← 研踪 PaperTrailarXiv: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
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 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
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 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 ↗