Ming Image 0.1 Design · Text to Image (Design)

ABOUT THE WORKFLOW

Generate a Design from Text
Describe the layout you want: colors, structure, text to render, and style. The model generates a finished composition with legible type and visual hierarchy. Turn on prompt enhancement to expand a short brief into a detailed layout caption before generation.

Model

• Ming Image 0.1 Design by inclusionAI (Ant Group). A 6B parameter open-source model built for design layouts, UI screens, posters, and infographics with accurate text rendering.

HOW IT WORKS

Step 1. Write your prompt
Describe the design you want. Include layout structure, colors, any text to render, and the overall style.
Works great with: UI screens · posters · infographics · cards

Step 2. Pick an aspect ratio
Choose the shape of the output. Square, portrait, and landscape ratios are available.

Step 3. Turn on prompt enhancement (optional)
A language model rewrites your short brief into a detailed layout caption. Useful when your prompt is a few words rather than a full description.

Step 4. Hit run and download
The model generates the full composition in one pass at 12 steps. The result saves as a PNG.
Ready for: Figma · Photoshop · Canva · any editor

First time? Leave every setting as-is. The defaults (1:1 square, 1 megapixel, 12 steps) are the right starting point for almost everyone.

RECOMMENDED SETTINGS

Quick-start guide. Find the goal that matches yours and copy the settings.

• Standard design (most people) — 1:1 square · 1 megapixel · 12 steps · prompt enhancement off. The right starting point for almost everyone.

• Quick concept check — 1:1 square · 1 megapixel · 12 steps. Fast enough to iterate on prompt wording before committing to a final version.

• Taller layout like a mobile screen or story — Switch the aspect ratio to 9:16 or 2:3. The model adapts the composition to the shape.

• Wider layout like a banner or header — Switch the aspect ratio to 16:9 or 3:2. Works well for web banners and social headers.

• Short prompt and not sure how to describe the layout — Turn prompt enhancement on. The language model expands your brief into a structured caption the image model works better with.

• Text in the image is not rendering correctly — Write the exact words you want in your prompt, spelled out character by character. Keep text in English for the strongest results.

Prompt: Be specific about structure, not mood. “A mobile app login screen with email and password fields, dark background, blue accent buttons, heading reads ‘Welcome Back’” works better than “a nice login page.” Spell out any text you want rendered exactly as it should appear.

LEARN

📹 Videos

• Intro to Floyo

• ComfyUI 101 Free Course ft. Sebastian Kamph

• Floyo 101 for Team Collaboration

✨ Quick links

• Help docs

• LoRA Training guide

• Discover more workflows

USE CASES

📱 UI and App Design
Generate screens, dashboards, and app interfaces from a text description to test layouts before building in Figma or code.

📊 Infographics and Data Layouts
Describe a structured layout with headings, stats, and sections and get a composed infographic with readable text and visual hierarchy.

🖼️ Posters and Marketing Cards
Create event posters, social cards, and promotional graphics with rendered headlines, taglines, and structured layouts.

🎨 Concept Exploration
Iterate on design directions by changing the prompt. Test color schemes, layout structures, and typography before committing to a full design.

💡 Presentation Slides
Generate slide layouts with headings, bullet structures, and visual elements as a starting point for decks and pitch materials.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• UI screens and app interfaces

• Posters with large headings and clear structure

• Infographics with sections, stats, and text blocks

• English text rendering

⚠️ May produce softer results

• Photorealistic images (this model is built for design, not photography)

• Small text in non-English languages

• Complex multi-page documents in a single image

• Highly detailed photographic textures

FAQ

What is Ming Image 0.1 Design?
Ming Image 0.1 Design is a 6B parameter open-source image model by inclusionAI, part of Ant Group. It is derived from Z-Image and built for generating design layouts, UI screens, posters, and infographics with accurate text rendering. It outputs 1024px or 2048px images and is released under the MIT license.

Can Ming Image 0.1 Design render readable text in images?
Yes. Accurate text rendering is one of its core strengths. Write the exact words you want in your prompt and the model renders them legibly inside the composition. Text rendering works best in English. Non-English text, especially at small sizes, may be less reliable.

What is prompt enhancement and when should I use it?
Prompt enhancement runs your brief through a language model that rewrites it into a detailed, structured layout caption before the image model sees it. Use it when your prompt is short or vague. Turn it off when you have already written a specific, structured prompt and want full control over the output.

Does Ming Image 0.1 Design support transparent backgrounds?
Yes. The model supports RGBA output, which means it can generate images with transparent backgrounds. This is useful for icons, UI elements, and assets you plan to composite over other content.

What resolution does Ming Image 0.1 Design output?
The model outputs at 1024px or 2048px, depending on the megapixel setting and aspect ratio. Resolution values snap to the nearest supported bucket. For most use cases, the default 1 megapixel setting produces clean results.

Is Ming Image 0.1 Design free and open source?
Yes. The model weights are published under the MIT license on Hugging Face and ModelScope. You can use the outputs commercially. On this platform, you pay for GPU generation time only.

How to run Ming Image 0.1 Design online?
You can run Ming Image 0.1 Design online through Floyo. No installation, no setup, no API key to wire up. Open the workflow in your browser, write your prompt, and hit run. Free to try.

WHY FLOYO?

Floyo is the only platform with team collaboration for ComfyUI in the browser. You run workflows with no install. You share run history, assets, and models across your team. You pay only when you generate. Floyo supports open-source and closed-source models.

A designer runs an edit and likes the result. A teammate opens that exact run from shared history and keeps going. No file handoffs. No version confusion.

For studios and enterprise teams, Floyo adds private workspaces, pooled resources, and a team usage dashboard. Other ComfyUI cloud tools run for one person at a time. Floyo runs for the whole team, with transparent per-generation costs.

Ready to try it?
Write a prompt describing your design and hit run. The settings are already set.

→ Launch Workflow, Free

Questions? Watch the free course or check the FAQ above.