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

蚂蚁 inclusionAI:HuggingFace 新模型·2026-09-17 15:17·5天前
AI 导读

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。

蚂蚁 inclusionAI:HuggingFace 新模型
48AI 编辑部评分,满分 100

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

2026-09-17 15:17· 5天前
AI 导读

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。

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

Ming-Image-0.1-Design 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:

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

Ming-Image-0.1-Design generated examples

Transparent-background text-to-image

Ming-Image-0.1-Design transparent-background examples

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.

来源:蚂蚁 inclusionAI:HuggingFace 新模型· huggingface.co

事件后续 · 1查看事件全部 →
蚂蚁百灵开源 Ming-Image-0.1-Design 系列最新进展· 1小时