<h2 id="ming-image">Ming-Image</h2><p>Ming Image 0.1 Design by inclusionAI (MIT), packaged by Comfy-Org for ComfyUI: photorealistic, uncensored out of the box, and it writes clean text.</p><h3 id="what-it-does-well">What it does well</h3><ul><li><p>Photographic nudes and portraits with natural skin texture, no LoRA needed</p></li><li><p>About 20 seconds per image at 1 megapixel on an 8 GB card with the int8 file</p></li><li><p>Clean typography on posters, covers and labels, in English and Chinese</p></li><li><p>Also anime and painted illustration</p></li><li><p>Plain-caption prompts: who, what she does, where, the light</p></li></ul><h3 id="which-file">Which file</h3><ul><li><p>8 GB cards and up: int8 convrot, 6.2 GB, the default</p></li><li><p>bf16, 12.3 GB: full precision, for merging and training</p></li></ul><h3 id="settings">Settings</h3><p>12 steps, cfg 1, euler, simple, about 1 megapixel (832x1248 or 1024x1024), the size the model is tuned for; 2048 px also works. The text encoder (ming_image_0.1_ling_mini_2.0_w4a8, 12.8 GB, in models/text_encoders) and the VAE (ming_image_vae_bf16, in models/vae) are both on this page. Needs a ComfyUI build with native Ming Image support: the main branch from 24 September 2026, or the next release.</p><h3 id="notes">Notes</h3><ul><li><p>The negative prompt does nothing at cfg 1</p></li><li><p>Nudity renders out of the box; explicit sex acts do not yet, the base has not learned them</p></li><li><p>The current files are Comfy-Org's, future release will include fine tuning</p></li></ul><p>Don't use it on real people.</p><p>中文：基于 inclusionAI 的 Ming Image 0.1 Design（MIT 许可），由 Comfy-Org 打包的原版文件：开箱即可生成写实裸体照片，文字渲染清晰。8G 显存用 int8 convrot（6.2 GB），bf16（12.3 GB）用于融合与训练。文本编码器（12.8 GB）和 VAE 也在本页。12 步，cfg 1，约 100 万像素。需要原生支持 Ming 的 ComfyUI。</p><h3 id="license">License</h3><p>MIT, Copyright (c) 2026 inclusionAI.</p>

Ming-Image-0.1-Design (uncensored, ComfyUI) | 夜曲 ✨

<p>Ming Image 0.1 Design for ComfyUI: Comfy-Org's int8 convrot and bf16 files, </p><p>With the VAE and a workflow at 12 steps, cfg 1.</p>

mingImage01DesignUncensored_v10_3242150.safetensors

mingImage01DesignUncensored_v10_bf16.safetensors

mingImage01DesignUncensored_v10.json

mingImage01DesignUncensored_v10_int8.safetensors

mingImage01DesignUncensored_v10.txt

v1.0

<h2>Ming-Image-0.1-Design Text-to-Image Workflow</h2><p>A text-to-image workflow for inclusionAI's Ming-Image-0.1-Design in ComfyUI: core nodes only, runs on an 8 GB card.</p><h3>What you get</h3><ul><li>One clean graph in four groups: models, prompt, size, sample and save</li><li>ComfyUI offers to download the three model files if they are missing (Comfy-Org, Hugging Face)</li><li>The reference settings: 12 steps, cfg 1, euler, simple</li><li>A note in the graph with sizes, timings and prompting tips</li></ul><h3>Files it loads</h3><ul><li>ming_image_0.1_design_int8_convrot (6.2 GB) in models/diffusion_models, or the bf16 file (12.3 GB)</li><li>ming_image_0.1_ling_mini_2.0_w4a8 (12.8 GB) in models/text_encoders</li><li>ming_image_vae_bf16 (0.25 GB) in models/vae</li><li>The model files are also on Civitai: <a href="https://civarchive.com/models/2961185" rel="ugc">https://civarchive.com/models/2961185</a></li></ul><h3>Size and speed</h3><ul><li>1024 (about 1 megapixel: 1024x1024, 832x1248 or 1248x832): about 22 s per image on an RTX 4070 Laptop 8 GB</li><li>2048 (2048x2048, the size inclusionAI recommends): about 85 s on the same card</li></ul><h3>Prompting</h3><p>Write a plain caption: who or what, what happens, where, the light. Put any text to render in double quotes; English and Chinese both work. At cfg 1 the negative prompt does nothing.</p><h3>Needs</h3><p>ComfyUI with native Ming Image support: the main branch from 24 September 2026, or the next release. No custom nodes.</p><h3>About the images</h3><p>Made with this workflow, unchanged, at 832x1248. Drag any of them into ComfyUI to load it.</p><p>中文：Ming-Image-0.1-Design 的 ComfyUI 文生图工作流，只用核心节点，8G 显存可运行。缺少的模型文件 ComfyUI 会提示下载。12 步，cfg 1，euler，simple；1024 尺寸约 22 秒一张，2048 尺寸约 85 秒。需要原生支持 Ming 的 ComfyUI。</p><h3>License</h3><p>Workflow: MIT, noctaluna. Ming-Image-0.1: MIT, Copyright (c) 2026 inclusionAI.</p>

Ming-Image-0.1-Design Text-to-Image Workflow (ComfyUI)

<p>Text to image with Ming-Image-0.1-Design: core nodes, 12 steps, cfg 1, runs on 8 GB.</p>

Files with SHA256: 7f5bed402dc8c77dc2e0ab1929a85d4df433b7cf7b599dfa8c353da98db0b90a