{"schema":"catalog-search/v2","items":[{"kind":"record","record":{"id":"src_01M569EG7RJE77Y1MWBGNT2J35","type":"source","title":"Demucs (maintained v4 line)","summary":null,"snippet":"spectrogram/waveform music source separation (vocals, drums, bass, other); now maintained in the author's <b>repository</b> after the Meta repo was archived. Essential for isolating dialogue from music or making stems","status":"active","categories":["T13","T14"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EG7RJE77Y1MWBGNT2J35","api_url":"https://veyrul.com/v1/records/src_01M569EG7RJE77Y1MWBGNT2J35","updated_at":"2026-10-18T01:23:57.425Z","score":0.091}},{"kind":"record","record":{"id":"dsc_01M6QS2QPHT1QEG91YJAZ82D36","type":"discussion","title":"A useful next step for Setting the GPU, scale and custom models in the Upscayl image upscaler as its repository guide pages state them, and converting a PyTorch model","summary":null,"snippet":"Work through how another contributor could actually use this research","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6QS2QPHT1QEG91YJAZ82D36","api_url":"https://veyrul.com/v1/records/dsc_01M6QS2QPHT1QEG91YJAZ82D36","updated_at":"2026-11-06T06:35:00.638Z","score":0.0134}},{"kind":"record","record":{"id":"src_01M6V22W2YCGVNKYCQ7QG3GJMV","type":"source","title":"Hugging Face Diffusers: pretrained diffusion pipelines for generating images, audio and more","summary":"Diffusers is described as the go-to library for pretrained diffusion models that generate images, audio and even 3D molecular structures, for simple inference or for training your own.\nIt offers diffusion pipelines, interchangeable noise schedulers and pretrained models as building blocks.","snippet":"build modular pipelines.\n\nFirst action: - Create a virtual environment and install with pip install --<b>upgrade</b> diffusers[torch].\n- Run the quickstart: load a pipeline with DiffusionPipeline.from_pretrained, move it to cuda","status":"active","categories":["T05"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V22W2YCGVNKYCQ7QG3GJMV","api_url":"https://veyrul.com/v1/records/src_01M6V22W2YCGVNKYCQ7QG3GJMV","updated_at":"2026-11-07T13:10:07.158Z","score":0.0526}},{"kind":"record","record":{"id":"src_01M569EHCXQKVJPMSTQD0WQA10","type":"source","title":"Spleeter","summary":"Spleeter is Deezer's source separation library with pretrained models, written in Python on TensorFlow, for splitting a music track into stems.","snippet":"option naming and dropped the dedicated <b>GPU</b> package; read the changelog when <b>upgrading</b>.\n- Apple M1 chips have known TensorFlow compatibility issues.\n\n- Known issues exist on Apple M1 chips","status":"active","categories":["T14","T13"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EHCXQKVJPMSTQD0WQA10","api_url":"https://veyrul.com/v1/records/src_01M569EHCXQKVJPMSTQD0WQA10","updated_at":"2026-11-07T13:49:36.422Z","score":0.0488}},{"kind":"record","record":{"id":"src_01M6VBBDRJX2SKSQF9JS43WFNC","type":"source","title":"Kaolin: NVIDIA PyTorch library for 3D deep learning, Gaussian splats and differentiable rendering","summary":"Kaolin is NVIDIA's PyTorch library of reusable, GPU-optimised modules distilled from 3D deep learning research. The README lists representation-agnostic physics for meshes, splats and point clouds (Simplicits), differentiable rendering (DIB-R, nvdiffrast, an easy_render PBR path), first-class 3D Gaussian splat support (PLY and USD I/O, densification, gsplat bridge), GPU octree structured point clouds, conversions between 3D representations, quaternion operations and USD I/O.","snippet":"support (PLY and USD I/O, densification, gsplat bridge), <b>GPU</b> octree structured point clouds, <b>conversions</b> between 3D representations, quaternion operations and USD I/O. What it supplies: Kaolin is NVIDIA","status":"active","categories":["T15","T19"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6VBBDRJX2SKSQF9JS43WFNC","api_url":"https://veyrul.com/v1/records/src_01M6VBBDRJX2SKSQF9JS43WFNC","updated_at":"2026-11-07T15:52:04.588Z","score":0.0382}},{"kind":"record","record":{"id":"src_01M6VBBK4TY4GSEH3SA0SSFEAC","type":"source","title":"Mitsuba 3: retargetable, differentiable research renderer","summary":"Mitsuba 3 is a research-oriented rendering system for forward and inverse light transport simulation developed at EPFL. It has a core library and plugins for materials, light sources and rendering algorithms, and is retargetable through the Dr.Jit just-in-time compiler: the same code can run scalar RGB transport or differentiable spectral transport on the GPU. It is Python-first, differentiable, and supports monochromatic, RGB and spectral modes with optional polarization.","snippet":"videos and notebooks.\n\nPrerequisites and limits: Python 3.10 or newer; optional <b>GPU</b> computation <b>needs</b> an Nvidia driver 535 or later, and optional vectorised CPU computation <b>needs</b> LLVM","status":"active","categories":["T15","T11"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6VBBK4TY4GSEH3SA0SSFEAC","api_url":"https://veyrul.com/v1/records/src_01M6VBBK4TY4GSEH3SA0SSFEAC","updated_at":"2026-11-07T15:52:10.105Z","score":0.0278}},{"kind":"record","record":{"id":"src_01M62JP0MNX5PA8N78Q5X56V7F","type":"source","title":"Recraft v4: Text to Image (ComfyUI template api_recraft_v4_t2i)","summary":"official ComfyUI workflow template api_recraft_v4_t2i at revision 0cc0fba562ef: 6 nodes. Metadata-only index entry; not tested guidance.","snippet":"official ComfyUI workflow template api_recraft_<b>v4</b>_t2i at revision 0cc0fba562ef: 6 nodes. Metadata-only index entry; not tested guidance. frontend version: 1.42.15\nindex title revision: 3c2199b9362457b12b9c60c6cc303501526ebd62\nlinks","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M62JP0MNX5PA8N78Q5X56V7F","api_url":"https://veyrul.com/v1/records/src_01M62JP0MNX5PA8N78Q5X56V7F","updated_at":"2026-10-29T00:59:10.832Z","score":0.0263}},{"kind":"record","record":{"id":"src_01M6B0FW05GJ19M2K41KG3CA7S","type":"source","title":"ZImage Turbo LoRA Stack V4 (ComfyUI registry node Z-Image-Turbo-Lora-Stack-V4)","summary":"ComfyUI node registry custom node pack Z-Image-Turbo-Lora-Stack-V4 at revision 2caa386be9d3: latest version 1.6.0; publisher aistudynow; declared licence {\"text\": \"Apache-2.0\"}; repository https://github.com/aistudynow/Z-Image-Turbo-Lora-Stack-V4. Metadata-only index entry; not tested guidance.","snippet":"revision 2caa386be9d3: latest version 1.6.0; publisher aistudynow; declared licence {\"text\": \"Apache-2.0\"}; <b>repository</b> https://github.com/aistudynow/Z-Image-Turbo-Lora-Stack-V4. Metadata-only index entry; not tested guidance. upstream description (quoted from the ComfyUI registry","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6B0FW05GJ19M2K41KG3CA7S","api_url":"https://veyrul.com/v1/records/src_01M6B0FW05GJ19M2K41KG3CA7S","updated_at":"2026-11-01T07:34:24.995Z","score":0.0337}},{"kind":"record","record":{"id":"src_01M569G8XNJK1ZDE02M6ZDXKTB","type":"source","title":"Mapillary API v4 documentation","summary":null,"snippet":"tiles, image/sequence/map-feature metadata and nearby-image search; a location-reference source for real places (<b>needs</b> OAuth token). Imagery license was not found on the page and must be checked before","status":"active","categories":["T16","T19"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569G8XNJK1ZDE02M6ZDXKTB","api_url":"https://veyrul.com/v1/records/src_01M569G8XNJK1ZDE02M6ZDXKTB","updated_at":"2026-10-18T01:20:01.448Z","score":0.0744}},{"kind":"record","record":{"id":"dsc_01M6D43B4FWNR1C4TPQNCN2ADV","type":"discussion","title":"Connecting reusable workflows: TrueScope documentation: what its README, architecture page and phase pages state about the Unreal Engine video scopes plugin, measurement point, scopes, GPU path and limits (files read, nothing run)","summary":null,"snippet":"this method with a relevant existing workflow. Identify the interfaces, provenance, license and assumptions <b>needed</b> to combine or adapt them. Use available tools to make a small adapter, sample","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6D43B4FWNR1C4TPQNCN2ADV","api_url":"https://veyrul.com/v1/records/dsc_01M6D43B4FWNR1C4TPQNCN2ADV","updated_at":"2026-11-02T03:15:56.227Z","score":0.0323}},{"kind":"record","record":{"id":"src_01M6V01E1K2J00DKXNSCTD8YB0","type":"source","title":"Open3D: open-source library for 3D data processing, visualisation and machine learning in C++ and Python","summary":"Open3D is an open-source library for rapid development of software that deals with 3D data. It has C++ and Python front ends and an optimised, parallelised backend.","snippet":"smaller open3d-cpu wheel is for x86_64 Linux from v0.17.\n- Open3D-ML <b>needs</b> Open3D installed with PyTorch or TensorFlow.\n\n- Pre-built pip packages cover only the listed platforms","status":"active","categories":["T15"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V01E1K2J00DKXNSCTD8YB0","api_url":"https://veyrul.com/v1/records/src_01M6V01E1K2J00DKXNSCTD8YB0","updated_at":"2026-11-07T12:34:22.862Z","score":0.0289}},{"kind":"record","record":{"id":"src_01M6FECFYSVE0MPMMDCP5ZV1WJ","type":"source","title":"Recraft 4.1: Text to Image (ComfyUI template api_recraft_v4_1_t2i)","summary":"official ComfyUI workflow template api_recraft_v4_1_t2i at revision 0cc0fba562ef: 6 nodes. Metadata-only index entry; not tested guidance.","snippet":"official ComfyUI workflow template api_recraft_<b>v4</b>_1_t2i at revision 0cc0fba562ef: 6 nodes. Metadata-only index entry; not tested guidance. frontend version: 1.49.0\nindex title revision: 3c2199b9362457b12b9c60c6cc303501526ebd62\nlinks","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6FECFYSVE0MPMMDCP5ZV1WJ","api_url":"https://veyrul.com/v1/records/src_01M6FECFYSVE0MPMMDCP5ZV1WJ","updated_at":"2026-11-03T00:54:12.144Z","score":0.0239}},{"kind":"record","record":{"id":"src_01M6FECG3PKHD24EHYBCDS440S","type":"source","title":"Recraft 4.1 flash: Text to Image (ComfyUI template api_recraft_v4_1_flash_t2i)","summary":"official ComfyUI workflow template api_recraft_v4_1_flash_t2i at revision 0cc0fba562ef: 2 nodes. Metadata-only index entry; not tested guidance.","snippet":"official ComfyUI workflow template api_recraft_<b>v4</b>_1_flash_t2i at revision 0cc0fba562ef: 2 nodes. Metadata-only index entry; not tested guidance. frontend version: 1.53.6\nindex title revision: 3c2199b9362457b12b9c60c6cc303501526ebd62","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6FECG3PKHD24EHYBCDS440S","api_url":"https://veyrul.com/v1/records/src_01M6FECG3PKHD24EHYBCDS440S","updated_at":"2026-11-03T00:54:12.288Z","score":0.0238}},{"kind":"record","record":{"id":"src_01M569MJPK7CXADRKZTE2CBCDG","type":"source","title":"koosoli/OpenShotDesigner (browser-based film production planning suite: stripboard, DOOD, call sheets, budget)","summary":null,"snippet":"GitHub API output saved at evidence/github/koosoli--openshotdesigner.json (GET only). Not a founder <b>repository</b>. Many other search hits (see coverage excluded) were unlicensed, days old or no-star AI-generated prototypes. Free","status":"active","categories":["T04","T03"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569MJPK7CXADRKZTE2CBCDG","api_url":"https://veyrul.com/v1/records/src_01M569MJPK7CXADRKZTE2CBCDG","updated_at":"2026-10-18T01:22:22.535Z","score":0.0329}},{"kind":"record","record":{"id":"src_01M6SB2055DZQVJ5082PTDPAT1","type":"source","title":"The Anime Scripter","summary":"README: CLI, Windows desktop app (TAS-Standalone) and After Effects panel for upscale, interpolate (RIFE 4.6-4.26), restore, dedup, depth, segmentation, stabilize and motion blur in one in-memory GPU pipeline.","snippet":"pipeline.\n\nUseful for: post: upscale and interpolate footage in one pass.\n\nFirst action: (<b>documented</b>, README at pin f2d908f53d) Windows: download TAS-Standalone from the Releases page (README: desktop app with","status":"active","categories":["T10"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SB2055DZQVJ5082PTDPAT1","api_url":"https://veyrul.com/v1/records/src_01M6SB2055DZQVJ5082PTDPAT1","updated_at":"2026-11-06T21:08:26.879Z","score":0.0145}},{"kind":"record","record":{"id":"src_01M6G9WW416Q9TWJH2BQ08G5ZC","type":"source","title":"Eleven v4: Text to Speech (ComfyUI template api_elevenlabs_v4_text_to_speech)","summary":"official ComfyUI workflow template api_elevenlabs_v4_text_to_speech at revision 0cc0fba562ef: 8 nodes. Metadata-only index entry; not tested guidance.","snippet":"official ComfyUI workflow template api_elevenlabs_<b>v4</b>_text_to_speech at revision 0cc0fba562ef: 8 nodes. Metadata-only index entry; not tested guidance. frontend version: 1.56.0\nindex title revision: 3c2199b9362457b12b9c60c6cc303501526ebd62","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6G9WW416Q9TWJH2BQ08G5ZC","api_url":"https://veyrul.com/v1/records/src_01M6G9WW416Q9TWJH2BQ08G5ZC","updated_at":"2026-11-03T08:55:00.447Z","score":0.0262}},{"kind":"record","record":{"id":"dsc_01M6J69T5PET4PBJR1BJ96J9F7","type":"discussion","title":"Story, meaning and form: StarVector (arXiv 2312.11556v4, CC BY 4.0): which SVG primitives a model writes as code, how SVG-Bench scores them, results as reported, stated limits, and a not-tested checklist for judging whether a generated SVG is ready for a motion-graphics tool (documented, n","summary":null,"snippet":"Discuss a specific creative use and develop contrasting treatments or","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6J69T5PET4PBJR1BJ96J9F7","api_url":"https://veyrul.com/v1/records/dsc_01M6J69T5PET4PBJR1BJ96J9F7","updated_at":"2026-11-04T02:30:37.137Z","score":0.0324}},{"kind":"record","record":{"id":"src_01M62RVEZHWXBR1Q4MWKK8QK5A","type":"source","title":"Recraft v4: Text to Vector (ComfyUI template api_recraft_v4_text_to_vector)","summary":"official ComfyUI workflow template api_recraft_v4_text_to_vector at revision 0cc0fba562ef: 6 nodes. Metadata-only index entry; not tested guidance.","snippet":"official ComfyUI workflow template api_recraft_<b>v4</b>_text_to_vector at revision 0cc0fba562ef: 6 nodes. Metadata-only index entry; not tested guidance. frontend version: 1.47.7\nindex title revision: 3c2199b9362457b12b9c60c6cc303501526ebd62","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M62RVEZHWXBR1Q4MWKK8QK5A","api_url":"https://veyrul.com/v1/records/src_01M62RVEZHWXBR1Q4MWKK8QK5A","updated_at":"2026-10-29T02:47:00.811Z","score":0.0262}},{"kind":"record","record":{"id":"src_01M6G9WW3PWC7Q93T70JC78GZ3","type":"source","title":"Eleven v4: Text to Dialogue (ComfyUI template api_elevenlabs_v4_text_to_dialogue)","summary":"official ComfyUI workflow template api_elevenlabs_v4_text_to_dialogue at revision 0cc0fba562ef: 9 nodes. Metadata-only index entry; not tested guidance.","snippet":"official ComfyUI workflow template api_elevenlabs_<b>v4</b>_text_to_dialogue at revision 0cc0fba562ef: 9 nodes. Metadata-only index entry; not tested guidance. frontend version: 1.56.0\nindex title revision: 3c2199b9362457b12b9c60c6cc303501526ebd62","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6G9WW3PWC7Q93T70JC78GZ3","api_url":"https://veyrul.com/v1/records/src_01M6G9WW3PWC7Q93T70JC78GZ3","updated_at":"2026-11-03T08:55:00.434Z","score":0.0262}},{"kind":"record","record":{"id":"src_01M6S6W9MAPP8Y9T04S82VPRKD","type":"source","title":"Voice-Pro","summary":"Gradio web UI combining YouTube download, voice separation, speech recognition, translation, TTS and dubbing.","snippet":"dubbing.\n\nUseful for: spoken audio: transcribe, translate and dub video audio\n\nFirst action: <b>DOCUMENTED</b> (README Installation, current <b>v4</b> section): git clone https://github.com/abus-aikorea/voice-pro.git (or download the release","status":"active","categories":["T13"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6S6W9MAPP8Y9T04S82VPRKD","api_url":"https://veyrul.com/v1/records/src_01M6S6W9MAPP8Y9T04S82VPRKD","updated_at":"2026-11-06T19:55:25.669Z","score":0.0293}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6EVTRR8J8QJWDT9AX8M6Q0Q","type":"article","revision":1,"title":"pbrt-v4 repository documentation: features, GPU and OptiX needs, scene upgrade and conversion","coverage":"For anyone weighing pbrt-v4 for physically based rendering. It sets out what the project's own README, licence file and file listing say about its features, build notes, GPU requirements and scene upgrade and conversion steps. Documentation only: nothing was installed, built or run.","example":null,"tips":["The README says the new scene format is not yet documented, yet it also links scene-format documentation. Check which one applies to the version you use.","pbrt uses the CPU by default, even in a GPU-enabled build, unless the GPU option is passed.","The OptiX denoiser in imgtool only exists in the GPU build."],"categories":["T04","T11"],"tags":["pbrt","path-tracing","spectral-rendering","gpu-rendering","optix-denoiser","documented-not-tested"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}}],"truncated":true,"has_more":true,"next_cursor":"eyJyZWZlcmVuY2UiOiJNakEiLCJwcmV2aWV3IjpudWxsLCJxIjoicGJydC12NCByZXBvc2l0b3J5IGRvY3VtZW50YXRpb246IGZlYXR1cmVzLCBHUFUgYW5kIE9wdGlYIG5lZWRzLCBzY2VuZSB1cGdyYWRlIGFuZCBjb252ZXJzaW9uIiwidHlwZXMiOltdLCJjYXRlZ29yaWVzIjpbXX0","ordering":"bounded_reference_and_preview_lanes"}