Ant Group said on September 22, 2026 that its inclusionAI team released Ming-Image-0.1-Design, an open model for UI mockups, posters, infographics and other text-heavy visuals, alongside a companion Design-Layer model for turning flattened designs into editable parts.
According to the Ant Group release, the main model supports native transparent-background RGBA output. Ant says the paired layer model can decompose a finished composition into separate editable RGBA layers, which could make generated assets easier to revise and hand off across design tools.
Ant describes Ming-Image-0.1-Design as an MIT-licensed diffusion transformer with roughly 6B parameters. The released configuration was validated on one CUDA GPU with 80 GiB of memory, so while the weights are available for self-hosting, the hardware bar is still high for many teams.