# 蚂蚁 inclusionAI 发布 Ming-Image-0.1-Design：6B 文本生图模型，支持透明背景

- 来源：蚂蚁 inclusionAI：HuggingFace 新模型
- 发布时间：2026-09-17 15:17
- AIHOT 分数：48
- AIHOT 链接：https://aihot.news/items/cmucupk940p2vroeddl8ac66x
- 原文链接：https://huggingface.co/inclusionAI/Ming-Image-0.1-Design

## AI 摘要

蚂蚁 inclusionAI 在 HuggingFace 发布 6B 文本到图像模型 Ming-Image-0.1-Design，面向 UI、信息图、海报等文字密集的视觉设计，可生成完整画面并支持 RGBA 透明背景输出。

## 正文

Ming-Image-0.1-Design is a 6B text-to-image model for UI, infographics, posters, and other text-rich visual designs. It generates complete visual compositions and supports RGBA output with transparent backgrounds.

UI/UX Design leaderboard

Quick Start

Use the companion Ming-Image repository for installation and inference:

git clone https://github.com/inclusionAI/Ming-Image cd Ming-Image pip install -r requirements.txt

python infer.py \ --model inclusionAI/Ming-Image-0.1-Design \ --task text-to-image \ --prompt assets/t2i_four_seasons_cabin_prompt.json \ --resolution 2048 \ --output-dir outputs/t2i

Prompt enhancement (PE) can use Ling-3.0-flash-VL or qwen3.8-27B; see text-to-image prompt rewriting.

Transparent-background generation

For transparent-background generation, prepend exactly one of the recommended RGBA phrases. See the transparent-background generation tip.

Deployment

We recommend the following inference frameworks to serve the model:

vLLM-Omni: see the recipes and installation guide.

Recommended settings

Resolution: 2048 x 2048 (recommended), or 1024 x 1024 for faster generation.

Sampling steps: 12.

CFG scale: 1.0.

Precision: BF16.

Hardware: one CUDA GPU with 80 GiB VRAM (validated configuration).

The public inference code maps text-to-image resolution requests to the supported 1024 or 2048 bucket.

Gallery

Text-to-image

Transparent-background text-to-image

The checkerboard is used only to preview transparency; it is not part of the generated RGBA images.

License

This model is released under the MIT License.