{"id":20141,"date":"2026-11-19T07:12:56","date_gmt":"2026-11-18T22:12:56","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/11\/19\/longcat-video-avatar-for-comfyui\/"},"modified":"2026-11-19T07:12:56","modified_gmt":"2026-11-18T22:12:56","slug":"longcat-video-avatar-for-comfyui","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/19\/longcat-video-avatar-for-comfyui\/","title":{"rendered":"LongCat-Video-Avatar: ComfyUI Paths"},"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\/LongCat-Video-Avatar\">Comfy-Org\/LongCat-Video-Avatar<\/a><\/td>\n<\/tr>\n<tr>\n<td>Published<\/td>\n<td>2026-11-19<\/td>\n<\/tr>\n<tr>\n<td>License<\/td>\n<td>mit<\/td>\n<\/tr>\n<tr>\n<td>Formats<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/format-safetensors-en\/\">safetensors<\/a><\/td>\n<\/tr>\n<tr>\n<td>Source type<\/td>\n<td>Primary source (the publisher itself)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><em>Values determined by this site&#8217;s code when the information was collected. Dates are JST.<\/em><\/p>\n<p><!-- \/lmw:facts --><\/p>\n<h2>Overview<\/h2>\n<p>Comfy-Org has released model files for &#8220;LongCat-Video-Avatar&#8221; compatible with ComfyUI. This model is an audio-driven video generation model that generates human videos based on audio input.<\/p>\n<p>The files provided in this repository are repackaged versions of <code>meituan-longcat\/LongCat-Video-Avatar-1.6<\/code> optimized for ComfyUI. By combining multiple inputs such as text, images, and audio, users can create avatar videos with natural lip-syncing.<\/p>\n<h2>Specifications<\/h2>\n<p>The main components included in this repository are as follows:<\/p>\n<ul>\n<li>Base model: <code>meituan-longcat\/LongCat-Video-Avatar-1.6<\/code><\/li>\n<li>Supported input\/output formats:\n<ul>\n<li>Audio-text-to-video &#8211; Audio-image-text-to-video &#8211; Audio-driven-video-continuation<\/li>\n<\/ul>\n<\/li>\n<li>Generated video specifications:\n<ul>\n<li>Supports single-character and multi-character generation. &#8211; Capable of generating long videos exceeding 10 minutes.<\/li>\n<\/ul>\n<\/li>\n<li>Main distributed files:\n<ul>\n<li>Diffusion model: <code>longcat-avatar-1.6_int8_convrot.safetensors<\/code> &#8211; Text Encoder: <code>umt5_xxl_fp16.safetensors<\/code>, <code>umt5_xxl_int8_convrot.safetensors<\/code> &#8211; VAE: <code>wan_2.1_vae.safetensors<\/code> &#8211; LoRA: <code>longcat-avatar-1.6_dmd_lora_rank128_bf16.safetensors<\/code>, <code>longcat-avatar-1.6_opsd_lora_rank128_bf16.safetensors<\/code><\/li>\n<\/ul>\n<\/li>\n<li>License: MIT License<\/li>\n<\/ul>\n<h2>Performance and Quality<\/h2>\n<p>Regarding the performance of the original model <code>LongCat-Video-Avatar-1.6<\/code>, the model card presents results from human evaluation experiments. In the &#8220;Human Preference Arena&#8221; based on 33,051 valid votes, comparisons were made with the following six systems:<\/p>\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>Model Name<\/th>\n<th>Evaluation Result<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>OmniHuman-2.0<\/td>\n<td>1st<\/td>\n<\/tr>\n<tr>\n<td>LongCat-Video-Avatar-1.6<\/td>\n<td>2nd (Bradley\u2013Terry Elo score: 1068.1)<\/td>\n<\/tr>\n<tr>\n<td>LongCat-Video-Avatar 1.5<\/td>\n<td>&#8211;<\/td>\n<\/tr>\n<tr>\n<td>HeyGen<\/td>\n<td>&#8211;<\/td>\n<\/tr>\n<tr>\n<td>OmniHuman-1.5<\/td>\n<td>&#8211;<\/td>\n<\/tr>\n<tr>\n<td>Kling Avatar 2.0<\/td>\n<td>&#8211;<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>In this evaluation, LongCat-Video-Avatar-1.6 fell short of OmniHuman-2.0, but scored higher than the previous version 1.5, HeyGen, OmniHuman-1.5, and Kling Avatar 2.0.<\/p>\n<p>Additionally, the model card reports the following quality improvements:<\/p>\n<ul>\n<li>Improved naturalness and stability of lip animation: Reduction of overly exaggerated or unnatural mouth movements, excessively red lip coloration, and temporal instability around the mouth.<\/li>\n<li>Stabilization of long-video generation: Suppression of error accumulation in autoregressive video continuation. This allows the generation of videos exceeding 10 minutes while maintaining visual quality, identity consistency, and temporal coherence.<\/li>\n<li>Accelerated inference: Optimization of the end-to-end pipeline and model execution enables more efficient deployment and serving.<\/li>\n<\/ul>\n<h2>Strengths and Use Cases<\/h2>\n<p>The original model <code>LongCat-Video-Avatar-1.6<\/code> specializes in audio-driven human (avatar) video generation. Specifically, it features the following use cases and characteristics:<\/p>\n<ul>\n<li><strong>Diverse Input Combinations<\/strong>: Can generate videos from audio and text only, or from a combination of audio, images, and text.<\/li>\n<li><strong>Video Continuation<\/strong>: Enables the continuation of existing videos (Video Continuation) using audio input.<\/li>\n<li><strong>Multi-Character Support<\/strong>: Supports animation generation for multiple characters as well as single characters.<\/li>\n<li><strong>Long Video Generation<\/strong>: Excels at creating long videos exceeding 10 minutes while maintaining visual quality and character consistency by suppressing error accumulation through autoregressive methods.<\/li>\n<li><strong>Natural Expression<\/strong>: Designed to enhance the naturalness of lip movements (lip-syncing) and the coordination of facial and body movements.<\/li>\n<\/ul>\n<p><!-- lmw:files --><\/p>\n<h2>Distributed Files<\/h2>\n<p><em>Weight files published in <a href=\"https:\/\/huggingface.co\/Comfy-Org\/LongCat-Video-Avatar\/tree\/main\">Comfy-Org\/LongCat-Video-Avatar<\/a>, listed by this site from the Hugging Face API. Sizes are the actual file sizes.<\/em><\/p>\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>File<\/th>\n<th>Size<\/th>\n<th>ComfyUI folder<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td><code>diffusion_models\/longcat-avatar-1.6_int8_convrot.safetensors<\/code><\/td>\n<td>15.97GB<\/td>\n<td><code>models\/diffusion_models\/<\/code><\/td>\n<\/tr>\n<tr>\n<td><code>loras\/longcat-avatar-1.6_dmd_lora_rank128_bf16.safetensors<\/code><\/td>\n<td>1.26GB<\/td>\n<td><code>models\/loras\/<\/code><\/td>\n<\/tr>\n<tr>\n<td><code>loras\/longcat-avatar-1.6_opsd_lora_rank128_bf16.safetensors<\/code><\/td>\n<td>1.26GB<\/td>\n<td><code>models\/loras\/<\/code><\/td>\n<\/tr>\n<tr>\n<td><code>text_encoders\/umt5_xxl_fp16.safetensors<\/code><\/td>\n<td>11.37GB<\/td>\n<td><code>models\/text_encoders\/<\/code><\/td>\n<\/tr>\n<tr>\n<td><code>text_encoders\/umt5_xxl_int8_convrot.safetensors<\/code><\/td>\n<td>5.69GB<\/td>\n<td><code>models\/text_encoders\/<\/code><\/td>\n<\/tr>\n<tr>\n<td><code>vae\/wan_2.1_vae.safetensors<\/code><\/td>\n<td>254MB<\/td>\n<td><code>models\/vae\/<\/code><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><em>The ComfyUI folder is shown only where the repository&#8217;s layout mirrors ComfyUI&#8217;s <code>models\/<\/code> directory.<\/em><\/p>\n<p><!-- \/lmw:files --><\/p>\n<h2>How to Get It<\/h2>\n<p>The files in this repository are used by placing them in the respective ComfyUI model folders.<\/p>\n<ul>\n<li><strong>Distribution Format<\/strong>: Provided in <code>safetensors<\/code> format.<\/li>\n<li><strong>Placement Paths<\/strong>:\n<ul>\n<li>Diffusion model: <code>ComfyUI\/models\/diffusion_models\/<\/code> &#8211; LoRA: <code>ComfyUI\/models\/loras\/<\/code> &#8211; Text Encoder: <code>ComfyUI\/models\/text_encoders\/<\/code> &#8211; VAE: <code>ComfyUI\/models\/vae\/<\/code><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>License agreement on Hugging Face is not required to use this model.<\/p>\n<p><!-- lmw:runnability --><\/p>\n<h2>Can You Run It Locally?<\/h2>\n<p>The publisher distributes this model as safetensors.<\/p>\n<p><strong>License \u2014 <code>mit<\/code> (Commercial use allowed):<\/strong> Permits commercial use, modification and redistribution, provided the copyright notice and license text are retained.<\/p>\n<p><em>Compiled by this site&#8217;s code from the published formats and the license field. License summaries are not legal advice \u2014 check the publisher&#8217;s original terms before relying on them.<\/em><\/p>\n<p><!-- \/lmw:runnability --><\/p>\n<p><!-- lmw:related --><\/p>\n<h2>Related Articles<\/h2>\n<ul>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/comfy-org-minimax-h3-image-released\/\">MiniMax-H3-Image 16-Megapixel Image Generation Model: 4GB+ VRAM<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/24\/comfy-org-ming-image-released\/\">Ming-Image UI Design-Specialized Image Generation Model: ComfyUI Paths<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/comfy-org-wevisone-vl-released-for-comfyui\/\">WeVisOne-VL Vision-Language Model: 8GB+ VRAM<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/comfy-org-releases-world-model-pan2-for-comfyui\/\">PAN2 World Model for Simulating Physical Changes: ComfyUI Paths<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:related --><\/p>\n<p><!-- lmw:next-steps --><\/p>\n<h2>What to Read Next<\/h2>\n<ul>\n<li><strong>Engines that run this model<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-comfyui-en\/\">ComfyUI<\/a><\/li>\n<li><strong>Formats this model is available in<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/format-safetensors-en\/\">Safetensors format guide and models<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:next-steps --><\/p>\n<h2>Sources<\/h2>\n<ul>\n<li><a href=\"https:\/\/huggingface.co\/Comfy-Org\/LongCat-Video-Avatar\">https:\/\/huggingface.co\/Comfy-Org\/LongCat-Video-Avatar<\/a><\/li>\n<li><a href=\"https:\/\/huggingface.co\/meituan-longcat\/LongCat-Video-Avatar-1.6\">https:\/\/huggingface.co\/meituan-longcat\/LongCat-Video-Avatar-1.6<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Comfy-Org has released LongCat-Video-Avatar model files for ComfyUI, enabling audio-driven human video generation.<\/p>\n","protected":false},"author":1,"featured_media":20140,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[203],"tags":[1142,677,5389,5391,209,1547,959,213],"class_list":["post-20141","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-image-video-and-audio","tag-comfy-org-en","tag-comfyui-en","tag-longcat-video-en","tag-longcat-video-avatar-en","tag-safetensors-en","tag-verified","tag--en"],"lang":"en","translations":{"en":20141,"ja":20139},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/20141","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=20141"}],"version-history":[{"count":0,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/20141\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media\/20140"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=20141"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/categories?post=20141"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/tags?post=20141"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}