{"id":11966,"date":"2026-11-17T11:00:51","date_gmt":"2026-11-17T02:00:51","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/?p=11966"},"modified":"2026-11-17T11:10:00","modified_gmt":"2026-11-17T02:10:00","slug":"nvidia-releases-kimodo-soma-rp-v1-2","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/nvidia-releases-kimodo-soma-rp-v1-2\/","title":{"rendered":"NVIDIA Releases Kimodo-SOMA-RP-v1.2 for 3D Motion Generation"},"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\/nvidia\/Kimodo-SOMA-RP-ArdyRep-v1.2\">nvidia\/Kimodo-SOMA-RP-ArdyRep-v1.2<\/a><\/td>\n<\/tr>\n<tr>\n<td>Publisher guide<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/publisher-nvidia-en\/\">NVIDIA: models and licenses<\/a><\/td>\n<\/tr>\n<tr>\n<td>Published<\/td>\n<td>2026-10-14<\/td>\n<\/tr>\n<tr>\n<td>License<\/td>\n<td>nvidia-open-model-license<\/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>NVIDIA has released &#8220;Kimodo-SOMA-RP-v1.2&#8221;, a diffusion model that generates 3D skeleton animations based on text prompts and detailed motion constraints. This model can generate 3D skeleton motions tailored to inputs such as text instructions, full-body poses, joint end-effector positions, movement trajectories, and waypoints.<\/p>\n<h2>Specifications<\/h2>\n<ul>\n<li>Architecture: Diffusion Model (Novel Two-Stage Transformer)<\/li>\n<li>Parameters: 282 M<\/li>\n<li>Output Specifications: 30 fps, up to 10 seconds (300 frames)<\/li>\n<li>Output Format Details:\n<ul>\n<li>Root Translation: 2D matrix (num_frames x 3) &#8211; Joint Rotations: 4D matrix (num_frames x 30 x 3 x 3)<\/li>\n<\/ul>\n<\/li>\n<li>Input Format Details:\n<ul>\n<li>Text: 1D string &#8211; Duration: 1D integer &#8211; Pose Constraints: 1D frame index for each constraint &#8211; Constrainable features include 3D joint positions, 3&#215;3 joint rotation matrices, 2D heading directions, 2D root positions, and more.<\/li>\n<\/ul>\n<\/li>\n<li>Supported Skeleton: 30-joint SOMA skeleton<\/li>\n<li>Training Data:\n<ul>\n<li>Bones Rigplay dataset (700 hours of motion capture data, text under 1 billion tokens)<\/li>\n<\/ul>\n<\/li>\n<li>License: NVIDIA Open Model License (reported to allow commercial use)<\/li>\n<\/ul>\n<h2>Performance and Quality<\/h2>\n<p>This v1.2 release fixes training splits. In the previous v1.1, some test data sequences leaked into the training set, meaning numbers on the Motion Generation Benchmark could not be fully compared with models trained on recommended splits. This leak has been removed in v1.2, making it a proper model for comparisons with other models on benchmarks.<\/p>\n<p>Regarding performance changes compared to v1.1, the model card reports the following. In v1.2, unnatural foot sliding (&#8220;foot skating&#8221;) is reduced, and constraint accuracy is maintained. Meanwhile, metrics indicating text adherence (R-precision and FID) are reported to be slightly lower than in v1.1, as a result of reflecting the removal of the data leak.<\/p>\n<h2>Strengths and Use Cases<\/h2>\n<p>This model aims to generate 3D human motion data for applications regardless of the user&#8217;s animation experience level. Specifically, the following use cases are anticipated:<\/p>\n<ul>\n<li>Humanoid robot demonstrations<\/li>\n<li>Digital human motions in digital twins and industrial simulations<\/li>\n<li>Digital human motion for synthetic data generation<\/li>\n<li>Animation creation in game and media development<\/li>\n<\/ul>\n<p>The model excels at locomotion, gestures, combat, dancing, and everyday actions. On the other hand, it is not designed to generate cartoon-like movements or physically unnatural motions, nor can it recognize surrounding objects to adjust its movements.<\/p>\n<h2>How It Differs from Similar Models<\/h2>\n<p>As a variation of this release, <a href=\"https:\/\/huggingface.co\/nvidia\/Kimodo-SOMA-RP-ArdyRep-v1.2\">nvidia\/Kimodo-SOMA-RP-ArdyRep-v1.2<\/a> has been published. This model is designed to predict the Ardy motion representation, outputting global roots and joint rotations using raw hip trajectories instead of the smoothed roots used in other Kimodo models. This enables direct interoperability with the <a href=\"https:\/\/github.com\/nv-tlabs\/ardy\">ARDY<\/a> model.<\/p>\n<p><!-- lmw:hardware --><\/p>\n<h2>Hardware Requirements<\/h2>\n<p><strong>Estimated requirements (calculated by Local Model Watch)<\/strong> \u2014 283M parameters<\/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>Your VRAM<\/th>\n<th>Quantization<\/th>\n<th>File size<\/th>\n<th>Est. memory needed<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>4GB (laptop iGPU \/ phone class)<\/td>\n<td>F32<\/td>\n<td>1.1GB<\/td>\n<td>1.3GB<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><em>Memory estimates add a 20% runtime overhead (KV cache, etc.) to the actual size of the distributed files. Actual usage varies with context length, batch size and inference engine. These figures are computed by this site from file sizes, not published by the model&#8217;s authors. The listed files are distributed in F32 (32-bit). Loading in a lower precision (BF16 or quantized) needs less memory, so treat this as the size of the files as distributed, not a minimum. This site has not measured the lower-precision figures. Compare with other models in our <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/vram-guide-en\/\">VRAM quick reference<\/a>. What the quantization names mean: <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/glossary-quantization-en\/\">glossary<\/a>.<\/em><\/p>\n<p><!-- \/lmw:hardware --><\/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>nvidia-open-model-license<\/code>:<\/strong> A custom license from the publisher. Check the original terms directly, including whether commercial use is permitted.<\/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:lab --><\/p>\n<h2>Our Own Measurements<\/h2>\n<h3>Measurements We Did Not Take<\/h3>\n<p>We have not confirmed that this site meets the commercial-use terms of this model&#8217;s license (<code>nvidia-open-model-license<\/code>). Because this site carries advertising, we did not run the model (no CPU run, answers, quantization comparison, conversion or generation).<\/p>\n<p><!-- \/lmw:lab --><\/p>\n<p><!-- lmw:files --><\/p>\n<h2>Distributed Files<\/h2>\n<p><em>Weight files published in <a href=\"https:\/\/huggingface.co\/nvidia\/Kimodo-SOMA-RP-v1.2\/tree\/main\">nvidia\/Kimodo-SOMA-RP-v1.2<\/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<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td><code>model.safetensors<\/code><\/td>\n<td>1.13GB<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><!-- \/lmw:files --><\/p>\n<h2>How to Get It<\/h2>\n<ul>\n<li>Distribution Format: safetensors<\/li>\n<li>Repository: <a href=\"https:\/\/huggingface.co\/nvidia\/Kimodo-SOMA-RP-v1.2\">nvidia\/Kimodo-SOMA-RP-v1.2<\/a><\/li>\n<li>Supported Tools: PyTorch<\/li>\n<\/ul>\n<p><!-- lmw:related --><\/p>\n<h2>Related Articles<\/h2>\n<ul>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/nvidia-releases-ardy-soma-rp-30fps-kimodorep-horizon60\/\">ARDY-SOMA-RP-30FPS-KimodoRep-Horizon60: File List<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/nvidia-dory-1-0-4b-recurrent-llm\/\">NVIDIA Releases Dory1.0-4B: A Recurrent 4B LLM with Dynamic Loops<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/nvidia-metrictrail-release\/\">MetricTrail: File List<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/nvidia-cosmos3-h-dreams-surgical-world-model\/\">Cosmos3-H-Dreams Video Generation Model: 48GB+ VRAM, File List<\/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>Find models by VRAM<\/strong> (This model runs from the 4GB tier) \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/vram-guide-8gb-en\/\">Other models that run on a 8GB GPU<\/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<li><strong>Learn about the publisher<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/publisher-nvidia-en\/\">NVIDIA: models, licenses and articles<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:next-steps --><\/p>\n<h2>Sources<\/h2>\n<ul>\n<li><a href=\"https:\/\/huggingface.co\/nvidia\/Kimodo-SOMA-RP-v1.2\"><a href=\"https:\/\/huggingface.co\/nvidia\/Kimodo-SOMA-RP-v1.2\">https:\/\/huggingface.co\/nvidia\/Kimodo-SOMA-RP-v1.2<\/a><\/a><\/li>\n<li><a href=\"https:\/\/huggingface.co\/nvidia\/Kimodo-SOMA-RP-ArdyRep-v1.2\"><a href=\"https:\/\/huggingface.co\/nvidia\/Kimodo-SOMA-RP-ArdyRep-v1.2\">https:\/\/huggingface.co\/nvidia\/Kimodo-SOMA-RP-ArdyRep-v1.2<\/a><\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Discover Kimodo-SOMA-RP-v1.2, an NVIDIA diffusion model for text-prompted and constrained 3D skeleton animation generation.<\/p>\n","protected":false},"author":1,"featured_media":11965,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[203],"tags":[3523,3525,3527,695,209,1547,1746],"class_list":["post-11966","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-image-video-and-audio","tag-3d-animation-en","tag-kimodo-en","tag-kimodo-soma-rp-v1-2-en","tag-nvidia-en","tag-safetensors-en","tag-verified","tag--en"],"lang":"en","translations":{"en":11966,"ja":11964},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/11966","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=11966"}],"version-history":[{"count":2,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/11966\/revisions"}],"predecessor-version":[{"id":17819,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/11966\/revisions\/17819"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media\/11965"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=11966"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/categories?post=11966"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/tags?post=11966"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}