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
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
- DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models (CVPR 2025 · similarity 0.88)
- When Worse is Better: Navigating the Compression Generation Trade-off In Visual Tokenization (NeurIPS 2025 · similarity 0.88)
- An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models (ICLR 2026 · similarity 0.88)
- Learning Visual Generative Priors without Text (CVPR 2025 · similarity 0.88)
- Image Generation Diversity Issues and How to Tame Them (CVPR 2025 · similarity 0.88)
- DiverseFlow: Sample-Efficient Diverse Mode Coverage in Flows (CVPR 2025 · similarity 0.88)
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.
