Ming-Image-0.1-Design Text Encoder

The original text encoder of inclusionAI's Ming-Image-0.1 (Ling-mini-2.0)

What it is

• The model that reads your prompt for Ming-Image-0.1-Design: Ling-mini-2.0, a mixture-of-experts language model with 16.3B parameters, 1.4B of them active per token

• w4a8, 12.8 GB: the version that runs beside the int8 Ming model on an 8 GB card with 32 GB of RAM

Bigger versions

Comfy-Org also publishes this encoder in int8 convrot (19.5 GB) and bf16 (36.7 GB): https://huggingface.co/Comfy-Org/Ming-Image

No abliteration needed

Ming-Image-0.1 renders nudity with this original encoder: https://civarchive.com/models/2961185. Explicit sex acts are not in the base model.

Works with

• Ming-Image-0.1-Design, whose files are on Civitai here: https://civarchive.com/models/2961185

• The Ming-Image-0.1 VAE: https://civarchive.com/models/2961357

• Not Ming-Image-0.1-Design-Layer, which has its own encoder files

Install

• Put it in ComfyUI/models/text_encoders/ and load it with the Load CLIP node: ComfyUI recognises it from its weights, whatever the type says

• Needs ComfyUI with native Ming Image support: the main branch from 24 September 2026, or the next release

About the images

Rendered with Ming-Image-0.1-Design (int8 convrot, 12 steps, cfg 1, 832x1248) and this encoder. Each prompt tests something the encoder has to get right: text in English and Chinese, counts, placement, several people with their own clothes, posters and app screens.

中文：Ming-Image-0.1 原版文本编码器（Ling-mini-2.0，MoE 结构，总参数 163 亿，每个 token 激活 14 亿），未经修改，w4a8 版本（12.8 GB），与 Comfy-Org 发布的文件逐字节一致，8G 显存加 32G 内存即可运行。放入 ComfyUI/models/text_encoders/，用 Load CLIP 节点加载。需要原生支持 Ming 的 ComfyUI。MIT 许可。

License

MIT, Copyright (c) 2026 inclusionAI.