{"id":3112,"date":"2026-09-24T17:10:46","date_gmt":"2026-09-24T08:10:46","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/09\/24\/comfy-org-ming-image-released\/"},"modified":"2026-09-24T17:10:46","modified_gmt":"2026-09-24T08:10:46","slug":"comfy-org-ming-image-released","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/24\/comfy-org-ming-image-released\/","title":{"rendered":"Comfy-Org Releases Ming-Image for ComfyUI"},"content":{"rendered":"<p><!-- lmw:facts --><\/p>\n<h2>At a Glance<\/h2>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Item<\/th>\n<th>Value<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Repository<\/td>\n<td><a href=\"https:\/\/huggingface.co\/Comfy-Org\/Ming-Image\">Comfy-Org\/Ming-Image<\/a><\/td>\n<\/tr>\n<tr>\n<td>Published<\/td>\n<td>2026-09-24<\/td>\n<\/tr>\n<tr>\n<td>License<\/td>\n<td>mit<\/td>\n<\/tr>\n<tr>\n<td>Formats<\/td>\n<td>safetensors<\/td>\n<\/tr>\n<tr>\n<td>Source type<\/td>\n<td>Unverified (not confirmed by a primary source)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><em>Values determined by this site&#8217;s code at collection time. Dates are JST.<\/em><\/p>\n<p><!-- \/lmw:facts --><\/p>\n<h2>Overview<\/h2>\n<p>It is reported that Comfy-Org has released <code>Comfy-Org\/Ming-Image<\/code>, a repackaged version of <code>inclusionAI\/Ming-Image-0.1-Design<\/code> developed by inclusionAI, making it available for use in ComfyUI. This repository organizes text-to-image model files to match ComfyUI&#8217;s directory structure. Note that this information has not been officially confirmed at this time.<\/p>\n<h2>Specifications<\/h2>\n<p>The specifications of the base model <code>inclusionAI\/Ming-Image-0.1-Design<\/code> and the provided file structure are as follows.<\/p>\n<h3>Basic Specifications<\/h3>\n<ul>\n<li>Parameters: 6B<\/li>\n<li>Output Specifications:\n<ul>\n<li>Recommended Resolution: 2048 x 2048 &#8211; Fast Generation Resolution: 1024 x 1024 &#8211; Background: Supports RGBA (transparent background) output<\/li>\n<\/ul>\n<\/li>\n<li>Recommended Settings:\n<ul>\n<li>Sampling Steps: 12 &#8211; CFG Scale: 1.0 &#8211; Precision: BF16<\/li>\n<\/ul>\n<\/li>\n<li>Prompt Expansion (PE): Mentions the use of <code>Ling-3.0-flash-VL<\/code> or <code>qwen3.8-27B<\/code><\/li>\n<li>License: MIT<\/li>\n<\/ul>\n<h3>File Placement in ComfyUI<\/h3>\n<p>The repackaged files are intended to be placed in the following ComfyUI directories.<\/p>\n<ul>\n<li><code>models\/diffusion_models\/<\/code>: <code>ming_image_0.1_design_bf16.safetensors<\/code>, etc.<\/li>\n<li><code>models\/text_encoders\/<\/code>: <code>ming_image_0.1_ling_mini_2.0_bf16.safetensors<\/code>, etc.<\/li>\n<li><code>models\/vae\/<\/code>: <code>ming_image_vae_bf16.safetensors<\/code><\/li>\n<\/ul>\n<h2>Performance<\/h2>\n<p>According to the model card, this model is specialized for generating UIs, infographics, posters, and other visual designs containing heavy text. It is reported to have the capability of generating complete visual compositions rather than just individual elements. It also supports transparent background generation in RGBA format, allowing the generation of images with transparent backgrounds by prepending specific recommended RGBA phrases to the prompt.<\/p>\n<p>Specific benchmark scores or numerical comparisons with other models are not included in the provided materials.<\/p>\n<h2>Strengths and Use Cases<\/h2>\n<p>Based on the documentation for the original model <code>inclusionAI\/Ming-Image-0.1-Design<\/code>, this model is specialized not only for generating general photos and illustrations but also for creating graphic designs and UI\/UX designs that include text elements.<\/p>\n<p>Specifically, the following use cases and features are envisioned:<\/p>\n<ul>\n<li><strong>Generation of Text-Heavy Visual Designs<\/strong>:<br \/>\n  It is suitable for generating images where text and layout are crucial, such as posters, infographics, and various UI screens. The tag information also includes <code>graphic-design<\/code> and <code>text-rendering<\/code>, pointing to an expected output of complete visual compositions that balance visual and textual elements.<\/li>\n<li><strong>Transparent Background (RGBA) Image Output<\/strong>:<br \/>\n  It supports output in RGBA format containing an alpha channel in addition to standard RGB images. It is reported that by specifying certain recommended phrases at the beginning of the prompt, users can directly generate parts or graphic assets with transparent backgrounds. This omits post-processing background removal and can be directly utilized for asset creation in web design and presentation slides.<\/li>\n<li><strong>Integration with Design Assistance and Slide Creation Skills<\/strong>:<br \/>\n  The original model&#8217;s repository indicates the existence of recommended tools such as UI design skills (<code>ling-ui-design<\/code>) and skills to convert images into editable slides (<code>image-to-editable-ppt<\/code>), suggesting a practical workflow for prototyping presentation materials and screen layouts.<\/li>\n<\/ul>\n<p>It is reported that this package, <code>Comfy-Org\/Ming-Image<\/code>, repackages these features for easy handling within ComfyUI, a node-based GUI environment.<\/p>\n<h2>How to Get It<\/h2>\n<p>Model files for <code>Comfy-Org\/Ming-Image<\/code> are available from the corresponding Hugging Face repository. Since it is not a gated model, users can download it directly without prior agreement to terms of use.<\/p>\n<p>Provided weight files are distributed in <code>safetensors<\/code> format, subdivided by model type and precision. Files according to the intended use should be placed in the respective folders within the ComfyUI installation directory.<\/p>\n<p>The list of placement destinations and files specified in the model card is as follows:<\/p>\n<h3>Diffusion Model Placement Destination<\/h3>\n<p><code>ComfyUI\/models\/diffusion_models\/<\/code><br \/>\n&#8211; <code>ming_image_0.1_design_bf16.safetensors<\/code><br \/>\n&#8211; <code>ming_image_0.1_design_int8_convrot.safetensors<\/code><br \/>\n&#8211; <code>ming_image_0.1_design_layer_bf16.safetensors<\/code><br \/>\n&#8211; <code>ming_image_0.1_design_layer_int8_convrot.safetensors<\/code><\/p>\n<p>In addition to the standard BF16 precision model, quantized int8_convrot versions and layer versions supporting layer separation are available.<\/p>\n<h3>Text Encoder Placement Destination<\/h3>\n<p><code>ComfyUI\/models\/text_encoders\/<\/code><br \/>\n&#8211; <code>ming_image_0.1_ling_mini_2.0_bf16.safetensors<\/code><br \/>\n&#8211; <code>ming_image_0.1_ling_mini_2.0_int8_convrot.safetensors<\/code><br \/>\n&#8211; <code>ming_image_0.1_ling_mini_2.0_w4a8.safetensors<\/code><br \/>\n&#8211; <code>ming_image_0.1_ling_mini_2.0_layer_bf16.safetensors<\/code><br \/>\n&#8211; <code>ming_image_0.1_ling_mini_2.0_layer_int8_convrot.safetensors<\/code><\/p>\n<p>It is reported that multiple lightweight and quantized variants, such as int8_convrot and w4a8 versions in addition to BF16 precision, are available for the text encoder side.<\/p>\n<h3>VAE Placement Destination<\/h3>\n<p><code>ComfyUI\/models\/vae\/<\/code><br \/>\n&#8211; <code>ming_image_vae_bf16.safetensors<\/code><\/p>\n<p>Users will select the necessary precision combinations according to their environment and workflow, place them in the above folders, and load them in ComfyUI.<\/p>\n<p><!-- lmw:related --><\/p>\n<h2>Related Articles<\/h2>\n<ul>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/13\/comfy-org-yue2-comfyui-release\/\">Comfy-Org Releases YuE2 for ComfyUI: Open Music Generation<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:related --><\/p>\n<h2>Sources<\/h2>\n<ul>\n<li><a href=\"https:\/\/huggingface.co\/Comfy-Org\/Ming-Image\">Comfy-Org\/Ming-Image (Hugging Face)<\/a><\/li>\n<li><a href=\"https:\/\/huggingface.co\/inclusionAI\/Ming-Image-0.1-Design\">inclusionAI\/Ming-Image-0.1-Design (Hugging Face)<\/a><\/li>\n<li><a href=\"https:\/\/huggingface.co\/inclusionAI\/Ming-Image-0.1-Design-Layer\">inclusionAI\/Ming-Image-0.1-Design-Layer (Hugging Face)<\/a><\/li>\n<\/ul>\n<blockquote>\n<p><strong>This article contains unverified information.<\/strong> We will append an update note once it is confirmed by a primary source.<\/p>\n<\/blockquote>\n","protected":false},"excerpt":{"rendered":"<p>Comfy-Org has released Comfy-Org\/Ming-Image, repackaging inclusionAI&#8217;s Ming-Image-0.1-Design for ComfyUI. Learn specifications, file layout, and more.<\/p>\n","protected":false},"author":1,"featured_media":3111,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[203],"tags":[1142,2182,677,2184,2186,2188,209,1565],"class_list":["post-3112","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-image-video-and-audio","tag-comfy-org-en","tag-comfy-org-ming-image-en","tag-comfyui-en","tag-image-generation-en","tag-ming-image-en","tag-ming-image-0-1-design-en","tag-safetensors-en","tag-unverified"],"lang":"en","translations":{"en":3112,"ja":3110},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/3112","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/comments?post=3112"}],"version-history":[{"count":0,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/3112\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media\/3111"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=3112"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/categories?post=3112"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/tags?post=3112"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}