PixText 推出两款约 0.95B 的开源权重模型，可直接在像素空间做本地文本精修。其中 PixText-MeanFlow 四步生成即可完成快速局部编辑，单图摊销成本低于 1 GPU 秒，仍保持 81.84% 字形通过率；文本纠错上达到 83.06% 字形通过率和 94.66% 目标字符精确 OCR 准确率，领先最强已报告基线。
PixText offers two ~0.95B open-weight models for local text refinement directly in pixel space.
🤖 https://modelscope.ai/models/ATH-MaaS/PixText
📄 https://modelscope.ai/papers/2610.18284
🏆 Strong text correction: Reaches 83.06% glyph pass and 94.66% exact target-character OCR accuracy on TextRefinementBench, ahead of the strongest reported baseline.
⚡ Four-step generation: PixText-MeanFlow delivers fast local edits in four steps, retaining an 81.84% glyph pass rate with under one GPU-second amortized cost per image in the paper's setup.
🖼️ Edit text, not the whole image: Provide regions and replacement text, then generate multiple targets jointly while keeping pixels outside the edited footprints unchanged.
🧩 Two checkpoints: Choose the 4-step MeanFlow model for quick use or the 25-step Teacher model for the higher-step workflow.
📜 Apache 2.0.
来源：ModelScope · x.com