Ming-Image 0.1 Design: 6B Model for UI, Infographics and Posters

ComfyUI Wiki

Ming-Image 0.1 Design is a 6B text-to-image model for UI, infographics and posters, with RGBA transparency output and ComfyUI support in progress.

M

Ming-Image 0.1 Design

Text-to-ImageUI DesignRGBA TransparencyText Rendering

6B open text-to-image model by inclusionAI built for visual design rather than photography. It composes UI screens, dashboards, infographics, posters and other text-heavy layouts, and can write an RGBA image with a real alpha channel for composite-ready output.

Hugging FaceGitHubDemo
DeveloperinclusionAI
Release Date2026-09-17
Architecture6B diffusion transformer (Z-Image derived) with a vision-language text encoder
Parameters6B
LicenseMIT
Resolution1024 x 1024 or 2048 x 2048
Sampling12 steps, CFG 1.0

Capabilities

  • Design generation: UI screens, dashboards, responsive card layouts, infographics, posters and logo sheets
  • Text rendering: layouts are built around legible rendered text rather than incidental captions
  • RGBA transparency: optional transparent-background output for assets that get composited somewhere else
  • Prompt enhancement: the official pipeline rewrites prompts with Ling-3.0-flash-VL or qwen3.8-27B before sampling
  • Two output buckets: 1024 for fast iteration, 2048 for full layouts

Guides and workflows related to this model series.

No articles found.

Comments

Sign in with GitHub to join the discussion.

Loading comments…