{"apiVersion":"v1","taxonomyVersion":1,"generatedAt":"2026-10-29T15:49:51.639Z","data":{"id":"wsa_qvwnbgtnpbx6","versionId":"ver_P5pfalkXjiyW","versionNumber":3,"title":"PixelUMM","maker":"NVIDIA","publisher":"NVIDIA","summary":"PixelUMM is an encoder-free multimodal model for understanding and generation across text, images, and video directly in pixel space. It accepts text, RGB images, and video frames, and produces text, RGB images, and video frames.","utility":"Researchers and developers can use PixelUMM to study unified multimodal modeling, generate images or video from text prompts, and produce text conditioned on images or video.","classifications":{"developmentType":"model","capability":["text generation","image generation","video generation","analysis"],"modality":["text","image","video","multimodal"],"access":["open weights"],"deployment":["on-premises"],"pricing":["unknown"],"targetUser":["researcher","developer"]},"attributes":{"availability":"Released checkpoint on Hugging Face","pricingModel":null,"deployment":"Requires Linux, an NVIDIA GPU, CUDA build of PyTorch, and FlashAttention","privacy":null,"licence":"NVIDIA One-Way Noncommercial License; use limited to non-commercial research or evaluation"},"score":0.883,"confidence":"high","capped":false,"correctionState":"current","publicationState":"published","lowConfidence":false,"eligibleForDerivedResults":true,"publishedAt":"2026-10-01T21:40:34.000Z","collectedAt":"2026-10-02T08:40:13.445Z","lastVerifiedAt":"2026-10-27T01:06:35.726Z","versionEffectiveAt":"2026-10-15T20:00:59.740Z","taxonomyVersion":1,"rubricVersion":"evidence-rubric-1","jevVersion":"typesafe/jev-1.13-20260917","webUrl":"https://wowsuchai.withglint.app/records/wsa_qvwnbgtnpbx6"},"nextCursor":null,"license":{"catalog":{"name":"CC BY 4.0","spdx":"CC-BY-4.0","url":"https://creativecommons.org/licenses/by/4.0/","attribution":"wowsuchai","attributionUrl":"https://wowsuchai.withglint.app","covers":["catalog metadata","classifications","generated summaries","feed event metadata"]},"excluded":{"covers":["source quotations","linked source content"],"terms":"Not licensed by wowsuchai. Source quotations and linked source content keep their original rights."}}}