---
id: "2026-09-22-ant-ming-image-0-1-design"
url: "https://postcutoff.com/e/2026-09-22-ant-ming-image-0-1-design/"
as_of: "2026-10-15T10:09:00+02:00"
date: "2026-09-22"
date_precision: day
category: open-source
importance: 2
confidence: medium
status: [Partly confirmed]
sources: 4
editor: human editor
human_review: null
version: "2026-10-14"
---

As of: 2026-10-15 10:09 CEST.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2026-09-22-ant-ming-image-0-1-design/

# Ant Group's inclusionAI open-sources Ming-Image-0.1-Design (MIT), a 6B text-to-image model for UI, posters and infographics with transparent output, plus a layer-splitting sibling

Around 22 Sept 2026 Ant Group's inclusionAI lab published Ming-Image-0.1-Design, a 6B-parameter MIT-licensed text-to-image model for text-heavy designs (UI screens, infographics, posters) that can output RGBA images with real transparency, and Ming-Image-0.1-Design-Layer, which splits a flattened design into editable transparent layers. Benchmark claims (Artificial Analysis UI/UX Design leaderboard, Crello) are shown only as images.

## Key facts
- Model card: 'a 6B text-to-image model for UI, infographics, posters, and other text-rich visual designs'; BF16 safetensors, diffusers and vLLM-Omni support; MIT license
- Recommended: 2048×2048 (1024×1024 for speed), 12 sampling steps, CFG 1.0; the only validated setup is one GPU with at least 80 GiB of memory
- Architecture (ComfyUI Wiki): 30-layer, 3840-dim diffusion transformer with a separate vision-language encoder; Kijai describes the base as Z-Image-derived with a new text encoder; the official pipeline rewrites prompts with Ling-3.0-flash-VL or a Qwen model first
- Design-Layer: separate 6B checkpoint that turns a flattened design plus a layer plan into the requested number of RGBA layers; paired with inclusionAI's 'Ling UI Design' and 'image-to-editable-PPT' agent skills in ling-cookbook
- Dates: Hugging Face repo created Sept 17, 2026; DataNorth gives Sept 22 as the release; ComfyUI core support merged Sept 24; repo still updated Oct 14 (425 likes; 3 adapters, 17 fine-tunes, 11 quantizations on the Hub)
- Benchmarks: placement on the Artificial Analysis UI/UX Design leaderboard and Crello layer-recovery results appear only as chart images, no numbers in text; community notes (ComfyUI Wiki) report text failures remain common at INT8

## What happened

inclusionAI, Ant Group's open-model lab behind the Ling and Ming families, released two 6B open-weight image models aimed at
graphic design rather than photos: one generates complete layouts with legible text and optional transparent backgrounds, the other
decomposes a finished design into separate editable layers. Community quantizations and ComfyUI support followed within days.

## Why it matters

Text rendering and editable layers are what designers need from image models; an MIT-licensed model that does both narrows the gap
with closed design tools. The quality claims are unverified, since the published comparisons are images only.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): 145 days after its cutoff
- Claude Opus 5.5 (training cutoff June 2026): 84 days after its cutoff
- Gemini 4 Argon (training cutoff March 2026): 175 days after its cutoff
- Grok 4.7 (training cutoff May 2026): 114 days after its cutoff

## Sources

1. [Hugging Face: inclusionAI/Ming-Image-0.1-Design](https://huggingface.co/inclusionAI/Ming-Image-0.1-Design) (huggingface.co, official)
2. [Hugging Face: inclusionAI/Ming-Image-0.1-Design-Layer](https://huggingface.co/inclusionAI/Ming-Image-0.1-Design-Layer) (huggingface.co, official)
3. [DataNorth: Ant Group releases Ming-Image-0.1-Design](https://datanorth.ai/news/ant-group-releases-ming-image-0-1-design) (datanorth.ai, press)
4. [ComfyUI Wiki: Ming-Image 0.1 Design, 6B UI and poster model in ComfyUI](https://comfyui-wiki.com/news/2026-09-23-ming-image-design) (comfyui-wiki.com, discussion)

## Changes

- 2026-10-14 (filed): Created from model card, HF API metadata, DataNorth and ComfyUI Wiki read

## Related

- 2026-09-29: [Ant Group's inclusionAI launches Ling 3.1 Flash, a 560B-parameter MoE, as a free trial with open weights promised](https://postcutoff.com/e/2026-09-29-ant-inclusionai-ling-3-1-flash/index.md)