by inclusionAI
Open-weights 6B text-to-image model for UI, infographics and posters, with 2K output and RGBA transparency.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
Ming-Image-0.1-Design is a 6B-parameter text-to-image model from inclusionAI, aimed at text-rich visual design such as UI mockups, infographics and posters. It generates complete compositions and can output RGBA images with transparent backgrounds. Per the model card, it is listed on a UI/UX Design leaderboard; creators reported it ranked first among open-weights models on the Artificial Analysis UI/UX leaderboard.
Weights are published on Hugging Face under the MIT license. Inference runs through the companion Ming-Image GitHub repository (infer.py), and vLLM-Omni is recommended for serving. Recommended settings are 2048x2048 (or 1024x1024 for speed), 12 sampling steps, CFG scale 1.0 and BF16 precision. Transparent output requires prepending one of the recommended RGBA phrases to the prompt.
The validated hardware configuration is a single CUDA GPU with 80 GiB VRAM, so local use needs a large GPU. Prompt enhancement can use Ling-3.0-flash-VL or Qwen models. A companion Design Layer model, mentioned by creators, splits flat designs into layers; it is not described on the provided model card. A Hugging Face Space demo is linked.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Open 6B text-to-image model for visual design (UI, infographics, posters) with 2K output and alpha transparency; a companion Design Layer model splits flat designs into layers. Ranked first among open weights on Artificial Analysis UI/UX leaderboard, MIT license.
Closest neighbours by meaning, not just by category.
Model · inclusionAI
Open-weights 6B unified text-to-image and instruction-based image editing model family from inclusionAI.
Model · Princeton
Fully open 3B text-to-image diffusion model from Princeton with released weights, training code, and data pipeline.
Model
Open-weights 6B text-to-image model family from Alibaba's Tongyi-MAI lab, with a fast 8-step Turbo variant.
Model · OpenMOSS
Open-weights 5B text-to-image model family from OpenMOSS with native JSON bounding-box layout control and text rendering.
Model · OpenAI
OpenAI's image generation model, accessed via the API and ChatGPT, supporting text prompts and reference images.
Model · Ideogram
Ideogram's open image model with text rendering and transparent backgrounds, available via the Ideogram app and API.