Rethinking Prompt Design for Inference-time Scaling in Text-to-Visual Generation
By: Subin Kim , Sangwoo Mo , Mamshad Nayeem Rizve and more
Potential Business Impact:
Improves AI art by changing instructions.
Achieving precise alignment between user intent and generated visuals remains a central challenge in text-to-visual generation, as a single attempt often fails to produce the desired output. To handle this, prior approaches mainly scale the visual generation process (e.g., increasing sampling steps or seeds), but this quickly leads to a quality plateau. This limitation arises because the prompt, crucial for guiding generation, is kept fixed. To address this, we propose Prompt Redesign for Inference-time Scaling, coined PRIS, a framework that adaptively revises the prompt during inference in response to the scaled visual generations. The core idea of PRIS is to review the generated visuals, identify recurring failure patterns across visuals, and redesign the prompt accordingly before regenerating the visuals with the revised prompt. To provide precise alignment feedback for prompt revision, we introduce a new verifier, element-level factual correction, which evaluates the alignment between prompt attributes and generated visuals at a fine-grained level, achieving more accurate and interpretable assessments than holistic measures. Extensive experiments on both text-to-image and text-to-video benchmarks demonstrate the effectiveness of our approach, including a 15% gain on VBench 2.0. These results highlight that jointly scaling prompts and visuals is key to fully leveraging scaling laws at inference-time. Visualizations are available at the website: https://subin-kim-cv.github.io/PRIS.
Similar Papers
Improving Text-to-Image Generation with Input-Side Inference-Time Scaling
Computation and Language
Makes computer pictures better from simple words.
Improving Text-to-Image Generation with Input-Side Inference-Time Scaling
Computation and Language
Makes computer pictures better from simple words.
Multi-Scale Visual Prompting for Lightweight Small-Image Classification
CV and Pattern Recognition
Makes computer vision work better on simple pictures.