ETCHR SFT-400K

📖Paper | 🏠Homepage | 🤗ETCHR-FLUX.2-klein-9B Model | 🤗ETCHR SFT-400K Dataset | 🤗ETCHR GRPO-10K Dataset | 🤗DL3DV-2K Benchmark

ETCHR SFT-400K is the SFT training data for transfering a passive instruction-following image editor (built on FLUX.2-klein-base-9B) into an autonomous, question-conditioned visual reasoning assistant. It contains 400,000 samples of five tasks (Fine-grained Perception, Chart Understanding, Maze Solving, Jigsaw Puzzle and Spatial Understanding). Each sample contains the raw image, an understanding question for this image as the editing prompt, and the groundtruth edit which helps the understanding model to answer this question.

📢 News

• 🚀 [2026/05/22] We have released the training and evaluation code of ETCHR.
• 🚀 [2026/05/21] We have released the ETCHR-FLUX.2-klein-9B Model, ETCHR-SFT-400K Dataset and ETCHR GRPO-10K Dataset.

🌈 Overview

We are thrilled to introduce ETCHR (Editing To Clarify and Harness Reasoning), a novel question-conditioned, reasoning-aware image editor designed to serve as a decoupled visual reasoning assistant for Multimodal Large Language Models (MLLMs).

By decoupling the specialized image editor from the downstream understanding model, ETCHR bridges the critical bottleneck where a purely textual chain of thought fails in fine-grained focus or complex spatial transformations.

💡 Highlights

• 🔥 Decoupled & Plug-and-Play: ETCHR functions as a separate module, allowing it to assist diverse downstream MLLMs (such as Qwen3-VL-8B, Gemini-3.1-Flash-Lite, or Kimi K2.5) without requiring any task-specific fine-tuning on the understanding models themselves.
• 🔥 Naturally Reflective Pipeline: Introduces an Edit-Verify-Reason inference mechanism where the understanding model filters out noisy or flawed edits, reverting safely to the original image when verification fails.

🛠️ Usage

You can find all source images, groundtruth edit and text instruction in SFT-400K.parquet. The data is organized in DiffSynth-Studio training format. See https://github.com/InternLM/ETCHR/blob/master/SFT/SFT.md for further details.

✒️Citation

If you find this project useful, please kindly cite:

@article{zhang2026etchr,
  title={ETCHR: Editing To Clarify and Harness Reasoning},
  author={Beichen Zhang, Yuhong Liu, Jinsong Li, Yuhang Zang, Jiaqi Wang, Dahua Lin},
  journal={arXiv preprint arXiv:2605.23897},
  year={2026}
}