inclusionAI open-sources two 6B Ming-Image-0.1-Design models

inclusionAI has open-sourced the Ming-Image-0.1-Design family under the MIT License as two complementary 6B models for visual-design workflows. Ming-Image-0.1-Design generates complete UIs, dashboards, infographics, and posters at up to 2048×2048 and can produce native transparent RGBA output. Ming-Image-0.1-Design-Layer decomposes flattened graphics into independently editable RGBA layers while preserving the original aspect ratio.

The pipeline combines multimodal prompt conditioning, a diffusion transformer, and a 4-channel VAE. Layer adds multi-frame generation for separate layer outputs.

ModelScope says Design ranks first among open-weight models on the Artificial Analysis UI/UX Design leaderboard and has strong text rendering. It also says Layer leads all 12 evaluated Crello settings and runs 4.3× faster than the evaluated 20B open-weight baseline.