Papers for
digital artists
Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.
Sonic Palette predicts changing color themes that match music
Sonic Palette: Predicting Dynamic Color Themes from Music
Abstract: We present Sonic Palette, a music-driven framework for predicting time-varying color themes from audio. Rather than treating music-to-palette generation as a static problem, our method formulates music--color correspondence as a cross-modal sequence prediction task that models how palette-level visual attributes evolve over time in response to music. Specifically, Sonic Palette uses a music-conditioned autoregressive Transformer to predict frame-wise color themes, each represented by five dominant colors, from input audio features. To support this task, we curate a dataset of paired audio--color sequences derived from 265 full-length official music videos. We further visualize the predicted color themes through a palette-guided recoloring process that preserves image structure while revealing temporally varying color appearance associated with the music. Quantitative results show that Sonic Palette predicts color themes that more closely match the ground truth, while subjective results indicate more natural temporal color transitions and stronger perceived music--color atmosphere alignment, highlighting its potential for music-driven visual design, computational art, and creative visual authoring.
Artwork protection improves by predicting best personalized style defense
How Well Is My Artwork Protected? Predicting and Tailoring Protection against Style Mimicry by Personalization
Abstract: Protection tools add an imperceptible perturbation to each artwork so that a model personalized on it fails to imitate its style, and they apply one recipe, a protection method at a fixed strength, to every artwork. We find that the same recipe protects artworks very differently, well beyond the noise of personalization seeds, and that cheap signals predict this protection before any personalization. Because protection rises and falls together across recipes, our method, Patina, predicts the protection of every recipe from one short trial protection and gives each artwork the weakest recipe whose predicted protection reaches a chosen level. At the same level of visibility, Patina lets more artworks pass the protection threshold than any single recipe and warns the artist about artworks for which no recipe is predicted to pass it.
Palmprint decomposer separates and edits texture from base appearance
Palmprint Decomposer: Interpretable and Editable Factorization via Synthetic Learning and Instance-Wise Refinement
Abstract: Palmprint recognition and synthesis methods focus on extracting discriminative textures or generating images with varied textures and appearances. However, they do not generally provide an explicit image-level representation that separates palmprint texture from its underlying base appearance for independent analysis or controlled editing. We introduce Palmprint Decomposer, an interpretable framework that represents a palmprint through independently editable factors and reconstructs the image through a multiplicative composition model. A color map and a light map characterize the base appearance, while a structure map and a global texture strength parameter describe texture modulation. However, accurate reconstruction alone does not guarantee separation of palmprint texture from base appearance, as fine palmprint textures may leak into the estimated base appearance. To mitigate this ambiguity, we train the decomposer exclusively on synthetic data with direct factor supervision, using asymmetric decoding paths and decomposition constraints to suppress texture leakage. Instance-Wise Refinement further improves real-image reconstruction by directly optimizing the predicted factors for each input without relying on the trained network. Experiments across seven datasets demonstrate high reconstruction fidelity, with the extracted structure maps generally achieving verification performance comparable to the original images. Compared with existing methods, our approach achieves better factor separation while preserving more discriminative palmprint texture information.
StyleJudge rates artistic style transfer more like human judges
StyleJudge: A Human-Validated, In-Context-Learning Vision-Language Evaluator for Artistic Style Transfer
Abstract: Automatic evaluation of artistic style transfer remains an open problem: existing metrics score an image pair in isolation, without seeing an example of the intended style transformation, and correlate poorly with human judgment. We introduce StyleJudge, a compact vision-language evaluator conditioned on a small set of reference source-to-stylized pairs before scoring a query pair, mirroring how a human rater calibrates to a style before judging a candidate. On a human-annotated benchmark of 878 rated pairs across 12 artistic styles (728 from 10 training/validation styles, 150 from 2 unseen styles), our efficient 0.8B-parameter StyleJudge reaches a Pearson correlation of 0.291 (Spearman 0.325) with human ratings on seen styles and 0.381 on unseen ones. On seen styles, it achieves the highest positive correlation among tested metrics: Gram-matrix style loss and CLIP similarity correlate weakly ($r=0.041$, $r=0.168$), while LPIPS (scored higher when closer to the source) correlates negatively ($r=-0.404$). We achieve this by distilling evaluation knowledge from a 72B-parameter vision-language teacher used only during training, which reaches $r=0.327$, confirming that most of its human alignment survives compact distillation. For training, we build a dataset of source-to-stylized pairs across the 12 styles via LoRA-adapted diffusion, densified with graded intermediate examples from a high-resolution image-morphing pipeline so the evaluator recognizes partial and complete stylization. On two held-out validation styles, StyleJudge reaches 28.2% exact-match agreement with its teacher's structured scores versus 1.1% for the untuned base model, with 67.8% shorter reasoning traces, and scores a pair in 39 s (median) using 2.5 GB of GPU memory on one NVIDIA T4. We release the human-rating benchmark, annotation guideline, SDXL-adapted FreeMorph code, and model weights.
SearchChord improves one-step image editing with smarter prompt selection
SearchChord: Prompt Preselection and Field Recomposition for One-Step Image Editing
Abstract: Finding effective prompts and seeds for one-step image editors requires balancing edit fidelity, source preservation, and computational cost. To address this challenge, we explore a large collection of candidate edits, where each candidate is defined by a unique prompt-seed pair, and generate corresponding images on demand. We present SearchChord, a training-free framework that leverages a large pool of such candidates, combining text-based preselection, image verification, and latent-field recomposition. Our ablation studies across pool sizes up to 200 candidates show that a pool of 100 offers a cost-effective operating point. Compared with feeding all 100 candidates into recomposition, TextSim preselects a subset of 10 candidates. Rather than uniform averaging, we incorporate image-verifier scores to weight each candidate during recomposition. Experiments on PIE-Bench and the proposed CropWeed-EditBench reveal a trade-off: candidate selection improves target-text alignment, while recomposition better preserves unmodified source content. The oracle verifier achieves the best performance in both preservation and target-text alignment. Practical verification partially recovers semantic alignment, but recomposition still compromises edit fidelity, including in agricultural image edits. These results motivate text-first preselection and stronger verification to balance preservation, fidelity, and cost. Code and data will be made publicly available.
Activating language model to steer narrative flow through typhoon storm
Activation Steering the Nan-Shan in Typhoon
Abstract: Typhoon is an audiovisual installation based on Joseph Conrad's novella, in which Captain MacWhirr steers the steamer Nan-Shan directly into and through a catastrophic storm. The novella is a study of what happens when the scale of a phenomenon exceeds the practical and conceptual frameworks available to comprehend it and of the paralysis that sometimes follows a demand for action in such overwhelming circumstances. We chose the text of Typhoon to reflect on human culture's current AI moment. We prompt a large language model, seeded with Conrad's original language, to feed endlessly on its own output, and explore when and how the text becomes increasingly alien and unwieldy as time progresses, including deviations from the narrative, digressions into the model's own instructions and thinking, and long periods of incoherent rumination. We employ methods from activation steering, including a novel adaptive steering method we introduce, to control the rhythm of the narrative and the model's digressions over long stretches of generation. The simultaneous efficacy and unpredictability of this steering showcases the tension between the perceived interpretability of AI, and the reality of a system that remains outside our comprehension and control.
Small data ai captures unique sounds of persian calligraphy
Small Data Generative AI for Culturally Specific Artistic Creation: A Case Study on the Sonic Space of sarir
Abstract: Large-scale generative AI (GenAI) models have become increasingly integrated into contemporary creative practice, yet they often reproduce cultural biases and fail to meaningfully engage with non-Western artistic traditions. In response, this paper explores a small-data approach that foregrounds artist-curated and culturally informed dataset creation and model training. Through a case study on sarir (the distinctive sound produced by the reed pen in Persian calligraphy), we demonstrate how small-data GenAI can operate within a highly situated cultural context that lies beyond the representational reach of large-scale GenAI models. We construct a bespoke sarir audio dataset and train two models, RAVE and StyleGAN2, adapting each to the sonic domain through audio synthesis and spectrogram generation. The resulting models learn the fine-grained timbral and gestural nuances of sarir, enabling both real-time interaction and extended generative output. By comparing these results with state-of-the-art text-to-audio models, we clearly demonstrate the disparity in their performance and highlight the expressive possibilities unlocked through the small data approach. This focused case study demonstrates the feasibility of small-data GenAI for culturally specific artistic creation and underscores the value of further investigations that extend this approach to other cultural materials and artistic domains.
Stable diffusion adapter improves historical art style image generation
The RenAIssance: Caption-Guided Diffusion Models for Historical-Art Visual Media
Abstract: Generative AI can expand cultural collections into prompt-responsive visual media, but historical artworks rarely provide the paired descriptions needed to adapt modern image generators. We present The RenAIssance, a scalable pipeline that turns a collection of historical European artworks into a reusable text-to-image media resource. The pipeline generates scene-level captions with BLIP and uses the resulting approximately 15,000 image--text pairs from DEArt to train a compact LoRA adapter for Stable Diffusion v1.5. The adapter shifts generated images toward the historical-art distribution while retaining the base model's ability to render novel concepts. On historical and contemporary prompts of different lengths, it improves FID to the DEArt reference distribution in every setting with only a modest decrease in CLIP text--image similarity. Qualitative results show that the same adapter can render both period-appropriate subjects and contemporary concepts in a coherent historical visual language. By decoupling a reusable style representation from the base generator, the approach offers a practical building block for controllable historical-art media creation, interactive authoring, and rich-media experiences.
Physics guided model improves realistic object insertion in images
A Bridge from Paste to Place: Physics-Guided One-Step Image Composition via Object-Scene Interaction
Abstract: Realistic image composition must make a pasted object appear naturally present in a scene while preserving the fine details of both foreground and background. Reference-based insertion methods can change object pose and appearance, while foreground harmonization methods and shadow-specific synthesis methods each address only part of this task. An efficient, unified solution to this task remains an open challenge. We introduce Paste2Place, an end-to-end, physics-guided flow-based model that learns a direct, one-step latent bridge from pasted inputs to realistic composites, guided by explicit albedo-shading-residual decomposition and recomposition within the model. To support model training and evaluation, we develop a Blender rendering and validation pipeline to generate paired composites with physical annotations, and construct real-scene pairs from open-source object-removal data. This effort yields 86,273 training pairs and a 1,500-example benchmark. Extensive qualitative and quantitative experiments demonstrate that Paste2Place achieves substantial advantages in image composition quality and inference speed. Overall, our work provides a clear task definition and an effective solution for image composition, and fills a gap in large-scale, high-quality datasets and benchmarks for training and evaluating image composition.
Portrait studio replays drawings to keep the same image
The Drawing You Watch Is the Portrait You Keep: A Replayable Machine Portrait Studio
Abstract: Ask an image model for your portrait and a finished picture arrives: no first line, no second thoughts, no record of how it got there, and a different picture if you ask again. I built a portrait studio that works the other way. A sitter chooses one of eight fictional artists, each written with a city, a medium and a tempo of its own, holds still for 8 to 12 seconds, and watches a drawing of themselves appear over 44 seconds. One still is sent after consent, a hosted image model returns a private study the sitter never sees, and a compiler turns that study into one drawing document. The live drawing, the saved sheet, the vector export and the film all read that document, and a replay makes no model call, so the drawing you watch is the portrait you keep. I describe the compiler in enough detail to rebuild it and say plainly what it is: an authored reconstruction at a compressed speed, not a recorded hand. On 16 generated test studies a sheet holds 8,784 to 16,378 timed contacts, about three quarters of them fixed-grid fills and nearly all shorter than one video frame, and recompiling one study gave byte-identical output four times on one machine. The paper also traces a bug that matters more than any of that. The earlier compiler estimated the paper colour tile by tile, read dark skin as paper, and in all eight hands kept less of a deep-complexioned face than a fair one (13 to 48 percent against 41 to 56). On 80 generated studies the rebuilt engine keeps the complexion difference the study already has (raw retention 89 to 120 percent), so the fairness question has moved upstream, to the study and the hosted model. The two test sitters are generated and differ in more than complexion, and no real-face or perceptual study exists yet. The studio is live at https://everyfaceproject.com.
Diffusion transformers produce clearer high resolution images with new attention and guidance
Restoring Semantic Fidelity for Training-Free High-Resolution Image Generation in Diffusion Transformers
Abstract: Diffusion Transformer (DiT)-based text-to-image models have recently achieved remarkable success in image synthesis. However, when directly applied beyond their training resolution, these models often suffer from severe semantic degradation, where meaningful semantic content disappears. Although existing training-free high-resolution generation methods can mitigate this issue, the inherent semantic degradation at high resolutions remains largely unresolved, leading to degraded fine-grained details. Furthermore, widely used structural guidance methods lack modeling of the structure and details in the intermediate trajectory, which degrades the quality of the generated results. In this paper, we propose a training-free framework for high-resolution image generation to address these challenges. First, we propose a text-visual scale-decoupled attention (TVSDA) module, which restores the model's ability to generate semantically meaningful content at high resolutions by preserving the global receptive field of text tokens while aligning the receptive field of image tokens with the training resolution. Second, we propose a structure-detail guidance (SDG) strategy that explicitly models structural information and fine details through scale-wise and temporal-wise guidance, overcoming the limitations of conventional low-resolution guidance. Extensive experiments demonstrate that our method significantly improves both structural coherence and detail fidelity over existing training-free DiT-based high-resolution generation approaches. The code is available at https://github.com/ljjcoder/Restoring-Semantic-Fidelity.
Computational aesthetics explains how ai measures and creates art
Special and General Computational Aesthetics
Abstract: Computational aesthetics is a field at the intersection of computer science, artificial intelligence, aesthetics, and other disciplines. As AI has developed, the field has formed relations of inclusion, intersection, or support with computational art, AI art, AI aesthetics, AI-generated content (AIGC), computational creativity, affective computing, and neuroaesthetics. Without distinguishing scope, objectives, and methods, it may be narrowed to image aesthetic quality assessment or expanded into an umbrella term for AI's involvement in art. We analyze its internal structure and its relations with neighboring concepts, and propose a two-level scope: special computational aesthetics (SCA) and general computational aesthetics (GCA). SCA centers on aesthetic measurement and aesthetic process modeling. The former primarily corresponds to "Aesthetic Perception": computationally identifying and representing aesthetic attributes and predicting human aesthetic evaluations; the latter primarily to "Aesthetic Understanding": computationally describing, testing, and explaining how human aesthetic perception and judgment are formed. GCA extends this core to include "Aesthetic Generation," namely artistic generation guided by computational aesthetic models. Some computational aesthetic tasks can also use non-AI methods. Research in this scope using AI algorithms and models we define as AI aesthetics, which may involve the special core and the general extension. "Aesthetic Generation" intersects with AIGC, AI art, and computational creativity, but belongs to the general extension defined here only when computational aesthetic models substantively constrain, guide, or optimize artwork generation. We also draw on Feng Peng's discussion of the computability of beauty, aesthetic experience, and art as a theoretical reference for clarifying boundaries between computational aesthetics and related concepts.
Orthogonal drift correction improves text to image prompt matching
ODC: Orthogonal Drift Correction for Improved Text-to-Image Semantic Alignment at Inference
Abstract: Text-to-image models have achieved remarkable success in generating high-quality images from textual descriptions. However, they often struggle with "semantic drift," where the generated output fails to precisely align with complex or nuanced text prompts. While recent approaches have attempted to address semantic errors regarding attribute binding or object presence, there remains a gap for a more holistic method that addresses these issues by directly refining the text embeddings of the initial user prompt. In this work, we introduce Orthogonal Drift Correction (ODC), an inference-time guidance method designed to mitigate semantic drift without requiring model retraining or additional user inputs. ODC guides image generation through a two-stage process. In the first stage, it identifies the semantic drift by evaluating the initially generated image against the user prompt in a shared vision-language embedding space. It then isolates the component of this drift vector that is orthogonal to the prompt's direction and translates it back into text via a vocabulary-based surrogate mechanism. In the second stage, it produces refined text conditioning for a second generation pass by feeding both the initial text embedding and the re-embedded drift representation into an adaptive rank-reduced concept removal module. Our experiments demonstrate that ODC consistently improves prompt-image alignment, increasing CLIP scores by up to 5.4% over the baseline on the COALBench-300 and PartiPrompts benchmarks. Furthermore, on the T2I-CompBench complex subset, ODC improves the average 3-in-1 score by 4.5% over the competing methods. As a plug-and-play module, ODC offers a practical and efficient method for improving the reliability of text-to-image models. Code is available at https://github.com/kasrakamali/ODC.
Material rebinding method transfers surface look while keeping shape intact
RATR: Training-Free Material Rebinding via Role Assignment and Temporal Routing
Abstract: Material rebinding aims to transfer the material appearance from a reference image while preserving the target object's geometry and identity. Existing methods typically struggle to balance material fidelity with structural preservation due to the coupled influence of structural and appearance cues in their visual conditions. We identify role entanglement in the target and reference conditions as a contributing factor the target condition carries both geometry and its original appearance while the reference condition contains material cues alongside object-specific structure. To address this issue, we propose RATR, a training-free material rebinding method built on a diffusion-based image editor that assigns complementary roles to the two conditions and coordinates their influence during denoising. To make the target condition primarily convey structure, we introduce an albedo-resolved surface release mechanism, which suppresses the target's original surface appearance while retaining geometric cues, yielding a structure-oriented condition for material transfer. On the reference side, the designed material evidence isolation mechanism emphasizes material cues while reducing interference from object-specific structure, yielding a complementary material-oriented condition.
SketchBloom expands sparse sketches into detailed editable vector art
SketchBloom: Training-Free Vector Sketch Outpainting with Stroke-Level Style Control
Abstract: Outpainting sparse sketches while preserving contour coherence and stroke style remains challenging. We present SketchBloom, a training-free framework that combines pretrained raster outpainting and style-transfer guidance with per-instance vector optimization. Given a sketch, a scene prompt, and an optional reference style, it produces an editable Scalable Vector Graphic (SVG) composed of Bezier strokes. Adaptive latent blending balances content contours and reference texture without model retraining. A reference-derived stroke vocabulary initializes contour- and DINO-attention-guided strokes, which are optimized separately for structure and texture before contour-emphasizing multiply fusion. As in prior optimization-based vector sketching, no task-specific network is trained; our contribution is the synthesis design specialized to sketch outpainting. On LineArtOut-1K, comprising 1,024 input and style combinations, SketchBloom improves perceptual, semantic, and structural fidelity over the evaluated vector baselines when all methods vectorize the same outpainted raster. This protocol evaluates vector synthesis rather than end-to-end outpainting or reference-style superiority. Runtime is approximately six minutes per pair on a single NVIDIA H200 GPU. Project page: https://khangcntn123.github.io/SketchBloom/
People prefer AI art more when they think a human made it
Beauty Is Human: When People Love AI-Generated Art, They Think a Human Made It
Abstract: Generative AI now produces images and poems that people cannot reliably distinguish from human-made work, so people often judge for themselves who made a work. We examine how these perceived-authorship judgments relate to aesthetic preference. In a public online AI Art Turing Test, 11,123 people judged whether each of 50 pictures (26 AI-generated) was made by a human and were asked for their favourite. Among the 9,152 respondents who judged their favourite, a picture was 22.1 percentage points more likely to be judged human-made when it was the respondent's favourite, holding respondent and picture fixed. The association was similar for AI-generated and human-made favourites, was positive for all 50 pictures, and appeared under every reported detection strategy. Respondents most negative about AI art chose fewer AI-generated favourites (47% against 60% among the most positive) but more often believed them human-made, partly because others also judged those pictures human. As a result, in every opinion group a third to two fifths of respondents named an AI-generated favourite they believed human-made. A reanalysis of a published experiment on AI-generated poetry, in which 230 people rated each poem before judging its authorship, found the same pattern, although the AI poems were rated higher. When provenance is hidden, liking and perceived human authorship travel together, consistent with aesthetic response serving as evidence of a human maker and with beliefs about the maker shaping enjoyment. The findings qualify research on bias against AI art, which typically uses explicit labels, and inform AI disclosure policy.
Translating poem emotions into moving math-based images
Translating Poetic Emotion into Dynamic Mathematical Visuals: A Strange Attractor-Based Approach
Abstract: Poetry conveys emotional experiences through language. This project investigates how poetic emotional experiences can be represented through dynamic mathematical visualisations while further developing a pipeline for this purpose. By leveraging a pretrained RoBERTa-based emotion classifier, the system analyses the fine-grained emotional states within a poem. These detected emotions are then mapped onto the parameters of strange attractors, complex structures from dynamical systems theory, to generate abstract, deterministic, and dynamic imagery. This work situates itself at the intersection of poetry, psychology, and mathematics, aiming to extend the poetic experience beyond language into the sensory domain
Method improves emotional image generation by preserving image content
Semantic-First MixGRPO: Reliable Emotional Image Generation via Temporal Decoupling
Abstract: Controllable image synthesis should modify visual affect without replacing the objects, layout, or relations specified by a prompt. Existing methods address this tension through conditioning architectures or auxiliary losses, while mixed ordinary differential equation (ODE) and stochastic differential equation (SDE) sampling has mainly been used to accelerate group relative policy optimization (GRPO). We instead study stochastic-window position as an attribute-control variable for flow-based image generation. Using FLUX.1-dev with EmotiCrafter-style valence-arousal conditioning, we compare fixed early, middle, and late four-transition SDE windows, progressive MixGRPO, and full-path Flow-GRPO under matched settings. Because step 0 has the highest noise, our semantic-first schedule uses deterministic ODE sampling at steps 0-19 to establish content, then confines stochastic exploration and policy updates to steps 20-23. Across three seeds, it achieves a CLIPScore of $29.662\pm0.276$, cross-affect DINO consistency of $80.1\pm0.9$, and semantic drift of 2.9%, while reducing training cost by 33.5% relative to full-path Flow-GRPO. Full-path stochastic training remains more accurate on valence-arousal targets, revealing a genuine trade-off. Semantic-first nevertheless improves both affect and semantic metrics over progressive scheduling, preserves the principal subject in 95.98% of images at five extreme or neutral targets, and receives the highest semantic-preservation and overall-preference ratings in a 30-participant study. These results identify probability-flow time as a practical graphics control dimension for reliable affective appearance manipulation.
Training-free method improves text-to-image matching with multiple objects and attributes
TIE: Training-free CLIP Embedding Guidance for Compositional Text-to-Image Alignment
Abstract: Text-to-image (T2I) diffusion models have advanced notably, but still fail to satisfy prompt conditions, resulting in attribute mismatches and missing objects. These errors normally fall into two categories: concept loss, when an object or attribute (i.e., concept) goes missing, and concept confusion, when an attribute is assigned to the wrong object or multiple objects blend together. Recent studies suggest that these challenges are caused by the limited capacity of CLIP text encoder to capture fine-grained semantic details. Although several methods have been proposed, concept loss and concept confusion persist in recent T2I models when handling multi-object, multi-attribute prompts. In this paper, we conduct an embedding-level analysis to develop a training-free, inference-time solution for concept loss and concept confusion across CLIP-based T2I models. We find that (1) concepts mentioned later exhibit higher embedding entropy, reflecting less concentrated representations that are more often associated with concept loss, and (2) the first CLIP attention layer captures the strength of binding between each object and its attribute. Guided by our findings, we introduce TIE, a method that improves semantic alignment through a single text-embedding update. TIE addresses concept loss via entropy-aware singular value amplification and resolves concept confusion through interpolation-extrapolation binding based on CLIP attention scores, all in a training-free manner. Extensive experiments demonstrate that TIE enhances semantic fidelity in multi-concept scenarios with minimal sampling overhead. The project page is available at https://hong-sujung.github.io/TIE/.
AdvFidelity unifies preference alignment and fast image generation in reinforcement learning
AdvFidelity: Unifying Preference Alignment and Few-Step Image Generation within Reinforcement Learning
Abstract: Practical image generation requires both human preference alignment and few-step efficiency, yet combining reinforcement learning (RL) with distillation is often multi-stage and may erode RL gains We observe that few-step RL progressively improves structural coherence, even with specialized rewards, but leaves low-level artifacts that these rewards may fail to penalize. To address this gap, we propose AdvFidelity, which integrates artifact-sensitive fidelity supervision into RL through an online adversarial reward. This enables joint reward alignment and high-fidelity few-step generation within a single RL stage, without distribution matching distillation (DMD) or other explicit distillation objectives. We train a discriminator to rank high-quality references (positives) above content-matched reconstructions (negatives) produced by the current generator. Reconstructing moderately noised references largely preserves style and scene layout while exposing low-level degradations. This encourages the discriminator to assess artifacts rather than content differences. With negatives reconstructed online, alternating updates adapt fidelity supervision to the generator's evolving failure modes. References can come from existing target-domain data or full-step model samples. Built on LeapAlign, AdvFidelity backpropagates gradients from both rewards through the few-step sampling trajectories used at inference. Across two model backbones and three task settings, AdvFidelity matches full-step LeapAlign in alignment, task performance, and overall generation quality and remains highly competitive with other evaluated full-step RL methods, using only 4 or 8 steps without CFG.
Painting change map enables precise control of digital painting videos
Painting Change Map as guidance for generating painting processes
Abstract: Digital art generation has undergone a massive paradigm shift, moving from static image synthesis to dynamic video generation that can mimic the human painting process. While existing models can synthesize visually stunning time-lapses of paintings being created or "unpainted," they largely treat the creative process as a black box. Current conditioning mechanisms are either too rigid, relying on static geometric cues like Canny edges or depth maps, or too holistic, utilizing simple scalar progress variables that offer no localized control. Consequently, users lack the agency to steer how a painting evolves over time. In this work, we argue that true control over the video generation of artwork requires a joint understanding of two fundamental dimensions: where an artist acts, and when those actions take place. To achieve this, we introduce the Painting Change Map, a novel spatio-temporal control mechanism that explicitly tracks normalized structural changes across a 1,000-timestep continuum, a resolution sufficient to capture fine-grained stroke-level changes while remaining computationally tractable. By mapping localized visual differences into an encoded RGB space, our representation enables fine-grained guidance for both the forward painting and reverse unpainting processes. Extensive benchmarking demonstrates the efficacy of our approach. We outperform existing control baselines and achieve competitive or superior results compared to state-of-the-art painting methods. Furthermore, under oracle conditions, our method surpasses all baselines by a significant margin. Code is available at https://github.com/Markus-Pobitzer/painting-change-map.
Reflection guided method improves text to image generation accuracy
Reflection-Guided Dynamics Rectification for Text-to-Image Generation
Abstract: Fine-grained rectification of existing generations under a limited additional budget remains a key problem in test-time optimization (TTO) for image generation. As for prior approaches, they could identify residual errors, but could not directly ensure that the model acts on the feedback during reasoning. Such errors stem from multiple sources, such as the initial noise or text prompt, and ultimately induce an execution gap of failing to handle potential deviations along the trajectory generating. However, classic models generally cannot remedy this gap. To narrow it, we propose Reflection-Guided Dynamics Rectification (RGDR), which turns reflections on completed outputs into corrective interventions on the process of sampling dynamics at the trajectory level. Specifically, RGDR could impact every sampling step by adapting to instantaneous intervention. Moreover, RGDR generates flexible candidates while adjudicating between them and the reference. As experiments show, rectification from RGDR starts from the existing base trajectory and reflection, and RGDR is substantially more effective than former trajectory exploration. Under matched budgets for additional image generation, RGDR's gain in the cross-model average final checklist score over the reference is $1.51\times$ that of TIR prompt refinement and $1.81\times$ that of Dynamic CFG.
Interpretable method improves emotional editing of complex images
IECLA: Interpretable Emotion Contribution Learning for Affective Image Editing
Abstract: Affective image editing (AIE) aims to evoke a target emotion while preserving the content and structure of a source image. Existing methods improve emotional expression or visual fidelity, but the target emotion alone does not reveal which source regions should be changed and which should remain intact, especially in complex scenes. We introduce Interpretable Emotion Contribution Learning for Affective Image Editing (IECLA), a framework that separates source-emotion attribution from target-aware editing. IECLA constructs signed object-level supervision through counterfactual interventions and trains a context-conditioned contribution predictor to localize evidence that supports or opposes the source emotion. At inference, an image-level evaluator estimates the source emotion directly from the input, while the predictor identifies editable and preservation evidence without repeated interventions. A target-aware editing agent then translates this evidence and the desired emotion into localized, content-aware operations for existing editors. Extensive evaluations show that IECLA predicts counterfactual contributions more faithfully on both in-domain and cross-dataset tests, while external VLM and independent human references support the quality of its localized evidence. Across six editing backbones, IECLA consistently strengthens target-emotion expression while preserving image content and structure, and user studies further show improved perceived target expression and naturalness.
Kingfisher speeds personalized image generation by splitting style and content
Kingfisher: Fast Personalized Visual Autoregressive Generation via Scale-Aware Prompt-Conditioned Scale Decomposition
Abstract: Personalized image generation has been extensively studied in diffusion models, often relying on subject-specific optimization of model weights, textual embeddings, LoRA modules, or adapters. In this work, we explore a different direction for fast personalization in visual autoregressive models. Our key observation is that a short prefix of early autoregressive scale codes is sufficient to strongly determine both object structure and global appearance, while later scales primarily refine the established generation trajectory. Based on this insight, we introduce Kingfisher, a model-tuning-free framework that decomposes early residual scale codes into content- and style-related components through prompt-conditioned scale-code subspaces. Given two real images, Kingfisher first decomposes their early scale codes, then recomposes the content components of one image with the style components of the other into a compact semantic prefix. The frozen generator subsequently predicts the remaining scales through bitwise self-correction for coherent refinement. Experiments on CSD-100 show that Kingfisher achieves strong content preservation and the highest style and text alignment among the evaluated methods, while reducing pair-specific preparation time by approximately 54x compared with diffusion-based methods and 7.5x compared with VAR-based alternatives. These results demonstrate that effective personalization can be achieved by directly manipulating the native scale-space representation of a frozen visual autoregressive generator.
UltraDiff improves high resolution image generation efficiency and quality
UltraDiff: Transferring High-Fidelity Priors to Compressed Latent Spaces for High-Resolution Image Generation
Abstract: High-resolution synthesis with Latent Diffusion Models (LDMs) faces a fundamental trade-off between computational cost and generative fidelity. This trade off is largely governed by the latent compression factor f (e.g. f8 denotes f=8 and f32 f=32). While aggressive compression (f32) significantly improves efficiency, it suffers from severe information loss and ambiguity compared to standard f8 models. We propose UltraDiff, a framework that reformulates this challenge as joint latent diffusion learning followed by marginal score distillation. We introduce MixTeacher, a dual branch DiT that models the joint f8-f32 distribution, utilizing shared attention to resolve the ambiguity of the compressed space with high fidelity f8 priors. Crucially, we propose vector field distillation in the native f32 space. Theoretically, this compels the student to learn the conditional expectation of the teacher trajectory, effectively filtering out compression artifacts. Across the evaluated 1K to 4K settings, UltraDiff approaches f8 level quality while preserving f32 efficiency. With 20 sampling steps on a single A100 GPU, it generates a 2K image in 6.2 seconds over 40 times faster than our f8 baseline.
Framework improves continuous emotion control in foundation image editors
Barycentric Guidance: Turning Foundation Image Editors into Continuous Affective Controllers
Abstract: Emotions are expressed on a continuum and are naturally described in the valence-arousal (VA) space. Existing VA-based image editors are typically training-based and domain-specific, limiting them to VA regions seen during training and making them brittle across datasets and domains. Meanwhile, despite producing high-quality edits, state-of-the-art foundation image editors are not continuous affective controllers: non-linear emotion representations in text encoders makes prompt interpolation poorly calibrated, so accurate and continuous VA control remains unreliable. To fill this gap, we introduce Barycentric Guidance, a training-free framework that turns pretrained foundation image editors into continuous affective controllers over VA, requiring no finetuning, extra data, or model changes. Our method maps any target VA point to simplex-based guidance weights, enabling VA controllability in three aspects: (i) accurate targeting of VA states, (ii) broad coverage across the VA plane, and (iii) continuous control. Across three face datasets, we improve VA target accuracy by 25-29%, expand VA-plane coverage by 28-50%, and increase expression diversity by 29-49%, over the strongest baseline. Unlike prior domain-specific methods, our training-free approach exploits the foundation model's inherent versatility, enabling generalization beyond human faces to animals, artworks, and complex scenes within a single framework. Code is available at https://github.com/harveymannering/BarycentricGuidance.
Foresee shows what actions enable with clear visual previews
Foresee: Making Procedural Futures Tangible through Generative Previews
Abstract: Procedural guidance can show users how to act without explaining what an action enables later. We present Foresee, an interface combining next-step guidance with consequence previews, method comparisons, and cross-step access. A hybrid pipeline combines structured rendering, image editing, and video generation. A literature-informed framework and six-participant formative study shaped its design. A 24-participant study compared AR guidance, AR with generated video, and Foresee across digital painting, gameplay, and cocktail making. Exploratory painting comparisons showed higher correct completion without a recorded error than AR and higher post-task quiz accuracy than generated-video guidance under task-wise correction. Interviews revealed that users could overlook valued explanations, match visible outcomes without understanding later possibilities, or wait for concrete demonstrations when symbolic cues were unclear. These findings inform generative previews that explain what actions enable or constrain while supporting ongoing execution.
Controllable sampling method boosts variety in AI generated images
Controllable Diverse Sampling through Pullback Directions
Abstract: Conditional diffusion models can generate high-quality images that align closely with a given prompt. However, samples generated from different random seeds may remain visually similar, limiting creative exploration. Existing approaches can increase variation, but often require additional optimization or sampling overhead, while stronger perturbations may introduce distortions that degrade image quality or prompt alignment. We propose a training-free method that leverages the local pullback geometry induced by the mapping from the conditioning-embedding space to the image space to identify directions of maximal output sensitivity. By steering different sampling trajectories along these directions, we encourage distinct generations while maintaining consistency with the conditioning signal. Experiments on MS-COCO and BrushNet show the efficacy of the method in improving diversity on prompt-conditioned image generation and inpainting.
Transformer model learns flexible score functions from few examples
Transformer-based In-Context Score Operator Learning for Diffusion Models
Abstract: Diffusion models typically learn the generative dynamics of a single target distribution or a family of distributions indexed by conditioning variables fixed during training. This limits their ability to adapt to a previously unseen distribution from only a small set of examples. We introduce an in-context solution operator learning framework for diffusion models, in which each target distribution is treated as a task drawn from a meta-distribution and is specified at inference time by an empirical context set. Our method learns an in-context score operator that maps the context samples, a noisy query point, and the diffusion time to the task-dependent score, enabling reverse-diffusion sampling on unseen tasks without retraining or parameter updates. A key observation is that the task-dependent score admits a Gaussian-kernel conditional-mean representation. Its empirical Nadaraya--Watson approximation can be represented exactly by a model in our constructed transformer class, providing a principled foundation for the proposed query-dependent attention architecture. The operator is trained through amortized denoising score matching across task distributions. We establish generalization-error bounds that quantify the effects of the context size, the numbers of training tasks and within-task samples, model complexity, and intrinsic and ambient dimensions. Numerically, we evaluate the method on a range of scientific and visual datasets, including Navier-Stokes, ERA5 climate data, QuickDraw sketches, and Food-101. The results show that the proposed method performs well on relatively simple task families, while its performance degrades as task complexity increases, thereby illustrating both the promise and the limitations of in-context learning for diffusion models.
ThinkDrag improves image editing by understanding semantic meaning
ThinkDrag: Semantic Drag-Based Image Editing with Visual Reasoning
Abstract: Drag-based image editing provides an intuitive interface for spatially controlled image manipulation by allowing users to specify handle and target points. Existing methods have made substantial progress through optimization-based, one-step, and feed-forward formulations, but they often interpret drag instructions as geometric displacements. This limits their effectiveness when the desired edit depends on interpreting image content and inferring a plausible semantic transformation from sparse point constraints. We introduce ThinkDrag, a unified multimodal framework for drag-based image editing with visual reasoning. ThinkDrag is trained to associate point constraints with meaningful object- and scene-level transformations, and can optionally produce an explicit reasoning trace that interprets the intended edit before image generation. This reasoning trace improves interpretability, particularly for ambiguous drags. Drag Endpoint Markers, motivated by an analysis of cross-image attention, provide an explicit correspondence signal that grounds each drag in image space. To support this framework, we construct a supervised dataset of semantic drag transformations paired with reasoning traces and introduce DragBench++, a benchmark targeting challenging drag-based editing scenarios with reference edit solutions. Experiments show that ThinkDrag achieves state-of-the-art performance, improving generation quality and plausibility while maintaining competitive point-following precision.
Velocity correction improves complex image generation with minimal slowdown
A Lightweight Velocity Correction Framework for Improving Instruction Following in Few-Step Text-to-Image Generation
Abstract: Few-step text-to-image generators produce high-quality images with few network forward passes, yet struggle with complex prompts involving multiple subjects, interactions, spatial relations, counting, and attribute binding. Can these errors be reduced without changing the generator's parameters or increasing its forward-pass count? We propose a lightweight correction framework for a frozen 6B-parameter generator. The generator predicts velocities that determine how its intermediate image representation is updated; a corrector with fewer than 20M parameters learns residual adjustments at selected sampling steps. Because earlier corrections change the states encountered at later steps, our On-Trajectory Flow-Bridge Supervision derives residual targets at the states actually reached during corrected generation. A single corrector is shared across selected steps and runs in parallel with the generator. Only the corrector is trained, requiring neither reward optimization nor re-distillation. To our knowledge, this is the first framework for lightweight velocity-residual adaptation of fully frozen few-step text-to-image generators that preserves their original sampling schedule and forward-pass count. On our target complex-scene distribution, the framework achieves a +17.60-percentage-point NetWin over frozen Z-Image-Turbo in pairwise instruction-following evaluation, with only 26.9 ms (0.84%) additional end-to-end latency per image and no increase in backbone evaluations.
Diffusion model attribution reveals how training examples shape images
Attributing HOW, Not Just WHICH: Counterfactual Response Trajectories for Diffusion Models
Abstract: Diffusion models have achieved remarkable success in image generation, yet tracing their outputs to individual training examples remains challenging. Existing attribution methods often compress factor-specific effects into scalar responses, making distinct internal changes indistinguishable. This is particularly limiting for diffusion models, where semantic factors emerge through evolving representation dynamics during denoising. We therefore reformulate diffusion data attribution as attributing factor-induced internal response trajectories. In this paper, we propose a novel Concept Attribution method through Dynamic Trajectories(CADT). We argue that attribution should therefore ask not only \emph{which} examples matter, but also \emph{how} their influence unfolds during generation. Specifically, we construct matched counterfactual pairs at identical noisy states to isolate factor-specific representation displacements, and model their directional and magnitude evolution across denoising as dynamic attribution signatures. For each training example and generated query, CADT extracts stage-wise feature vectors and integrates them along the denoising process to form a trajectory descriptor. Applying the same construction across the training set yields a bank of factor-specific trajectory descriptors. The covariance statistics of this bank are then used to construct . CADT uses this covariance-aware positive-semidefinite kernel to calibrate the query and training representations, and compares the calibrated query trajectory with each training trajectory to produce the final training-sample attribution scores. Experiments on multiple public datasets show consistent improvements over existing diffusion attribution baselines across hierarchical, compositional, and style attribution.
Balancing watermark quality and robustness in diffusion image marking
Diffusion-Generated Image Watermarking: A Two-Axis Taxonomy and Three Protocol-Bounded Case Studies
Abstract: Watermarking diffusion-generated images requires balancing provenance signals with image quality, robustness, and computational cost. This work organizes methods along two axes: insertion mechanism and primary signal-bearing representation, and formalizes a representative $z_T$-Fourier pipeline for verification and identification. We then use the taxonomy to structure three protocol-bounded case studies. The first examines associations among frequency integrity, detection, quality, and cropping behavior. The second revisits persistence under seed-linked and seed-independent editing and formulates a scoped Semantic Imprinting Hypothesis without claiming a localized carrier or causal mechanism. The third studies single-shot VAE-latent phase modulation, including its efficiency, regeneration robustness, and robustness--quality operating points. Finally, we separate four content-level attack families from model/pipeline adaptation, propose corresponding evaluation protocols and testable conjectures for parameter-tuning threats, and identify additional temporal extensions for video. These analyses do not establish a universal ranking; instead, they provide a framework for matched, protocol-aware comparisons of watermarking systems for diffusion-generated images.
Improving boundary quality in multi-region image stylization
Enhancing Multi-Region Stylization with Interior-Guided Boundary Repair
Abstract: Region-based neural style transfer enables fine-grained artistic control by allowing independent stylization of semantic image regions. However, compositing these regions often leads to boundary artifacts, degrading visual quality. We propose Interior-Guided Boundary Repair (IGBR), a lightweight and model-agnostic method that improves boundary handling in multi-region stylization. IGBR repairs boundary pixels using interior-guided propagation and applies inward, distance-based blending restricted to object-background boundaries, preventing inter-object style leakage. The method is derived from a region-wise constrained formulation with a closed-form solution and can be seamlessly integrated into existing stylization pipelines without retraining. To evaluate efficiency of our IGBR, we introduce quantitative metrics that measure boundary consistency, gradient artifacts, inter-object leakage, and interior preservation without requiring annotated stylized images. Our experiments and evaluations demonstrate that the proposed IGBR consistently produces plausible boundaries, outperforming prior blending techniques in boundary consistency, gradient stability, and interior preservation. The code is available at https://github.com/Son-SDT/IGBR.
Latent diffusion allows detailed local control of image style and content
Local Content-Style Control for Diffusion-based Image Stylization
Abstract: Image stylization with latent-diffusion models entangles two independently refined axes: what a region depicts and how it is depicted. Such pipelines expose only global controls, yet professional retouching demands deliberate, region-specific control. We lift two conditioning weights already present in a ControlNet + IP-Adapter stylization pipeline from global scalars to per-location spatial maps, yielding local, per-axis control of content and style in a single generative pass. Because the two weights act on disjoint pathways, adjusting them independently spans a 2x2 retouching vocabulary, from free regeneration to identity preservation. We validate that edits stay confined to the retouched region and that each weight predominantly steers its own axis. Our approach requires no retraining and drops unchanged into any such pipeline.
Ai co-doodler helps artists find and flex creative limits
Reflecting on Creative-Boundaries with an AI Co-Doodler
Abstract: In this pictorial, we consider how the negotiation of creative boundaries with a co-creative AI system can create moments for personal creative reflection. We ground this in our experiences with Froggi-Draw, a single-initiative co-doodling system that gives users power to decide when and how much an AI "collaborator" (Froggi) contributes to their drawing. From a 1-week pilot study where (n=8) novice and experienced artists doodled daily with the system, we report on ways participants navigated creative risk and uncertainty, and how their usage and perceptions of Froggi shifted over time. In moments of disruption, participants described the system as encroaching on their creative territory. We consider how the design of a supportive, co-creative AI "collaborator" might look like the design of a supportive power dynamic---and finding ways to offer users control to find, reflect upon, and flexibly negotiate the boundaries of that dynamic.
Step distilled models enable style transfer via text instructions
Salvation Lies Within: Eliciting Inherent Style Transfer in Step-Distilled Diffusion Models
Abstract: Adapting step-distilled text-to-image (T2I) models through post-training incurs additional computational costs and affects native few-step generation behavior. This motivates a complementary route beyond style-specific adaptation: drawing on the visual knowledge already encoded in step-distilled T2I models to elicit stylistic capabilities through language. Pursuing this direction requires textual guidance that captures how visual attributes jointly define a style and remain applicable as the depicted content changes. To explore this approach, we introduce StyleForge, a fully automatic, training-free framework that expresses reference styles as reusable rendering instructions. By integrating overall rendering characteristics with local color and lighting behavior, StyleForge organizes visual evidence from reference images into a coherent specification of how the target style should be expressed. The specification is then compiled into textual guidance that can be reused across content prompts, enabling frozen step-distilled T2I models to render different subjects and scenes in the reference style while retaining native few-step generation. Extensive experiments show relative gains of up to 29.47\% in generation quality scores over the strongest baseline, while Pareto analysis indicates that improved stylization is accompanied by strong adherence to the requested content.
Text-to-image method balances quality and variety of generated images
Traversing the Satisfaction-Diversity Frontier in Text-to-Image Diffusion
Abstract: Text-to-image generation enables users to explore several images generated from the same prompt. For these generated images to be useful, each one must reflect the user's preferences, measured by a learned reward, and differ visually from the others to maintain diversity. Existing methods are limited: they either address reward and diversity separately or combine them in one aggregate score, enabling high diversity to offset low rewards. In this paper, we address these limitations by formulating generation as satisficing: every image (candidate) must satisfy a reward floor and the batch of images must satisfy a diversity cutoff. The reward floor controls the balance between worst-candidate reward and batch diversity; we show that varying this floor defines a Pareto frontier. To traverse this frontier, we introduce SatisDive, a training-free inference-time method. SatisDive uses a batch-relative reward cutoff to distinguish lower- from higher-reward candidates, emphasizing reward improvement for candidates below the cutoff and diversity among candidates above it. On Pick-a-Pic, at matched DreamSim, SatisDive improves worst-candidate reward over FK steering by up to 0.43 with FLUX.1-dev as the base model and HPSv3 as the reward, and by up to 0.70 with SANA-1.6B as the base model and ImageReward as the reward. More broadly, across their overlapping DreamSim ranges, SatisDive's satisfaction-diversity curve Pareto-dominates FK steering's curve in each setting.
Generating self-referential images with conformal geometric transformations
Moore, Escher, Penrose: A Conformal Golden Braid
Abstract: I don't think I have ever done anything as peculiar in my life. Among other things, it shows a young man looking with interest at a print on the wall of an exhibition that features himself. How can this be? Perhaps I am not far removed from Einstein's curved universe.'' So wrote M.C. Escher about his 1956 lithograph Print Gallery. Nearly half a century later, a mathematical analysis related its geometry to an untwisted source image through a conformal power map $z \mapsto z^α$, $α\in \mathbb{C}$. Building on this construction, we use a frozen text-to-image diffusion model to generate new self-referential scenes. Prompting alone does not enforce the recursion, while a post-hoc transformation can leave structures poorly connected. Applying the transformation during sampling is also insufficient: the denoiser may "repair" the intended distortion or drift out of the prescribed geometry. We construct a generalized inverse $T^\dagger$ of the non-invertible image transformation $T$, adapted to its recursive constraint. In the idealized formulation, the Penrose identity $TT^\dagger T = T$ makes $TT^\dagger$ an idempotent projection onto geometrically admissible images. Yet denoising only the transformed image remains an out-of-distribution task, even with projection. We therefore braid denoising steps with $T$ and $T^\dagger$: source-space steps develop the untwisted scene, while transformed-space steps refine its appearance and connections in the final geometry. We generate Print Gallery-like compositions and explore further transformations. Rather than distorting a finished image, we let the scene and its distortion develop together.
Unified image editors improve quality by switching text generation mode
When Text-to-Image Helps Editing: The Effects of Conditioning During Denoising
Abstract: Unified models are trained for both instruction-based image editing and text-to-image (T2I) generation, but standard editing pipelines keep source-image conditioning throughout denoising. We ask whether editing can benefit from T2I, and study how the effects of conditioning vary across edits and denoising stages. In pure editing, source attention declines for some edits over the sampling trajectory. This observation led us to task switching, which lets the model draw on its T2I capabilities. Across three unified editors and four benchmarks, switching to the T2I task for bounded intervals improves edit quality, while mean perceptual preservation remains close to pure editing across all three models. Unified editors therefore benefit from using both conditioning modes they are trained for, and the timing of the switch sets the balance between quality and preservation.
Benchmark tests multimodal image models with multiple visual instructions
VIF-Bench: Evaluating Visual Instruction Following in Multi-Reference Image Generation
Abstract: Recent multimodal image generation models can take multiple images and textual instructions as input, enabling reference-based generation guided not only by text but also by visual instructions such as layouts, arrows, and pose cues. However, existing benchmarks do not evaluate the joint setting in which multiple references must be composed under multiple and heterogeneous visual-instruction images. To address this gap, we introduce VIF-Bench, a benchmark of 1,241 tasks designed to assess the edge of model capabilities in this joint setting by covering: (i) multi-reference generation (up to 7) under multiple heterogeneous visual instructions (up to 6), (ii) cases where reference images can potentially compete with visual instructions (e.g., a strongly posed subject vs. a target pose), and (iii) controlled comparison of visual instructions with text descriptions at different levels of specificity. Using these capabilities, we uncover three findings: (1) models face an adherence-artifact trade-off: once models reach stronger visual instruction adherence, stronger adherence tends to coincide with more instruction artifacts in generated images, (2) visual instruction adherence tends to be lower on tasks whose reference images carry a salient state of the controlled attribute (e.g., a neon-lit subject under a light-direction instruction), most consistently for light and wind, and (3) for models that can understand visual instructions, it is often better to provide visual constraints directly rather than describe them in text; when using text, a moderate level of detail works better than an exhaustive description. VIF-Bench is released as an open benchmark to establish a basis for fair comparison in controllable multi-reference image generation.
Trigger indexed memory improves personalized text to image generation
V-Engram: Trigger-Indexed External Memory for Modular Text-to-Image Personalization
Abstract: Pretrained text-to-image models contain broad visual knowledge, yet they cannot reliably acquire or refine a specific visual identity from only a few references while preserving compositional control. Token-embedding methods are compact but often underfit identity, whereas adapter-based methods improve fidelity through persistent weight updates that can be costly to store and interfere when concepts are composed. We introduce V-Engram, a trigger-indexed external memory mechanism for Stable Diffusion 3.5. Each concept is assigned an explicit trigger that retrieves concept-specific memory, whose gated directions enter frozen text-encoder and MMDiT context states as relative residuals. Separating this memory from backbone adaptation enables prompt-selective and multi-concept access without merging model updates. Experiments show that V-Engram broadly matches DreamBooth-LoRA in overall subject fidelity while showing advantages in settings such as contextual subject preservation. Prompt-matched loading retrieves only matched entries, reducing most additional adaptation-state loading for a single-concept query. Qualitative results further demonstrate paired-trigger composition and same-class separation, while prompts without registered entries retain the frozen model's base behavior. Together, these results establish trigger-indexed memory as a modular interface for adding targeted visual evidence without rewriting the generator.
Constrained edit fields improve precision in text guided image editing
Constrained Edit Fields for Training-Free Flow Editing
Abstract: Text-guided image editing aims to perform a desired edit while preserving source content unrelated to it. Pretrained rectified-flow models enable training-free editing of real images through modifications to their sampling trajectories. However, responses at locations unrelated to the desired edit can still accumulate along the editing trajectory and become visible in the final result. To overcome this, we propose Constrained Edit Fields (CEF), which assigns each spatial location a continuous edit responsibility that quantifies its relevance to the desired edit. CEF estimates edit responsibility directly from the source image when the relevant content is present. For edits whose target content is absent from the source, CEF first generates an unconstrained proposal to reveal its realized spatial support and then estimates responsibility from that proposal. At each editing step, CEF decomposes the base edit field into prompt-induced and trajectory-induced components, enabling edit responsibility to preserve instruction-relevant updates while suppressing unintended trajectory-induced changes. Evaluated on all 700 PIE-Bench examples, CEF achieves state-of-the-art Structure Distance, background LPIPS, and background MSE with both Stable Diffusion 3.5 Medium and FLUX, while retaining competitive instruction alignment. On Stable Diffusion 3.5 Medium, it reduces these metrics over the previous best results by 10.2%, 21.2%, and 48.0%, respectively.
Gradient-based method improves image focus in reinforcement learning alignment
SGA-Flow-GRPO: Spatial Gradient-Guided Credit Assignment for Flow-GRPO
Abstract: Reinforcement Learning (RL) has proven effective in aligning flow-based generative models with human preferences. Recently, Flow-GRPO has emerged as an efficient critic-free paradigm by calculating advantages over sampled candidate trajectories. However, standard Flow-GRPO applies a uniform scalar advantage across both temporal denoising steps and spatial latent dimensions, without explicitly accounting for the spatial structure of generated images, which may lead to sub-optimal policy updates. To address this, we propose a novel gradient-guided spatial credit assignment framework tailored for Diffusion Transformers (DiTs). We first reformulate the transition-level log-likelihood in Flow-GRPO into a token-wise representation natively aligned with DiT patch architectures, constructing spatially fine-grained importance sampling ratios. To allocate localized credit without rigid, boundary-sensitive segmentation heuristics, we introduce a continuous spatial credit map derived from reward gradients. Crucially, we employ an outlier-robust normalization scheme based on Median Absolute Deviation (MAD) coupled with temperature scaling, effectively eliminating gradient noise while highlighting functional prompt-aligned regions. Extensive evaluations on GenEval show that our approach delivers SOTA alignment quality, achieving a convergence rate comparable to top-tier methods like DiffusionNFT while substantially improving upon Flow-GRPO-based methods in alignment performance.
Text structures transformed into unique dance movements revealing hidden patterns
The Choreographic Genome: Amplifying the Silent Structure of Text into Dance
Abstract: Recent advances in generative artificial intelligence have enabled the synthesis of complex human motion with unprecedented fidelity. However, current text-to-motion systems rely strictly on linguistic semantics: if an input reads "I put my hands up", the model searches for a pose with raised hands, and every non-semantic property of the text is discarded as noise. In this work, we treat that discarded structure as the signal. We present an embodied visualization instrument that amplifies not what a text means, but how it is built. Our method first quantizes dance kinematics into a motion codebook of 256 stylistic "regions" using Principal Component Analysis and K-Means clustering, and orders those regions along the dominant axis of movement. We then map the raw byte representation of any input text directly onto this codebook, producing a deterministic sequence of regions that we call the text's "choreographic genome". A precomputed plausibility graph and a set of physics smoothing routines turn this genome into fluid, full-body movement, so that the dancing body becomes a display surface for the byte-level structure that semantic systems ignore. Through a series of artistic case studies, including a Shakespeare sonnet, a machine error log, source code, an abolitionist's question, and Indigenous and Devanagari scripts, we show that each text produces a visibly distinct dance, and that scripts marginalized by ASCII-centric computing are amplified into close to three times as much movement per character. We frame this not as a motion-synthesis benchmark, but as a critical and poetic visualization that asks what we choose to count as signal, and what we allow to go unheard.
Multimodal AI helps create authentic Ulos weaving designs
Multimodal Conditioning of Fine-Tuned Stable Diffusion XL for Controllable and Culturally Faithful Ulos Motif Generation
Abstract: The traditional Batak Ulos weaving industry faces growing challenges in producing diverse, innovative motifs due to limitations in conventional, manually driven design methods. This study proposes a multimodal generative framework integrating a fine-tuned Latent Diffusion Model (Stable Diffusion XL v1.0 via LoRA) with a Multimodal Large Language Model (LLaMA 1.5-7B) to enable controllable, culturally faithful Ulos motif generation. Four complementary conditioning mechanisms: text, image, representation, and semantic map (via ControlNet) jointly guide the generation process, each governing a distinct aspect from semantic intent to spatial layout. A five level ablation study across three scenarios (shape transformation, colour variation, and high-complexity input) shows that conditioning effectiveness is not proportional to the number of mechanisms combined: Text + Image + Semantic Map achieved the best FID (270) and CLIP Score (0.65 - 0.70) but the weakest SSIM (0.65), while Text + Image + Representation offered the best overall balance, with stable SSIM (0.84) and competitive FID (280). Combining all four mechanisms yielded the weakest FID (330), indicating conflicting optimization signals. Qualitative evaluation by nine weavers and thirty public participants confirmed statistically significant positive acceptance (Wilcoxon, p=0.007 and p<0.001, respectively). A web-based prototype supporting text-to-image and image-to-image generation was also developed, offering a practical digital design tool for cultural heritage preservation.
Feature rearrangement improves single image generation quality and structure
FRPSS: Feature Rearrangement in Pre-Shape Space for Single-Image Generation
Abstract: Generative models trained on a single image often struggle to balance global structural integrity and local diversity. Existing single-image generation methods commonly rely on random noise to drive the generation process and lack explicit global structural constraints, making the generated results prone to spatial structural misalignment when structural variations occur. To address the issue, Feature Rearrangement in Pre-Shape Space for Single-Image Generation (FRPSS) is proposed in this paper. The core of FRPSS is the Manifold Structural Rearrangement with Feature Augmentation on Geodesic Surface (MSR-FAGS) module. MSR-FAGS replaces the randomly initialized features of the low-scale generator with rearranged Pre-Shape features and uses the features to guide image generation at subsequent scales, thereby reducing the risk of structural misalignment. To support downstream tasks such as stylization, a Scale-adaptive Sliding-window Patch Extraction (SSPE) strategy is further designed, and a directional Contrastive Language-Image Pre-training supervision module with SSPE (CLIP-SSPE) is constructed. Qualitative and quantitative experiments demonstrate that FRPSS achieves the best Single Image Fréchet Inception Distance (SIFID) scores on all three datasets while maintaining competitive Learned Perceptual Image Patch Similarity (LPIPS). Further qualitative experiments verify the effectiveness of FRPSS across multiple downstream tasks with the CLIP-SSPE module.
Chinese digital painters balance human and AI roles in creative work
Where Does the Human End? Creative Agency with Generative AI across Five Years of Chinese Digital Painting
Abstract: As generative AI enters creative work, practitioners must decide where AI assistance ends and human authorship begins. Human-agent interaction (HAI) research has examined AI as a tool, collaborator, consultant, and competitor. The longitudinal problem is how these roles are revised as systems become more capable, public, and economically embedded. We report a five-year interview study with 17 Chinese digital painters, based on annual semi-structured interviews from 2021 to 2025. Participants described recurring but non-uniform patterns of protective resistance, pragmatic task delegation, and, for some, reflective agency repartitioning. Early resistance protected observation, originality, signature, and ownership from AI. Later delegation placed AI in bounded tasks such as references, backgrounds, rough sketches, and client-facing drafts. By 2025, some participants built hybrid workflows around human-only zones, while others described fatigue, precarity, or difficulty locating a remaining human role. Peer norms, emotional climates, and production pressures shaped which delegations felt useful, acceptable, or exhausting. Copyright, authorship, and creative labor remained recurring limits on what participants were willing to delegate. We frame these accounts as longitudinal agency partitioning, the situated work of deciding which stages, responsibilities, values, and claims remain human in creative human-agent interaction. We discuss design implications for revisable agency-boundary controls, provenance scaffolds, and community-facing authorship norms.
Digital marbling programs recovered efficiently from images with replay method
Inverse Digital Marbling: Recovering Gesture Programs with a Replay Adjoint
Abstract: Pigment deposition in paper marbling displaces the pattern already present, coupling the appearance of each gesture to later actions. We recover executable programs for a deposition-based digital marbling model: given a target image, we optimise an ordered program of capsule insertions whose replay approximates it. The capsule primitive continuously joins circular drops to elongated deposits. Its transport is exactly area-preserving and has a closed-form inverse on the exterior of the deposited region. A replay adjoint reconstructs intermediate states, retaining coordinates lost inside deposits and periodic position checkpoints. At 2000 gestures and 1024^2 pixels, the PyTorch replay implementation uses 8.7x less memory than the tested checkpointed-autograd configuration at comparable step time; the fused implementation fits a program in about four minutes on one workstation GPU. We evaluate image reconstruction on five marbled sheets, compare against transport-disabled fitting, one-pass geometric compensation and a published stroke-based fitter at matched stroke count, and measure sensitivity to an alternative ordered-drop transport. Recovered programs replay across a 4x range of linear resolution. Edits specified in program order or in palette space -- inserting a gesture, recolouring a stage, translating a stage -- replay correctly under the same model; edits specified by image content, such as moving a motif, do not. On synthetic targets with known generating programs, the recovered programs match the images but not the generating gestures under a positional matching statistic. The output is an editable program in the specified digital medium.
Single image analysis reveals repeated objects for better modeling
Bottom-up Modeling of Repeated Elements via Single Image Analysis-by-Synthesis
Abstract: We address the problem of discovering repeated elements from a single image. In contrast to existing approaches that depend on large annotated datasets, curated multi-image collections, or object segmentation masks, we show that a single image can suffice to learn a meaningful object model in a completely bottom-up fashion, without any prior knowledge beyond a coarse scale prior. Our method learns a tunable image-space prototype of the repeated elements through a reconstruction objective, enabling the model to identify and synthesize consistent object instances within the same image. Experiments on 116 real images from the FSC-147 dataset demonstrate that our method successfully learns coherent element models and captures intra-category variation on challenging images. Qualitative results reveal superior reconstructions and interpretable decompositions compared to classical decomposition, joint alignment, and 3D object modeling methods, while maintaining a simple 2D formulation. These results suggest that meaningful object discovery can emerge from single image learning alone.