AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

TokenRepel: Generating Diverse Image Sets Without Sacrificing Quality

Qingtao Yu, Zhen Wang, Ning Lai, Boyang Hu, Hongdong Li, Dylan Campbell

NeurIPS 2026 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes TokenRepel, an inference-time method that boosts visual diversity of text-to-image batches generated from the same prompt by repelling hidden latent tokens, while keeping average image quality.

Problem

Text-to-image models produce visually homogeneous image sets for a single prompt, and naive diversity methods tend to degrade image quality.

Approach

Uses the intrinsic geometry of hidden latent token representations in pretrained T2I models, introducing a token repulsion mechanism that pushes apart the latent representations of images generated in the same batch under one prompt, applied at inference time.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy