inclusionAI/Ming-Image-0.1-Design — new model trending #30 on Hugging Face
inclusionAI releases Ming-Image-0.1-Design, a 6B MIT-licensed text-to-image model for UI, infographics, and posters with RGBA transparent-background output, trending on Hugging Face.
inclusionAI's Ming-Image-0.1-Design is a 6B text-to-image model specialized for UI design, infographics, posters, and other text-rich visuals, released under the MIT License and trending #30 on Hugging Face. It supports RGBA output with transparent backgrounds and generates at 1024 or 2048 resolution with 12 sampling steps, CFG 1.0, and BF16 precision on a single 80-GiB-VRAM CUDA GPU. Prompt enhancement can leverage Ling-3.0-flash-VL or qwen3.8-27B, and deployment is supported via vLLM-Omni.
- 6B text-to-image model targeted at UI, infographics, and text-rich designs
- MIT-licensed open weights with RGBA transparent-background generation support
- Runs on one 80 GiB VRAM CUDA GPU; deployable via vLLM-Omni
- Trending #30 on Hugging Face
Full article258 words · extracted from huggingface.co · click to collapse
# Ming-Image-0.1-Design
[🧩 ModelScope](https://www.modelscope.cn/models/inclusionAI/Ming-Image-0.1-Design) · [🤗 Hugging Face](https://huggingface.co/inclusionAI/Ming-Image-0.1-Design) · [📄 Blog](https://mp.weixin.qq.com/s/VGdtxfM8kbHIQJw50VD_Sw) · [🖥️ Demo](https://huggingface.co/spaces/hugging-apps/ming-image-0-1-design-demo)<br>
[🎨 Design Skill](https://github.com/inclusionAI/ling-cookbook/tree/main/resources/recommended-skills/ling-ui-design) · [📊 PPT Skill](https://github.com/inclusionAI/ling-cookbook/tree/main/resources/recommended-skills/image-to-editable-ppt)
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
<p align="center">
<img src="./assets/uiux_leaderboard.webp" width="100%" alt="Ming-Image-0.1-Design UI/UX Design leaderboard">
</p>
## Quick Start
Use the companion [Ming-Image repository](https://github.com/inclusionAI/Ming-Image)
for installation and inference:
```bash
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](https://github.com/inclusionAI/Ming-Image#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](https://github.com/inclusionAI/Ming-Image#transparent-background-generation-tip).
## Deployment
We recommend the following inference frameworks to serve the model:
- vLLM-Omni: see the [recipes](https://github.com/vllm-project/vllm-omni/blob/main/recipes/inclusionAI/Ming-Image.md)
and [installation guide](https://docs.vllm.ai/projects/vllm-omni/en/latest/getting_started/quickstart/).
## Recommended settings
- Resolution: **2048 x 2048** (recommended), or **1024 x 1024** for faster
generation.
- Sampling steps: **12**.