Coco Labs 推出设计模型 Vyb：按图层输出结构而非像素
Coco Labs 出了个设计模型 Vyb，不是吐图片而是按图层给结构，文字能改、图形是矢量，还能直接导 Figma，比图像模型 76% 的分数高到 90.3%。
Coco Labs 发布设计模型 Vyb，逐元素生成设计稿，每个元素独立成层，文字保持可编辑文本、图形保持矢量、照片保持像素。Vyb 能从网站自动抓取 logo、字体和准确色值。在 145 个随机选取的 Google fonts 测试中，以像素重叠度（IoU）计分，Vyb 达到 90.3%，对比组中最强图像模型为 76.0%，该测试的测量上限是 94.4%。由于每层保留原生类型，导出 Figma 时结构可完整保留。
Design is the next place where models are learning to output structure instead of pixels.
Vyb, a design model from Coco Labs, builds a graphic element by element, each on its own layer, so text stays live text, graphics stay vectors and photos stay pixels.
That changes what you get back. The headline can be retyped. The logo is the logo file, pulled from your website along with your fonts and exact colors.
Across 145 randomly chosen Google fonts, scored by pixel overlap (IoU) against a programmatic render, Vyb reached 90.3%. The measurement ceiling on that test is 94.4%, and the strongest image model in the comparison reached 76.0%.
Because every layer keeps its native type, the export to Figma carries the structure across intact.
- TestingCatalog20:13原文
