAGE (Soft-gated Asymmetric Guardrail for Embeddings) modifies the embeddings of risky prompts, aiming to return a safe image instead of a refusal. Third, a latent detector checks the one-step clean latent estimate midway through denoising, reaching nearly image-level performance and halting generation when risk is detected. We also construct the RevGen Safety Benchmark to evaluate T2I safety under realistic conditions: 10,000 prompts built through real-image reverse generation, with a rewriting step that supplies controlled intellectual-property (IP) characters, covering graded porn/gore risks, categorical IP risks, and benign negatives. Across five open-weight T2I models, InGuard reaches 97.9-98.8% safety rate, matching or exceeding the outer guardrail, with 57.5-73.5% less benign disturbance, ~3.7x fewer parameters, and 50-55.6% of denoising steps skipped.

Text-to-image (T2I) models are typically evaluated for bias using slot-based templates such as ``a photo of a [profession]''. Such templates probe only \emph{explicit} demographic attributes (e.g., gender, skin tone) in isolation. They overlook a broader \emph{implicit} bias that arises in natural prompts: when stereotype-relevant attributes are left unspecified, models still default to stereotypical outputs. We introduce IMPLICIT-Bench, a benchmark for measuring implicit bias in T2I models under such prompts. The key design is a structured-knowledge-graph (KG) construction of controlled prompt triplets: neutral, stereotype, and anti-stereotype variants that differ only along a single bias dimension while preserving scene semantics. This enables precise attribution of bias effects that template benchmarks cannot achieve. IMPLICIT-Bench comprises 5,493 prompts across 11 bias categories, validated through multi-model agreement, CLIP-based verification, and human evaluation. Using this benchmark, we show that state-of-the-art T2I models exhibit systematic bias under neutral prompts, a failure mode largely invisible to existing evaluations. We then use IMPLICIT-Bench to evaluate debiasing methods, uncovering a fundamental trade-off between bias reduction and semantic fidelity.

Text-to-image generative models are widely used in professional and creative settings, yet how they represent gender across occupations -- and whether newer models are fairer -- remains poorly understood across multiple generations. We evaluate gender representation across 20 occupations, 5 prompt templates, and 4 Stable Diffusion model generations (SD 1.5, SD 2.1, SDXL, SD 3 Medium), generating 8,000 images with n = 100 per occupation-model cell (5 prompts x 20 images), and classifying all with DeepFace. Across the 8,000 open-source images, 76.4% show male subjects (95% CI [75.1%, 78.7%], p < 2.2 x 10^-16, Benjamini-Hochberg adjusted). More strikingly, 57.6% of images for historically female-coded occupations show male subjects (raw p = 3.43 x 10^-22, BH-adjusted p = 1.71 x 10^-21). All nine significant tests reported in this paper survive BH correction across 10 tests. When compared against U.S. Bureau of Labor Statistics workforce data, models underrepresent women by 20-46pp on average, with particularly large deviations for near gender-balanced occupations: scientist (48% female in BLS, 82-99% male in model outputs) and cleaner (46% female in BLS, 80-92% male in outputs). Model generations do not improve steadily: bias worsens from SD 1.5 to SDXL before partially recovering in SD 3 Medium. A preliminary comparison with GPT-image-1 on five occupations suggests lower bias than open-source models, though the practical effect is small (Cramer's V = 0.080) and the comparison is exploratory. No model achieves gender parity.

Existing evaluations of concept unlearning in text-to-image (T2I) diffusion models primarily rely on attack success rates obtained through automated adversarial prompt search. However, these metrics provide only empirical evidence over a finite set of queries and leave residual leakage over the broader prompt space largely unquantified. This limitation can lead to overestimating unlearning effectiveness and underestimating safety risks. To address this gap, we introduce a novel certification framework for T2I concept unlearning that provides high-confidence guarantees with bounded error on residual concept leakage. Our approach combines statistical certification with worst-case analysis along concept-relevant embedding directions to derive explicit upper bounds on leakage probability under user-specified confidence levels. We evaluate our framework across three major concept categories namely NSFW content, artistic styles, and celebrity identities, and six state-of-the-art unlearning methods. Certified leakage bounds consistently exceed standard attack success rates by 16.2%, uncovering substantial residual risks missed by existing evaluation protocols. Crucially, our results demonstrate that empirical attack-based evaluations can significantly underestimate residual leakage and establish certification as a necessary complement for reliable auditing of concept unlearning in T2I diffusion models.

Commercial text-to-image systems silently revise user prompts before generating images, a step users typically cannot disable or even see. Yet, existing audits of cultural bias examine only the final images and treat generation as a single pipeline, so they cannot tell where the bias originates. We introduce WORLDVIEW, a multilingual benchmark of 8,960 prompts across 15 languages and 31 language-context pairings. Using it, we audit the revision layer in three systems (DALL-E-3, Imagen-4, GPT-Image-1.5) through a three-step analysis of how heavily it marks each cultural context, whether it flattens that context into a narrow vocabulary, and whether that vocabulary is stereotypical. Relative to a no-context English baseline, the US is the least-marked context, while non-Western and non-Anglophone contexts are marked far more heavily, flattened into narrow vocabularies applied across topically diverse prompts, and reduced to recognizable cultural stereotypes. Comparing images from original versus revised prompts on models without a revision layer, we identify the layer itself as a previously undocumented, causal source of this stereotyping. To locate cultural bias, and fix it, we must audit the system as deployed, not the model alone.

Text-to-image (T2I) models have achieved remarkable success at faithfully rendering specified objects and attributes, yet their ability to produce visual metaphors, images that convey abstract ideas by combining elements from two distinct domains, remains largely unexamined. To bridge this gap, we introduce VMetaphor-Bench, the first benchmark for evaluating visual metaphor generation in T2I models. It comprises 1,500 visual metaphors curated from real-world creative imagery, organized into three levels and ten categories, with each sample paired with two prompts of differing specificity. For evaluation, we develop a hybrid framework within an MLLM-as-judge paradigm, combining a multiple-choice question (MCQ) based protocol of 9,594 questions across four levels of metaphorical fidelity with a dimension-based scoring protocol along three perceptual dimensions. Extensive evaluation of 11 representative T2I models reveals that even the strongest proprietary models struggle with compositional structuring and cross-domain mapping, key aspects of metaphorical expression, highlighting visual metaphor generation as an important frontier for future T2I research.

We present an overview of the ImageEval 2026 shared task on culturally grounded Arabic multimodal evaluation. It includes two tasks: (i) AynVQA, covering spoken visual question answering and image-grounded hallucination detection in English and Modern Standard Arabic (MSA), and (ii) CRAI-Bench, evaluating the cultural accuracy of text-to-image generation. A total of 14 teams participated in the test phase, with 12 teams submitting system description papers. Participating systems used a range of approaches, including zero-shot prompting, fine-tuning of vision-language models, speech-recognition pipelines, ensembling, and score calibration. We describe the task setup, datasets, evaluation procedure, and participating systems, and summarize the main results across the different tracks. All datasets and evaluation scripts from the shared task are released to the research community. The shared task highlights the challenges of culturally grounded multimodal evaluation, particularly for Arabic speech and image-text reasoning.

Text-to-image models learn associations between concepts - in the case of this paper, people's professions, which we refer to as roles - and visual attributes. These associations can underpin many observed forms of stereotypical bias. A key open question in this area is whether these associations are stable or change when visual representations of people in professional roles are placed in different prompted contexts. We introduce ContextBias, a controlled evaluation framework, and ContextBench, a benchmark spanning 92 roles and 1,656 semantically controlled prompts, designed to isolate the effect of contextual variation on role-linked visual representations. Evaluating four state-of-the-art models on 66,240 generated images, we find that placing a role in a semantically unrelated context does not suppress role-linked attributes; instead, cross-role attribute concentration increases (pooled BI $+0.047$). Demographic cues, characteristic garments, and role-specific tools remain highly prevalent across context-free, related, and unrelated conditions, and are robust to semantic prompt reformulation. Scene composition and camera framing show the greatest context-sensitivity. These findings reveal a form of stereotypical persistence that remains largely invisible to context-free evaluations, highlighting the need for controlled contextual variation in bias benchmarking. Code and dataset: https://huggingface.co/datasets/shaghayegh/ContextBias , https://github.com/Sina-Emami/ContextBias

Text-to-image (T2I) models are increasingly asked to illustrate literary and cultural content, yet we cannot measure how well an image renders the meaning of a poem. The task is many-sided: a good illustration must be visually sound, faithful to the poem's imagery and scene, culturally and stylistically apt, free of spurious text, and true to its emotion, and its deepest requirements, imagery and especially implicit emotion, are never stated in the words. Existing metrics (CLIPScore, BLIPScore, VQAScore) reward literal text-image correspondence and so cannot tell whether an illustration succeeds, let alone why, or even separate the best model from the worst. We introduce TangPoetryBench, a multi-dimensional benchmark of 1,280 images (320 classical Chinese Tang poems x 4 state-of-the-art T2I models) with quality-controlled human annotations across ten dimensions. Analyzing this data, we reveal the shared and model-specific strengths and weaknesses of current T2I models, including their ability to evoke a poem's implicit emotion. We further introduce PoemAutoEvaluator (PAE), an open, rubric-conditioned evaluator that reaches parity with a strong proprietary judge (Claude), generalizes to an unseen generator and a second poetic tradition (Song Ci), and lets the benchmark scale to new images without fresh human annotation. We release the benchmark, annotations, and evaluator.

Text-to-image (T2I) generation has achieved remarkable progress in recent years. However, existing research has largely focused on English-only settings, leaving cross-lingual performance gaps and language-specific effects insufficiently explored. To fill this gap, we introduce LingT2I, a benchmark covering 10 widely used languages with 33K prompts, designed to evaluate cross-lingual effects in both content generation and text rendering. Building on this benchmark, we conduct a comprehensive cross-lingual analysis, uncovering linguistic inequality and language-dependent trade-offs across evaluation dimensions. Beyond quantitative evaluation, we further reveal a range of language-dependent generation patterns, highlighting how linguistic factors and their corresponding cultural contexts systematically impact model outputs. Our benchmark and analysis provide a foundation for studying cross-lingual behavior in T2I generation and facilitate the development of more robust and inclusive models. Code and dataset are available at https://github.com/RISys-Lab/LingT2I.

Recent advances in visual generative models have enabled high-quality image and video generation, but evaluating these models often demands sampling hundreds or thousands of images or videos, which is computationally expensive. Existing evaluation methods also rely on rigid pipelines that overlook specific user needs and provide numerical results without clear explanations. Mimicking how humans quickly form impressions of a model's capabilities from only a few samples, we propose the Evaluation Agent framework, which employs human-like strategies for efficient, dynamic, multi-round evaluations, offering detailed, user-tailored analyses. Given a natural-language evaluation request, the agent decomposes it into sub-aspects, generates targeted prompts, samples images or videos from the evaluated model, invokes suitable evaluation tools, and iteratively updates its plan from the observed evidence, covering both predefined benchmark dimensions and open-ended user concerns. The framework is thus efficient, promptable, explainable, and scalable across models and tools. Experiments show that Evaluation Agent reduces evaluation time to 10% of traditional methods while delivering comparable results. We further introduce Open Evaluation Agent (Open-EA) by constructing EA-CoT-10K, a corpus of history-conditioned step-level instruction-tuning records derived from multi-round evaluation rollouts, and training EA-3B from Qwen2.5-3B-Instruct as a local planning backbone that preserves the structured reasoning, tool invocation, and summary protocol of the API-based agent while reducing dependence on proprietary backbones. Experiments validate the API-based agent on established T2I/T2V benchmarks and open-ended queries, and evaluate Open-EA on four in-domain and three out-of-domain T2V generator families, showing partial cross-family transfer of the learned policy.

The generation of mathematically precise diagrams from tex- tual prompts has emerged as a critical yet underexplored capability of Large Language Models (LLMs). This has been of interest to researchers in the areas of curriculum preparation, automated ranking of problem sets, and scientific publishing. For LLMs to achieve this, it requires per- fect coordination between Spatial Reasoning, Mathematical Reasoning, and Rendering systems. While existing benchmarks such as MathVision, MathVista are built for Math Reasoning or DiagramGenBenchmark, Mer- maidSeqBench on general purpose diagram generation, no prior work provides a standardized set of prompt, image pairs that can be used to evaluate the LLMs specifically on math diagram generation. This includes fields that span both both text-to-code and text-to-image paradigms. We introduce Math-Vision Diagrams, the first benchmark specifically designed to evaluate LLMs on mathematical diagram generation, and the first to assess text-to-code and text-to-image generation paradigms together in a single unified setting, agnostic of the underlying coding lan- guage or model type. Building on the Math-Vision benchmark, we select a subset of 2920 images out of 3040 from high-quality competition problems with essential visual context. A novel pipeline combining an ensemble of LLMs with Subject Matter Expert (SME) curation is presented, together with a suite of evaluation metrics. Testing several leading models against this benchmark, we demonstrate that LLMs struggle with math diagram generation. All code, data, curation pipeline, and evaluation scripts will be fully open-sourced.

Similes provide a compact and expressive way to describe visual characteristics in text prompts. Recent text-to-image models (t2i models) can produce visually compelling outputs from simile prompts, yet even frontier models frequently misinterpret the metaphorical vehicle and confuse it with the object. These systematic failures reveal a gap between figurative language and object-level visual grounding in t2i models. To investigate this issue, we propose a scalable evaluation framework for simile understanding. Our framework includes (1) a controlled simile dataset in which metaphorical vehicles are drawn from a predefined set of object-detectable categories and combined with diverse templates, (2) automatic grounding metrics based on YOLO (You Only Look Once) detection, and (3) text encoder layer analysis using Diffusion Lens to track how metaphorical vehicles emerge during generation. Experiments across architecturally diverse t2i models reveal consistent literalization failure patterns. We further discuss potential mitigation strategies for improving simile grounding in t2i models.

Text-to-image diffusion models enable personalization of specific visual concepts from a small number of reference images. However, generating a single image that contains multiple personalized subjects, each bound to user-specified attributes such as clothing, accessories, and held objects, remains largely unaddressed. Without explicit spatial constraints, concurrently activated concept checkpoints produce overlapping cross-attention responses, causing per-subject identity degradation and attribute misalignment. Moreover, no established benchmark jointly evaluates these two failure modes in the personalized multi-subject setting. We present MultiCompose, a composition framework that decouples per-concept personalization from multi-subject inference. A semantic preservation regularization maintains attribute binding capacity during fine-tuning, while a two-phase inference procedure automatically establishes subject layout and composes per-concept predictions through spatially exclusive masks. We further introduce MSP-Bench, a benchmark that jointly evaluates identity fidelity (ID), attribute binding accuracy (BIND), and attribute misalignment (MIS) through a dual-pathway protocol. Experiments show that MultiCompose outperforms existing methods on both conventional metrics and MSP-Bench, confirming the benchmark's ability to reveal failure modes that conventional metrics overlook. Code is available at https://github.com/I2-Multimedia-Lab/MultiCompose

Spatial instruction following has become a crucial requirement for text-to-image (T2I) generation. A common challenge arises when directional expressions are interpreted under different frames of reference. For example, ``the left of'' may refer to the viewer's image coordinates or to the intrinsic orientation of an object, leading to different expected layouts. Existing T2I benchmarks reveal important layout failures, yet they rarely isolate whether models can follow a specified frame of reference when it differs from camera view. To mitigate this gap, we introduce FoR-T2I, a benchmark for evaluating this distinction with 1,200 prompt pairs built from controlled spatial layouts. In each pair, the camera-view (Cam) prompt states the target relation in camera view, while the frame-of-reference (FoR) prompt describes the same target placement through an oriented anchor object. Across 22 closed-source and open-source T2I models, mean final accuracy is 41.8% lower on FoR prompts than on matched Cam prompts; even the best-performing model achieves only 44.3% FoR accuracy. This suggests that current models struggle more when the same layout is described through an object's orientation rather than directly in image coordinates. We further analyze this gap by relation type and camera view, compare several training-free prompting and feedback-based mitigation strategies, and propose a VLM-gated rewriting approach that selects rewritten prompts using visual feedback, improving average FoR accuracy from 25.0% to 29.2% under the same generation budget.

Text-to-image (T2I) generation models are increasingly embedded in applications such as media content creation and education, raising concerns about how their outputs may reproduce social biases. Prior work has shown that T2I models exhibit social biases, yet existing evaluations largely focus on a photo generation task. As a result, it remains unclear whether and how such biases manifest in more narrative visual formats, such as storyboards and comics, where characters and events are presented across multiple panels. In this work, we compare bias expression across photo, storyboard, and comic generation in six T2I models by adapting BBG, a text-based bias evaluation framework, to image generation. Our results show that proprietary models generate 25.9% biased outputs in photo generation on average, with biased outputs increasing by 9.6pp in storyboard generation and 18.2pp in comic generation. We also find that photos mainly encode biases through subtle visual cues, while storyboards and comics reveal them more explicitly through event sequencing, character positioning, narrative resolution, and textual elements. These findings show that biases that remain less visible in photo generation may surface in narrative visual formats, highlighting the importance of evaluating T2I systems with diverse visual formats beyond photo generation.

Generative artificial intelligence (AI) has transformed text-to-image synthesis, yet its ability to represent specialized engineering domains remains largely unexplored. As an exmaple in nuclear engineering, general-purpose foundation models frequently generate physically incorrect or conceptually inconsistent images because they lack domain-specific knowledge. This work presents one of the first systematic studies of domain adaptation for nuclear text-to-image generation through fine-tuning of open-source diffusion models. We curate a dataset of 1,000 captioned nuclear energy images spanning reactors, fuel cycles, radiation, and related concepts, and use it to fine-tune three state-of-the-art open-source models: Stable Diffusion XL (SDXL), SD-v3.5-Medium, and the flow-matching Flux.1 model. Their performance is evaluated using both quantitative image-similarity metrics and qualitative expert assessment against the corresponding zero-shot models. Fine-tuning substantially improves the fidelity of SDXL, provides only limited gains for SD-v3.5-Medium, and yields no measurable improvement for Flux.1, demonstrating that adaptation effectiveness depends strongly on the underlying generative architecture rather than model scale alone. We further compare the fine-tuned models against three leading commercial systems--GPT-Image-2, Gemini-3.1-Flash-Image, and Midjourney. Although GPT-Image-2 and Gemini generate convincing images for broad nuclear concepts, they frequently fail on specialized engineering prompts, where the fine-tuned open-source models produce more accurate and technically consistent outputs. These results establish domain-specific fine-tuning as a practical pathway for developing trustworthy generative AI tools for domain-specific applications.

We study empirical scaling properties for text conditioning in visual generation. Such properties have rarely been measured because diffusion loss does not scale with the number of tokens in natural-language prompts. Surprisingly, we find that the converged diffusion loss scales with the amount of structured language in the prompt. To quantify structured language, we adapt two complementary measures: a white-box likelihood metric (GPG) and a black-box attribute metric (ED). Across controlled training runs, the converged diffusion loss decreases approximately linearly with GPG and follows a power law with ED. Guided by these scaling properties, we improve \emph{diffusability} by constructing structured prompts with semantic and geometric annotations derived from images, and improve \emph{promptability} by training a prompter through supervised fine-tuning, cold-start, and verifier-gated on-policy distillation. The resulting system outperforms all evaluated open-weight models on nearly every compositional, reasoning, and world-knowledge benchmark, while matching or surpassing the strongest closed-weight models on most evaluations.

While text-to-image models exhibit remarkable visual fidelity, they frequently violate fundamental physical commonsense. Existing benchmarks often rely on coarse-grained descriptions, failing to diagnose the mastery of specific physical principles. Moreover, the high stochasticity of generative processes causes current prompt optimization methods to suffer from gradient hallucinations, where optimizers are misled by transient visual artifacts rather than systemic flaws. To address these challenges, we introduce OmniPhys, a rigorous benchmark of 1,551 samples grounded in a Physical Knowledge Graph. By aligning PhET simulations with standard curricula, OmniPhys operationalizes a knowledge-to-scenario pipeline that performs diagnostic stress tests via a dual-path verification protocol. We further propose OmniPrompt, an iterative framework that treats physical alignment as a discrete optimization problem. For each query, OmniPrompt aggregates K stochastic images into a per-query feedback buffer. Across training, it further merges feedback from batches of B queries before each meta-policy update, filtering seed and query-local noise. Evaluations across 12 representative text-to-image models reveal universal physical bottlenecks. Results demonstrate that OmniPrompt significantly enhances physical consistency across diverse backbones, proving the transferability and efficacy of our evolved meta-policies. The code and data are available at https://github.com/zjukg/OmniPhys

Concept unlearning is increasingly used to limit the reproduction of protected or unsafe visual concepts in text-to-image models. Existing evaluations, however, mostly study targets that dominate the whole image, such as styles, broad object categories, or portrait-like identities, leaving company logos comparatively underexamined. Logos create a different failure mode: a small localized mark can carry the entire protected concept, must be visually precise to remain recognizable, and can be triggered implicitly by products, storefronts, packaging, or advertisements even when the word ``logo'' is absent. We introduce LU-500, a logo-unlearning benchmark built from Fortune Global 500 companies to study this localized and semantically entangled setting. LU-500 contains nearly 10,000 curated text-query and logo-image pairs, with an explicit track (LUex-500) and an implicit contextual track (LUim-500). To avoid reducing the task to a binary detector score, we define a multi-grained protocol that evaluates both local logo removal and global image preservation in pixel and latent spaces. Experiments on representative inference-time methods, including NP, SLD, and SEGA, and compatible fine-tuning-based methods such as ESD and Forget-Me-Not, show that the evaluated methods struggle to remove logo evidence without changing non-target content. We further analyze ProLU, a prompt-space multi-agent baseline: it improves local erasure by removing logo-inducing semantics, but also illustrates why prompt filtering is not a substitute for weight-level disentanglement. Correlation analyses over logo area, location, and structural complexity suggest that future logo unlearning may need spatially aware controls, such as SSIM-guided constraints, rather than purely global concept suppression.

Recent advances in multimodal generative models have enabled instruction-based image generation to move beyond semantic manipulation to knowledge-driven visual reasoning. However, these methods focus on explicit commonsense reasoning, shallow causal understanding, and direct knowledge recall, failing at knowledge-intensive generation. We develop \textbf{ExpertVerse}, a capability-centric benchmark to evaluate generative models via knowledge-intensive lens. ExpertVerse stratifies reasoning generation across an orthogonal taxonomy of \textit{9 cognitive capabilities} and \textit{8 expert disciplines}, yielding \textit{58 sub-disciplines}. We curate 1,611 expert-annotated instances covering single-image editing, multi-image composition, and text-to-image generation. We further develop an automated workflow to produce \textbf{ExpertVerse-100K}, a large-scale dataset with reasoning traces and knowledge-anchored rationale annotations. Based on this, we train \textbf{KnowThinker} with RL fine-tuning, a VLM reasoning engine with world knowledge that jointly generates thinking processes and refined instructions. Towards the cross-modal credit misalignment and multi-objective gradient conflicts in multi-reward optimization, we propose a tailored Bootstrapped Pareto Policy Optimization (BPPO), which synergizes Bootstrapping Reward Rectification (BRR) and Conflict-Aware Pareto Advantage Fusion (CPAF). Extensive results of both open-source and proprietary models exposes critical reasoning deficits, highlighting imperative for knowledge-intensive benchmarks towards next-generation visual generation.