Ming-Image: Open Design and Layer Decomposition Model Family
ComfyUI Wiki
Ming-Image is inclusionAI's open 6B family for visual design generation and editable layer decomposition, with RGBA output and ComfyUI support in progress.
M
Ming-Image
ImageText-to-ImageUI DesignRGBA OutputOpen 6B model family by inclusionAI for visual design generation. The Design checkpoint composes UI screens, infographics and text-heavy posters with optional RGBA transparency, and the Layer checkpoint decomposes a flattened design into independently editable transparent layers.
| Developer | inclusionAI |
| Release Date | 2026-09-17 |
| Architecture | 6B diffusion transformer + vision-language text encoder |
| License | MIT |
| Output | 1024 / 2048 image buckets, optional RGBA |
| ComfyUI | Repacked weights available, core support in progress |
Models
| Model | Description | License | Released |
|---|---|---|---|
| Ming-Image 0.1 Design | 6B text-to-image model for UI, infographics and posters, with RGBA transparency | MIT | 2026-09-17 |
| Ming-Image 0.1 Design Layer | 6B model that decomposes a flattened design image into editable transparent layers | MIT | 2026-09-17 |
Select a model above for curated weight downloads, tutorials, and related information.
Comments
Sign in with GitHub to join the discussion.