# Progressive Prompt Detailing for Improved Alignment in Text-to-Image Generative Models

Source: [Progressive Prompt Detailing for Improved Alignment in Text-to-Image Generative Models](<https://www.sota2.com/research/paper/68fa790a1e209131cea7bd83>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:52:00.639Z

Authors: Ketan Suhaas Saichandran, Xavier Thomas, Prakhar Kaushik, Deepti Ghadiyaram

Published: 2025-03-22T15:05:21.000Z

## Abstract

Text-to-image generative models often struggle with long prompts detailing complex scenes, diverse objects with distinct visual characteristics and spatial relationships. In this work, we propose SCoPE (Scheduled interpolation of Coarse-to-fine Prompt Embeddings), a training-free method to improve text-to-image alignment by progressively refining the input prompt in a coarse-to-fine-grained manner. Given a detailed input prompt, we first decompose it into multiple sub-prompts which evolve from describing broad scene layout to highly intricate details. During inference, we interpolate between these sub-prompts and thus progressively introduce finer-grained details into the generated image. Our training-free plug-and-play approach significantly enhances prompt alignment, achieves an average improvement of more than +8 in Visual Question Answering (VQA) scores over the Stable Diffusion baselines on 83% of the prompts from the GenAI-Bench dataset.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.17794>)

[PDF](<https://arxiv.org/pdf/2503.17794.pdf>)
