Search papers, labs, and topics across Lattice.
This paper introduces Atelier, a shortcut-aware control-state planning framework designed to enhance artist-grounded text-to-image generation by translating vague artistic intent into explicit control states. By integrating artist-level knowledge and local patch references, Atelier effectively reduces reliance on canonical shortcuts that compromise fidelity to the user's intended scene. The framework demonstrates significant improvements in style fidelity and structural preservation across various image generation models, highlighting the importance of explicit artistic controls in overcoming limitations in current generation methods.
Artist-grounded image generation can achieve unprecedented fidelity by explicitly controlling for artistic intent, rather than relying on shortcuts that distort user vision.
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.
