AttnRouter enhances image editing on MMDiT with per-category attention routing

Researchers have developed AttnRouter, a novel method for training-free image editing on the MMDiT model. This approach utilizes KVInject, a single-forward attention manipulation that blends source-image key/value projections into the noise stream. AttnRouter further enhances this by employing a per-category routing table to dispatch edits to the most effective operation for preserving source structure, significantly improving image quality. AI

影响 Introduces a more efficient and effective method for training-free image editing, potentially improving generative model capabilities.

排序理由 This is a research paper detailing a new method for image editing on a specific model. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

• AttnRouter
• ImgEdit-Bench
• KVInject
• MasaCtrl
• MMDiT
• Qwen-Image-Edit-2511
• DINO-I

• 论文
• 模型发布

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →