{"id":13146,"date":"2026-11-17T11:02:07","date_gmt":"2026-11-17T02:02:07","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/?p=13146"},"modified":"2026-11-17T11:11:16","modified_gmt":"2026-11-17T02:11:16","slug":"tencent-releases-wevisone-vl-vision-language-models","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/tencent-releases-wevisone-vl-vision-language-models\/","title":{"rendered":"Tencent Releases WeVisOne-VL Vision Language Models"},"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\/tencent\/WeVisOne-VL-4B\">tencent\/WeVisOne-VL-4B<\/a><\/td>\n<\/tr>\n<tr>\n<td>Family guide<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/model-tencent-wevisone-vl-en\/\">WeVisOne-VL guide (2 articles)<\/a><\/td>\n<\/tr>\n<tr>\n<td>Publisher guide<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/publisher-tencent-en\/\">Tencent: models and licenses<\/a><\/td>\n<\/tr>\n<tr>\n<td>Published<\/td>\n<td>2026-10-22<\/td>\n<\/tr>\n<tr>\n<td>License<\/td>\n<td>apache-2.0<\/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>Tencent&#8217;s WeChat Vision team has released &#8220;WeVisOne-VL-4B&#8221; and &#8220;WeVisOne-VL-2B&#8221; as the &#8220;WeVisOne-VL&#8221; series of vision-language models, which integrate everything from object recognition in images to pixel-level processing.<\/p>\n<p>Developed based on Qwen3-VL, this model group achieves object-level recognition\u2014such as open-vocabulary object detection, referring localization, object counting, pointing, and OCR\u2014as well as pixel-level recognition, such as referring segmentation and promptable alpha matting, within a single framework.<\/p>\n<p>By combining structured next-token prediction with a lightweight pixel decoder of approximately 9.6M parameters (for the 4B version) or approximately 9.5M parameters (for the 2B version), it enables the processing of high-precision visual perception tasks.<\/p>\n<h2>Specifications<\/h2>\n<p>Based on the published model cards and repository configuration information, the specifications are as follows:<\/p>\n<ul>\n<li>Architecture: Qwen3VLForConditionalGeneration (based on Qwen3-VL)<\/li>\n<li>Pixel decoder (mask_decoder.pt) parameter count:<\/li>\n<li>WeVisOne-VL-4B: 9,609,764 parameters (approx. 9.6M) &#8211; WeVisOne-VL-2B: 9,511,460 parameters (approx. 9.5M)<\/li>\n<\/ul>\n<p>As part of the model&#8217;s internal structure, dedicated coordinate tokens are designed to represent normalized bounding boxes and coordinate points. It is specified to return &#8220;None&#8221; if the instructed target does not exist within the image, and for high-density prediction tasks, it outputs a dedicated instance identification token with token ID &#8220;152678&#8221; immediately after each prediction box.<\/p>\n<p>Additionally, the pixel decoder &#8220;mask_decoder.pt&#8221;, which is an essential component during inference, consists of the following three main components:<\/p>\n<ul>\n<li>Visual Feature Adapter: An adapter that integrates and adapts multi-level pre-merge ViT features from Qwen3-VL.<\/li>\n<li>Box-Guided Query Decoder: Equipped with six deformable cross-attention blocks initialized from the hidden states of instance identification tokens and Fourier-encoded bounding box priors.<\/li>\n<li>Instance-Conditioned Dense Prediction Head: Employs &#8220;FullCanvasAlphaCascadeHead&#8221;, which progressively refines predictions across S\/4, S\/2, and S\/1 resolution scales, outputting a smooth continuous alpha matte at full resolution with a stride of 1.<\/li>\n<\/ul>\n<p>As a design to enhance inference efficiency, this model group adopts an approach of directly generating structured outputs without explicit Chain-of-Thought (CoT). Furthermore, in the current revision, perception processing is targeted at single images, and video grid inputs are specified to be rejected on the pixel decoder side.<\/p>\n<h2>Strengths and Use Cases<\/h2>\n<p>The WeVisOne-VL series excels at consistently processing tasks ranging from accurately identifying objects in images through language instructions to pixel-level masks and cutouts (alpha matting).<\/p>\n<p>Strengths and functions indicated in the model cards and tag information are as follows:<\/p>\n<ul>\n<li>Open-vocabulary object detection<\/li>\n<li>Referring localization \/ referring expression comprehension<\/li>\n<li>Point grounding \/ object pointing<\/li>\n<li>Object counting<\/li>\n<li>OCR \/ OCR localization<\/li>\n<li>Referring expression segmentation<\/li>\n<li>Image matting \/ promptable alpha matting<\/li>\n<\/ul>\n<p>This model group is designed for research into advanced visual grounding tasks, such as high-precision cutout tasks for specific subjects based on instruction sentences (queries), locating objects that match natural language instructions, and counting quantities.<\/p>\n<p>On the other hand, the official model card also clearly states usage notes and limitations.<\/p>\n<p>First, it is not suitable for autonomous critical decision-making or purposes aimed at individual identification. It is released under the premise of research use.<\/p>\n<p>In addition, as a limitation in pixel-level processing, it is reported that the extraction accuracy of fine alpha boundaries (contour parts) is greatly affected by image resolution, extreme occlusion (the degree to which the subject is hidden), complex transparency, and the phrasing of the prompt. Furthermore, because it is configured to directly output structured data without Chain-of-Thought (CoT) to emphasize inference speed and efficiency, it is not suitable for processing involving complex multi-step logical reasoning. The current revision specializes in single-image perception tasks and does not support video grid inputs.<\/p>\n<p><!-- lmw:hardware --><\/p>\n<h2>Hardware Requirements<\/h2>\n<p><strong>Estimated requirements (calculated by Local Model Watch)<\/strong> \u2014 4.8B 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>Q5_K_S<\/td>\n<td>2.9GB<\/td>\n<td>3.5GB<\/td>\n<\/tr>\n<tr>\n<td>8GB (RTX 4060 \/ 3060 Ti, etc.)<\/td>\n<td>Q8_0<\/td>\n<td>4.4GB<\/td>\n<td>5.3GB<\/td>\n<\/tr>\n<tr>\n<td>12GB (RTX 4070 \/ 3060 12GB, etc.)<\/td>\n<td>F16<\/td>\n<td>8.2GB<\/td>\n<td>9.9GB<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><strong>Inference engine support<\/strong> (architecture name matched against each project&#8217;s own model registry in its source code, checked 2026-11-17): llama.cpp: registered, vLLM: registered, MLX (mlx-lm): registered.<\/p>\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. File sizes are measured from the converted build <a href=\"https:\/\/huggingface.co\/mradermacher\/WeVisOne-VL-4B-GGUF\">mradermacher\/WeVisOne-VL-4B-GGUF<\/a>. 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><strong>Runs in Ollama, LM Studio and llama.cpp via a converted build.<\/strong><\/p>\n<p>The publisher ships safetensors, but <a href=\"https:\/\/huggingface.co\/mradermacher\/WeVisOne-VL-4B-GGUF\">mradermacher\/WeVisOne-VL-4B-GGUF<\/a> provides a GGUF build you can use.<\/p>\n<p><strong>License \u2014 <code>apache-2.0<\/code> (Commercial use allowed):<\/strong> Permits commercial use, modification and redistribution. Redistribution requires including the license and stating changes; includes a patent grant.<\/p>\n<p><strong>Compression:<\/strong> the Q5_K_S build measures 5.16 bits per weight \u2014 about 32% the size of the original 16-bit weights, calculated by this site from the actual file sizes.<\/p>\n<p><em>Compiled by this site&#8217;s code from the published formats, converted builds we have found, and each engine&#8217;s own model registry. &#8220;Not found&#8221; means we have not seen such a build, not that none exists. 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:peers --><\/p>\n<h2>Recent Models in the Same Size Class<\/h2>\n<p><em>Models with <\/em><em>4\u201315B<\/em><em> parameters that Local Model Watch covered recently, listed by code from our article log for comparison. VRAM tiers are this site&#8217;s estimates; licenses are as stated on the model cards.<\/em><\/p>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<p class=\"lmw-table-hint\" style=\"margin:0 0 4px;font-size:0.85em;opacity:0.7;\">\u2192 Scroll horizontally to see all columns<\/p>\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Model<\/th>\n<th>Parameters<\/th>\n<th>Smallest VRAM tier<\/th>\n<th>License<\/th>\n<th>Our article<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>tencent\/Youtu-Parsing-Omni<\/td>\n<td>5.3B<\/td>\n<td>12GB<\/td>\n<td>youtu-parsing<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/tencent-youtu-parsing-omni\/\">Youtu-Parsing-Omni Omnimodal Analysis Model: 12GB+ VRAM<\/a> (2026-11-17)<\/td>\n<\/tr>\n<tr>\n<td>nvidia\/Muse-Spark-Open-816B-A42B-DFlash2<\/td>\n<td>4.4B<\/td>\n<td>12GB<\/td>\n<td>nvidia-open-model-agreement-license<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/nvidia-muse-spark-open-816b-a42b-dflash2-2\/\">Muse-Spark-Open-816B-A42B-DFlash2 Vision-Language Model: 12GB+ VRAM<\/a> (2026-11-17)<\/td>\n<\/tr>\n<tr>\n<td>inclusionAI\/ZwZ2-9B-GGUF<\/td>\n<td>9.4B<\/td>\n<td>8GB<\/td>\n<td>apache-2.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/zwz2-9b-gguf-released\/\">ZwZ2-9B-GGUF Vision-Language Model: 8GB+ VRAM<\/a> (2026-11-17)<\/td>\n<\/tr>\n<tr>\n<td>inclusionAI\/ZwZ2-4B-GGUF<\/td>\n<td>4.5B<\/td>\n<td>4GB<\/td>\n<td>apache-2.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/zwz2-4b-gguf-released\/\">ZwZ2-4B-GGUF Vision-Language Model: 4GB+ VRAM<\/a> (2026-11-17)<\/td>\n<\/tr>\n<tr>\n<td>microsoft\/Mage-VL-Cowork<\/td>\n<td>4.7B<\/td>\n<td>12GB<\/td>\n<td>apache-2.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/microsoft-mage-vl-cowork-hybrid-agent\/\">Mage-VL-Cowork Vision-Language Model: 12GB+ VRAM, GGUF Builds<\/a> (2026-11-17)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><!-- \/lmw:peers --><\/p>\n<h2>How to Get It<\/h2>\n<p>The model weights for WeVisOne-VL are available on Hugging Face. They are distributed in safetensors format, provided along with additional pixel decoder weights (mask_decoder.pt). Because it is not a gated model, it can be downloaded and used without prior application or consent procedures. The Apache-2.0 license is applied.<\/p>\n<p>To run inference, you need to install the dedicated inference package from the official GitHub repository. After installation, you can load the model and execute tasks using a Python script like the following.<\/p>\n<p>An example code when using WeVisOne-VL-4B is as follows:<\/p>\n<pre><code class=\"language-python\">from PIL import Image\nfrom wevisone_vl import WeVisOneVL\n\nmodel = WeVisOneVL(&quot;tencent\/WeVisOne-VL-4B&quot;, device=&quot;auto&quot;, dtype=&quot;bfloat16&quot;)\nimage = Image.open(&quot;example.jpg&quot;).convert(&quot;RGB&quot;)\nresult = model.predict(image, task=&quot;matting&quot;, query=&quot;person&quot;, temperature=0.0)\nprint(result.response, len(result.masks))\n<\/code><\/pre>\n<p>If you want to use a lighter model, you can run it similarly by switching the model identifier to &#8220;tencent\/WeVisOne-VL-2B&#8221;.<\/p>\n<pre><code class=\"language-python\">from PIL import Image\nfrom wevisone_vl import WeVisOneVL\n\nmodel = WeVisOneVL(&quot;tencent\/WeVisOne-VL-2B&quot;, device=&quot;auto&quot;, dtype=&quot;bfloat16&quot;)\nimage = Image.open(&quot;example.jpg&quot;).convert(&quot;RGB&quot;)\nresult = model.predict(image, task=&quot;matting&quot;, query=&quot;person&quot;, temperature=0.0)\nprint(result.response, len(result.masks))\n<\/code><\/pre>\n<p><!-- lmw:variants --><\/p>\n<h2>Quantized and Converted Variants<\/h2>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<p class=\"lmw-table-hint\" style=\"margin:0 0 4px;font-size:0.85em;opacity:0.7;\">\u2192 Scroll horizontally to see all columns<\/p>\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Added<\/th>\n<th>Publisher<\/th>\n<th>Format<\/th>\n<th>Repository<\/th>\n<th>Smallest VRAM tier (build, est. memory)<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>2026-11-17<\/td>\n<td>mradermacher<\/td>\n<td>GGUF<\/td>\n<td><a href=\"https:\/\/huggingface.co\/mradermacher\/WeVisOne-VL-4B-GGUF\">mradermacher\/WeVisOne-VL-4B-GGUF<\/a><\/td>\n<td>Q5_K_S 3.5GB (fits in 4GB VRAM)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>File sizes of each build:<\/p>\n<ul>\n<li>Available builds in mradermacher\/WeVisOne-VL-4B-GGUF: Q2_K 1.7GB \/ Q3_K_S 1.9GB \/ Q3_K_M 2.1GB \/ Q3_K_L 2.2GB \/ IQ4_XS 2.3GB \/ Q4_K_S 2.4GB \/ Q4_K_M 2.5GB \/ Q5_K_S 2.9GB \/ Q5_K_M 2.9GB \/ Q6_K 3.4GB \/ Q8_0 4.4GB \/ F16 8.2GB<\/li>\n<\/ul>\n<p>In addition, 3 converted build(s) from other uploaders exist on Hugging Face; this site lists only builds from the model&#8217;s publisher or established quantization maintainers.<\/p>\n<p><em>This section is appended automatically by Local Model Watch when a converted build of this model appears after publication. Memory figures are estimated from the size of the distributed files. What the quantization names mean: <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/glossary-quantization-en\/\">glossary<\/a>.<\/em><\/p>\n<p><!-- \/lmw:variants --><\/p>\n<p><!-- lmw:related --><\/p>\n<h2>Related Articles<\/h2>\n<ul>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/18\/tencent-releases-wevisdoc-document-parsing-models\/\">Tencent Releases WeVisDoc-2B and WeVisDoc-4B Document Parsing Models<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/tencent-releases-dspine-parallel-draft-model\/\">Qwen3-8B-DSpine-b16: 4GB+ VRAM<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/tencent-qwen3-8-27b-dspine-b16\/\">Qwen3.8-27B-DSpine-b16 Draft Model for Speculative Decoding: 8GB+ VRAM<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/hy-memory-30b-a3b-2\/\">Hy-Memory-30B-A3B Text Generation Model: 12GB+ VRAM, GGUF Builds<\/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>Explore the same model family<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/model-tencent-wevisone-vl-en\/\">WeVisOne-VL family overview (2 articles, 1 converted builds)<\/a><\/li>\n<li><strong>Engines that run this model<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-llama-cpp-en\/\">llama.cpp<\/a> \/ <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-ollama-en\/\">Ollama<\/a> \/ <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-vllm-en\/\">vLLM<\/a><\/li>\n<li><strong>What Q5_K_S, Q8_0 mean and where to get this model<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/format-gguf-en\/\">GGUF format guide and models<\/a> \/ <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/glossary-quantization-en\/\">Quantization and model-format glossary<\/a><\/li>\n<li><strong>Learn about the publisher<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/publisher-tencent-en\/\">Tencent: 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\/tencent\/WeVisOne-VL-4B\">tencent\/WeVisOne-VL-4B (Hugging Face)<\/a><\/li>\n<li><a href=\"https:\/\/huggingface.co\/tencent\/WeVisOne-VL-2B\">tencent\/WeVisOne-VL-2B (Hugging Face)<\/a><\/li>\n<li><a href=\"https:\/\/github.com\/Tencent\/WeVisOne-VL\">Tencent\/WeVisOne-VL (GitHub)<\/a><\/li>\n<\/ul>\n<p><!-- lmw:updates --><\/p>\n<h2>Update History<\/h2>\n<ul>\n<li>2026-11-17: Added converted builds to \u201cQuantized and Converted Variants\u201d: mradermacher\/WeVisOne-VL-4B-GGUF<\/li>\n<li>2026-11-17: Updated the hardware requirements table with the actual file sizes of mradermacher\/WeVisOne-VL-4B-GGUF.<\/li>\n<\/ul>\n<p><!-- \/lmw:updates --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Tencent&#8217;s WeChat Vision team has released WeVisOne-VL-4B and WeVisOne-VL-2B, integrating object recognition and pixel-level processing.<\/p>\n","protected":false},"author":1,"featured_media":13145,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[310],"tags":[1494,1172,1547,1952,4037,4039],"class_list":["post-13146","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-new-models","tag-qwen3-vl-en","tag-tencent-en","tag-verified","tag-vlm-en","tag-wevisone-vl-en","tag--en"],"lang":"en","translations":{"en":13146,"ja":13144},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/13146","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=13146"}],"version-history":[{"count":3,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/13146\/revisions"}],"predecessor-version":[{"id":17919,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/13146\/revisions\/17919"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media\/13145"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=13146"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/categories?post=13146"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/tags?post=13146"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}