Beyond Starry Night: Shortcut-Aware Control-State Planning for Artist-Grounded Text to Image Generation

• URL: http://arxiv.org/abs/2608.06751v1
• Date: Fri, 07 Aug 2026 03:17:49 GMT
• Title: Beyond Starry Night: Shortcut-Aware Control-State Planning for Artist-Grounded Text to Image Generation
• Abstract summary: Atelier is a shortcut-aware control-state planning framework for artist-grounded image generation.<n>ArtIntentBench is a benchmark covering Van Gogh and Qi Baishi across artwork re-rendering, period/style-controlled generation.
• Score: 35.53038441504792
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Artist-grounded image generation requires more than appending an artist name to a prompt. Image models often respond to artist names through canonical shortcuts, such as recurring motifs, generic palettes, or overrepresented period signatures, rather than preserving the user's intended scene. We introduce Atelier, a shortcut-aware control-state planning framework for artist-grounded image generation. Atelier translates underspecified artistic intent into an explicit control state that separates scene anchors, preserve/transform decisions, style-regime hypotheses, role-bound artist evidence, and shortcut-avoidance constraints. It grounds this state using artist-level knowledge and local patch references, compiles backend-aware generation plans, and iteratively refines candidates through global and local authenticity feedback. We further introduce ArtIntentBench, a benchmark covering Van Gogh and Qi Baishi across artwork re-rendering, period/style-controlled generation, historically unseen subjects, shortcut auditing, and human preference evaluation. Across open-weight and closed-source generators, Atelier improves artist-level style fidelity, preserves source structure more faithfully, and substantially reduces shortcut substitution compared with prompt-engineered, retrieval-augmented, and general-purpose agent baselines. These results suggest that artist-grounded generation is bottlenecked not only by image synthesis, but by the upstream inference of explicit, evidence-grounded artistic controls.

Related papers

• MythraGen: Two-Stage Retrieval Augmented Art Generation Framework [11.27056623462154]
  Our method extracts features from a large-scale art dataset, optimizing the generation process by combining artist-specific styles and content.<n>Our proposed method can generate artworks that closely match the user's input, significantly outperforming existing solutions.
  arXiv  Detail & Related papers  (2026-06-22T07:02:33Z)
• The Name-Free Gap: Policy-Aware Stylistic Control in Music Generation [4.654067937895813]
  We study whether lightweight, human-readable descriptors can provide a policy-robust alternative for stylistic control.<n>We evaluate two artists: Billie Eilish (vocal pop) and Ludovico Einaudi (instrumental piano)<n>Results show that artist names are the strongest control signal across both artists, while name-free descriptors recover much of this effect.
  arXiv  Detail & Related papers  (2025-08-31T01:27:16Z)
• Identifying Prompted Artist Names from Generated Images [59.34482128911978]
  A common and controversial use of text-to-image models is to generate pictures by explicitly naming artists.<n>We introduce a benchmark for prompted-artist recognition.<n>The dataset contains 1.95M images covering 110 artists.
  arXiv  Detail & Related papers  (2025-07-24T17:59:44Z)
• ArtistAuditor: Auditing Artist Style Pirate in Text-to-Image Generation Models [61.55816738318699]
  We propose a novel method for data-use auditing in the text-to-image generation model.<n>ArtistAuditor employs a style extractor to obtain the multi-granularity style representations and treats artworks as samplings of an artist's style.<n>The experimental results on six combinations of models and datasets show that ArtistAuditor can achieve high AUC values.
  arXiv  Detail & Related papers  (2025-04-17T16:15:38Z)
• Rethinking Artistic Copyright Infringements in the Era of Text-to-Image Generative Models [47.19481598385283]
  ArtSavant is a tool to determine the unique style of an artist by comparing it to a reference dataset of works from WikiArt. We then perform a large-scale empirical study to provide quantitative insight on the prevalence of artistic style copying across 3 popular text-to-image generative models.
  arXiv  Detail & Related papers  (2024-04-11T17:59:43Z)
• Learning Subject-Aware Cropping by Outpainting Professional Photos [69.0772948657867]
  We propose a weakly-supervised approach to learn what makes a high-quality subject-aware crop from professional stock images. Our insight is to combine a library of stock images with a modern, pre-trained text-to-image diffusion model. We are able to automatically generate a large dataset of cropped-uncropped training pairs to train a cropping model.
  arXiv  Detail & Related papers  (2023-12-19T11:57:54Z)
• LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation [121.45667242282721]
  We propose a coarse-to-fine paradigm to achieve layout planning and image generation. Our proposed method outperforms the state-of-the-art models in terms of photorealistic layout and image generation.
  arXiv  Detail & Related papers  (2023-08-09T17:45:04Z)
• QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity [94.5479418998225]
  We propose a new style transfer framework called QuantArt for high visual-fidelity stylization. Our framework achieves significantly higher visual fidelity compared with the existing style transfer methods.
  arXiv  Detail & Related papers  (2022-12-20T17:09:53Z)
• Continuation of Famous Art with AI: A Conditional Adversarial Network Inpainting Approach [1.713291434132985]
  This work explores the application of image inpainting to continue famous artworks and produce generative art with a Conditional GAN. An inpainting GAN is then tasked with learning to reconstruct the original image from the centre crop by way of minimising both adversarial and absolute difference losses. Images are resized rather than cropped and presented as input to the generator. Following the learning process, the generator then creates new images by continuing from the edges of the original piece.
  arXiv  Detail & Related papers  (2021-10-18T10:39:32Z)

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

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