跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2609.35673 · v2

FlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching

首次提交 2026-09-29 01:28
版本更新 2026-11-15 21:53
雷达观测 2026-11-17 19:15
arXiv ↗PDF ↗

摘要

Tool-based image editing (image retouching) is commonly formulated with autoregressive multimodal large language models (MLLMs) that sequentially generate reasoning, tool selections, and parameter values. In this work, we present a novel approach to tool-based image editing by framing the task as a flow matching problem. We introduce FlowTool, a framework that directly models the distribution of high-quality tool parameters conditioned on the input image and user instruction using conditional rectified flow. FlowTool combines a vision-language model backbone for multimodal understanding with a Diffusion Transformer parameter generator that transforms Gaussian noise into an editing plan. We train FlowTool with a two-stage supervised flow-matching curriculum, followed by reward-based post-training. Across four benchmarks, FlowTool significantly outperforms specialized MLLM agents and remains competitive with proprietary MLLMs, while reducing latency by at least 50×50\times and using nearly half the memory of the evaluated local baselines. These results demonstrate that tool-based image editing can be effectively modeled as conditional generation over structured continuous editing parameters, without autoregressive reasoning.

作者备注:Under review

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-15 21:53 · 最新观测版本

FlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching

Tool-based image editing (image retouching) is commonly formulated with autoregressive multimodal large language models (MLLMs) that sequentially generate reasoning, tool selections, and parameter values. In this work, we present a novel approach to tool-based image editing by framing the task as a flow matching problem. We introduce FlowTool, a framework that directly models the distribution of high-quality tool parameters conditioned on the input image and user instruction using conditional rectified flow. FlowTool combines a vision-language model backbone for multimodal understanding with a Diffusion Transformer parameter generator that transforms Gaussian noise into an editing plan. We train FlowTool with a two-stage supervised flow-matching curriculum, followed by reward-based post-training. Across four benchmarks, FlowTool significantly outperforms specialized MLLM agents and remains competitive with proprietary MLLMs, while reducing latency by at least 50×50\times and using nearly half the memory of the evaluated local baselines. These results demonstrate that tool-based image editing can be effectively modeled as conditional generation over structured continuous editing parameters, without autoregressive reasoning.

查看此版本解读 →查看此版本原文 ↗