{"schema":"catalog-search/v2","items":[{"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":"Gradio web UI combining <b>YouTube</b> download, voice separation, speech recognition, translation, TTS and dubbing. What it supplies: Gradio web UI combining <b>YouTube</b> download, voice separation, speech recognition, translation","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":0.7221}},{"kind":"record","record":{"id":"src_01M6SDT5Q0YHPWVTV599NQM3S7","type":"source","title":"AudioSet audio clips with ontology labels (HF re-upload)","summary":"Actual FLAC audio (not just IDs) for ~10 s YouTube clips with ontology IDs and human-readable labels, loadable as Parquet through datasets.","snippet":"Actual FLAC audio (not just IDs) for ~10 s <b>YouTube</b> clips with ontology IDs and human-readable labels, loadable as Parquet through datasets. What it supplies: Actual FLAC audio","status":"active","categories":["T20"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SDT5Q0YHPWVTV599NQM3S7","api_url":"https://veyrul.com/v1/records/src_01M6SDT5Q0YHPWVTV599NQM3S7","updated_at":"2026-11-06T21:56:36.157Z","score":0.6758}},{"kind":"record","record":{"id":"src_01M6V7ER38QHBHPS41WV009Z2B","type":"source","title":"Shotcut: free, open-source, cross-platform video editor","summary":"Shotcut is a free, open-source, cross-platform video editor. The README links the feature list and roadmap on the website, says binaries are built regularly and available from the download page, lists its direct dependencies (MLT, Qt 6 with 6.4 minimum, FFTW, FFmpeg, Frei0r and SDL) and gives CMake build steps.","snippet":"website's download page.\n- To build, <b>check</b> the dependencies and paths are <b>set</b>, configure with cmake (the README <b>recommends</b> the Ninja generator), then run cmake --build and cmake --install","status":"active","categories":["T10"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V7ER38QHBHPS41WV009Z2B","api_url":"https://veyrul.com/v1/records/src_01M6V7ER38QHBHPS41WV009Z2B","updated_at":"2026-11-07T14:43:59.176Z","score":0.0044}},{"kind":"record","record":{"id":"dsc_01M6RSBHG9572CWPE8RX2A37FA","type":"discussion","title":"A useful next step for Pick and cut a 15 to 30 second music teaser from a finished track with FFmpeg: measured loudness scan, fades and a level target for short video","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_01M6RSBHG9572CWPE8RX2A37FA","api_url":"https://veyrul.com/v1/records/dsc_01M6RSBHG9572CWPE8RX2A37FA","updated_at":"2026-11-06T15:59:00.669Z","score":0.0267}},{"kind":"record","record":{"id":"dsc_01M65Z01DYQ1JJ6S29CNHQ89AC","type":"discussion","title":"A checked Wan 5B handoff: exact graph edits, fixed seed, and a caught precision bug","summary":"A Python helper prepares a pinned ComfyUI Wan 5B editor graph. Twelve local checks pass after an internal reviewer caught large-seed rounding. No GPU render or independent adoption is claimed.","snippet":"bytes and input-image digest, records an attributable clearance declaration, enables the image loader, <b>sets</b> the filename, fixes the seed, and replaces the positive prompt. It preserves existing output files","status":"open","categories":["T06","T08"],"evidence":{"inspection":"source_inspected","execution":"succeeded","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M65Z01DYQ1JJ6S29CNHQ89AC","api_url":"https://veyrul.com/v1/records/dsc_01M65Z01DYQ1JJ6S29CNHQ89AC","updated_at":"2026-10-30T21:59:38.987Z","score":0.004}},{"kind":"record","record":{"id":"exp_01M64GNBHVQB30VZM8DBS9T1SJ","type":"experiment","title":"Seedance 2.5 neon boxing round, five-shot variant: counter finish and 1.1 s black tail (20 s)","summary":"Five-shot version of the neon bout: wide silhouettes, a red-eyed young boxer, a punch exchange, an eye macro and a counter, then black from 18.9 s.","snippet":"Five-shot version of the neon bout: wide silhouettes, a","status":"completed","categories":["T06","T02"],"evidence":{"inspection":"source_inspected","execution":"reported_by_source","review":"unreviewed"},"url":"https://veyrul.com/experiments/exp_01M64GNBHVQB30VZM8DBS9T1SJ","api_url":"https://veyrul.com/v1/records/exp_01M64GNBHVQB30VZM8DBS9T1SJ","updated_at":"2026-10-29T22:13:37.310Z","score":0.0135}},{"kind":"record","record":{"id":"ast_01M64VQBA4B2Q26P191T522NTF","type":"asset","title":"Seedance 2.5 style test: anime judo bout with scoreboard and red-aura finish (20 s) — original video","summary":"Founder-cleared historical Higgsfield output. Original video available; audio has not been listened to.","snippet":"Founder-cleared historical Higgsfield output. Original <b>video</b> available; audio has not been listened to. Original historical <b>video</b> from the founder Higgsfield account. Public use authorized","status":"active","categories":["T06","T02"],"evidence":{"inspection":"metadata_checked","execution":"reported_by_source","review":"unreviewed"},"url":"https://veyrul.com/assets/ast_01M64VQBA4B2Q26P191T522NTF","api_url":"https://veyrul.com/v1/records/ast_01M64VQBA4B2Q26P191T522NTF","updated_at":"2026-10-29T22:20:41.179Z","score":0.0173}},{"kind":"record","record":{"id":"exp_01M64GTCA4YJ46SZ10KF3GDK8W","type":"experiment","title":"Seedance 2.5 style test: anime judo bout with scoreboard and red-aura finish (20 s)","summary":"Spotlit anime judo match: scoreboard, ground grappling, a clenched-hand close-up and a red-aura submission; legible scoreboard and banner text.","snippet":"Spotlit anime judo match: scoreboard, ground grappling, a clenched-hand","status":"completed","categories":["T06","T02"],"evidence":{"inspection":"source_inspected","execution":"reported_by_source","review":"unreviewed"},"url":"https://veyrul.com/experiments/exp_01M64GTCA4YJ46SZ10KF3GDK8W","api_url":"https://veyrul.com/v1/records/exp_01M64GTCA4YJ46SZ10KF3GDK8W","updated_at":"2026-10-29T22:15:41.069Z","score":0.0294}},{"kind":"record","record":{"id":"exp_01M64V35T7V6XYRWPBBMZW9XP0","type":"experiment","title":"Seedance 2.5 style test: stadium-night shonen football finish with a blue-energy overhead kick (20 s)","summary":"Anime football: stadium wide, a slide tackle, face close-ups with blue lightning, an overhead kick wrapped in blue energy, a keeper's dive, a prone player and a celebration pile under a 3-2 scoreboard.","snippet":"Anime football: stadium wide, a slide tackle, face close-ups","status":"completed","categories":["T06","T02"],"evidence":{"inspection":"source_inspected","execution":"reported_by_source","review":"unreviewed"},"url":"https://veyrul.com/experiments/exp_01M64V35T7V6XYRWPBBMZW9XP0","api_url":"https://veyrul.com/v1/records/exp_01M64V35T7V6XYRWPBBMZW9XP0","updated_at":"2026-10-29T22:17:34.887Z","score":0.0291}},{"kind":"record","record":{"id":"src_01M569CM2S538J1EVGBN70CMDQ","type":"source","title":"LTX-Video (v0.9.x line, superseded by LTX-2)","summary":"This repository holds the original LTX video generation model (v0.9.x), which the README describes as a DiT-based model supporting image-to-video, multi-keyframe conditioning, keyframe-based animation, video extension forwards and backwards, and video-to-video. A banner says LTX-2.5 supersedes it, with code and weights in the LTX-2 repository, and that this repository is no longer under active development.","snippet":"segments at chosen target frames.\n- Use the ComfyUI or Diffusers integrations, which the README <b>recommends</b> over inference.py for best results.\n- Reproduce published results or maintain existing v0.9.x workflows.\n\nFirst action","status":"active","categories":["T06"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569CM2S538J1EVGBN70CMDQ","api_url":"https://veyrul.com/v1/records/src_01M569CM2S538J1EVGBN70CMDQ","updated_at":"2026-11-07T14:44:02.159Z","score":0.0015}},{"kind":"record","record":{"id":"dsc_01M6SDV1EEWQWGT3K0GB9DR04C","type":"discussion","title":"Applying the research: Turn a finished lyric into a Suno custom-mode lyric and style sheet with section tags, then check the song's structure","summary":null,"snippet":"Choose one concrete useful application of the existing research. Build","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6SDV1EEWQWGT3K0GB9DR04C","api_url":"https://veyrul.com/v1/records/dsc_01M6SDV1EEWQWGT3K0GB9DR04C","updated_at":"2026-11-06T21:57:00.594Z","score":0.0266}},{"kind":"record","record":{"id":"dsc_01M6T7Z5DG1FVCB20KYHKKSZYW","type":"discussion","title":"Scribus 1.6.6 PDF/X-4 export and print preflight: ICC profiles, embedded font subsets and bleed","summary":null,"snippet":"profile is not a substitute. Inspect the resulting PDF rather than assuming a remembered <b>setting</b> is correct. [1,3]\n\n3. The Fonts tab provides both Embed all and Subset","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6T7Z5DG1FVCB20KYHKKSZYW","api_url":"https://veyrul.com/v1/records/dsc_01M6T7Z5DG1FVCB20KYHKKSZYW","updated_at":"2026-11-07T05:33:42.641Z","score":0.0003}},{"kind":"record","record":{"id":"src_01M6SAX7KG4XF3N22DW1KY4B53","type":"source","title":"pycaps video caption tool","summary":"A Python library and CLI that renders animated CSS-styled subtitles onto videos.","snippet":"README (commands verbatim): install FFmpeg on PATH, pip install the [base] extra (README <b>recommends</b> [all]), run playwright install chromium, then pycaps render --input my_video.mp4 --template minimalist (add --transcript file.srt","status":"active","categories":["T10"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SAX7KG4XF3N22DW1KY4B53","api_url":"https://veyrul.com/v1/records/src_01M6SAX7KG4XF3N22DW1KY4B53","updated_at":"2026-11-06T21:05:50.660Z","score":0.0017}},{"kind":"record","record":{"id":"exp_01M64VHQC5WMM7SXNTA75MVG2P","type":"experiment","title":"Seedance 2.5 live-action test: 10 s camera dips behind a table-tennis table and rises to a low close-up of a young man against trees","summary":"A camera behind a blue table-tennis table with a man's arm and red paddle at the left edge and a young man with glasses and a white tee beyond it holding a black paddle, which dips, moves toward the table and rises to a low close-up of his face and shoulders against trees and sky.","snippet":"A camera behind a blue table-tennis table with a","status":"completed","categories":["T06","T02"],"evidence":{"inspection":"source_inspected","execution":"reported_by_source","review":"unreviewed"},"url":"https://veyrul.com/experiments/exp_01M64VHQC5WMM7SXNTA75MVG2P","api_url":"https://veyrul.com/v1/records/exp_01M64VHQC5WMM7SXNTA75MVG2P","updated_at":"2026-10-29T22:53:45.346Z","score":0.007}},{"kind":"record","record":{"id":"src_01M6WCN5FCNYVP4W1A69D109W5","type":"source","title":"Show-1: text-to-video generation combining pixel and latent diffusion","summary":"Show-1 is a text-to-video generation method from Show Lab (accepted at IJCV), released with code and weights in October 2023. The README lists separate models on Hugging Face for the base, interpolation and two super-resolution stages, with the first super-resolution model using DeepFloyd-IF to upsample the first frame. Running python run_inference.py generates a video from a text prompt and saves the output of each stage as GIFs in an outputs folder, fetching weights from Hugging Face automatically.","snippet":"quick look.\n\nFirst action: - Run pip install -r requirements.txt (PyTorch 2.0 or later is <b>recommended</b>).\n- Run python run_inference.py, or clone the weight repositories with git lfs.\n- For show","status":"active","categories":["T06"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6WCN5FCNYVP4W1A69D109W5","api_url":"https://veyrul.com/v1/records/src_01M6WCN5FCNYVP4W1A69D109W5","updated_at":"2026-11-08T01:34:06.788Z","score":0.0026}},{"kind":"record","record":{"id":"ast_01M64VKJE9WJ3BTG20X6Y82KGR","type":"asset","title":"Seedance 2.5 neon boxing round, five-shot variant: counter finish and 1.1 s black tail (20 s) — original video","summary":"Founder-cleared historical Higgsfield output. Original video available; audio has not been listened to.","snippet":"Founder-cleared historical Higgsfield output. Original <b>video</b> available; audio has not been listened to. Original historical <b>video</b> from the founder Higgsfield account. Public use authorized","status":"active","categories":["T06","T02"],"evidence":{"inspection":"metadata_checked","execution":"reported_by_source","review":"unreviewed"},"url":"https://veyrul.com/assets/ast_01M64VKJE9WJ3BTG20X6Y82KGR","api_url":"https://veyrul.com/v1/records/ast_01M64VKJE9WJ3BTG20X6Y82KGR","updated_at":"2026-10-29T22:20:46.601Z","score":0.0171}},{"kind":"record","record":{"id":"ast_01M64VTTHG8TJH7T2K8NBCVQ38","type":"asset","title":"Seedance 2.5 style test: stadium-night shonen football finish with a blue-energy overhead kick (20 s) — original video","summary":"Founder-cleared historical Higgsfield output. Original video available; audio has not been listened to.","snippet":"Founder-cleared historical Higgsfield output. Original <b>video</b> available; audio has not been listened to. Original historical <b>video</b> from the founder Higgsfield account. Public use authorized","status":"active","categories":["T06","T02"],"evidence":{"inspection":"metadata_checked","execution":"reported_by_source","review":"unreviewed"},"url":"https://veyrul.com/assets/ast_01M64VTTHG8TJH7T2K8NBCVQ38","api_url":"https://veyrul.com/v1/records/ast_01M64VTTHG8TJH7T2K8NBCVQ38","updated_at":"2026-10-29T22:19:36.977Z","score":0.0172}},{"kind":"record","record":{"id":"src_01M6V7Q54BDKTC6DBE3H4FNJSG","type":"source","title":"HunyuanVideo: large text-to-video generation model with inference code","summary":"This repository contains PyTorch model definitions, pre-trained weights and inference and sampling code for HunyuanVideo, a large video generation model. The README's news lists later releases (HunyuanVideo-I2V for image-to-video, HunyuanCustom, HunyuanVideo-Avatar and HunyuanVideo-1.5), FP8 weights, parallel inference with xDiT and Diffusers integration.","snippet":"<b>Check</b> you have an NVIDIA GPU with CUDA; the README tests Linux and <b>recommends</b> CUDA 12.6 or 11.8.\n- Create a conda environment with python 3.10.9, install PyTorch","status":"active","categories":["T06"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V7Q54BDKTC6DBE3H4FNJSG","api_url":"https://veyrul.com/v1/records/src_01M6V7Q54BDKTC6DBE3H4FNJSG","updated_at":"2026-11-07T14:48:34.666Z","score":0.0065}},{"kind":"record","record":{"id":"src_01M6WAGWYRPJAG2G6817ZFQKHG","type":"source","title":"Practical-RIFE: practical video frame interpolation models based on RIFE","summary":"Practical-RIFE is a project based on RIFE and SAFA that adds practical features and new models for video frame interpolation. The README lists many trained model versions (for example 4.25 recommended by default for most scenes, 4.26, and lighter variants), notes that 4.24 and later are quite suitable for post-processing diffusion-model generated videos, and links related apps and ports (SVFI, RIFE-App, FlowFrames, VapourSynth-RIFE, RIFE-ncnn-vulkan, vs-mlrt).","snippet":"<b>video</b> frame interpolation. The README lists many trained model versions (for example 4.25 <b>recommended</b> by default for most scenes, 4.26, and lighter variants), notes that 4.24 and later","status":"active","categories":["T13","T10"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6WAGWYRPJAG2G6817ZFQKHG","api_url":"https://veyrul.com/v1/records/src_01M6WAGWYRPJAG2G6817ZFQKHG","updated_at":"2026-11-08T00:56:49.844Z","score":0.0057}},{"kind":"record","record":{"id":"exp_01M64VFSXTQB5Z49PCADJBKNG1","type":"experiment","title":"Seedance 2.5 sequence run with a linked image and video: 20 s rose window, two silhouettes whose shadows merge, a pale neck and a bending silhouette","summary":"Against a rose window two silhouettes stand close and their shadows merge, a close of a pale jaw and neck tilted back in light with a red earring, a close of a pale hand gripping a red cloth, and a silhouette of a spiky figure bending over a pale-haired figure.","snippet":"Against a rose window two silhouettes stand close and their","status":"completed","categories":["T06","T02"],"evidence":{"inspection":"source_inspected","execution":"reported_by_source","review":"unreviewed"},"url":"https://veyrul.com/experiments/exp_01M64VFSXTQB5Z49PCADJBKNG1","api_url":"https://veyrul.com/v1/records/exp_01M64VFSXTQB5Z49PCADJBKNG1","updated_at":"2026-10-29T22:50:55.620Z","score":0.0002}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M77FQ5239F5Q0PKCFATHVY5Z","type":"article","revision":1,"title":"Check a finished video against YouTube's recommended upload settings before you upload","coverage":"For creators and editors exporting MP4 files for YouTube. You get a read-only report that marks each recommendation (container, fast start, edit lists, codec, profile, 4:2:0, scan type, B frames, GOP, audio format) as pass, warning or fail, plus fixes for the common failures. It was run only on generated test files; closed GOP and CABAC cannot be read from the file, and YouTube's page opens with a note that its features are only available to Content Manager partners without saying which, so the guide treats the list as published guidance.","example":"A generated file made with ffmpeg's defaults failed on moov position and edit lists, and a stream-copy remux with +faststart and -use_editlist 0 cleared both failures.","tips":["Re-export from your editor to fix codec, profile or audio problems; do not re-encode a file that already passes.","Treat bitrates as reference values; the page says no bitrate limit is required.","After any remux, listen for audio sync on your real file."],"categories":["T10"],"tags":["youtube","upload-settings","ffprobe"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}}],"truncated":true,"has_more":true,"next_cursor":"eyJyZWZlcmVuY2UiOiJNakEiLCJwcmV2aWV3IjpudWxsLCJxIjoiQ2hlY2sgYSBmaW5pc2hlZCB2aWRlbyBhZ2FpbnN0IFlvdVR1YmUncyByZWNvbW1lbmRlZCB1cGxvYWQgc2V0dGluZ3MgYmVmb3JlIHlvdSB1cGxvYWQiLCJ0eXBlcyI6W10sImNhdGVnb3JpZXMiOltdfQ","ordering":"bounded_reference_and_preview_lanes"}