{"schema":"catalog-search/v2","items":[{"kind":"record","record":{"id":"dsc_01M6SSGJPREZKCZGJPG9WWE7DM","type":"discussion","title":"Connecting reusable workflows: Can a local music model go on a commercial release? Check code, weights, training data and route: ACE-Step, MusicGen, Stable Audio Open","summary":null,"snippet":"Compare this method with a relevant existing workflow. Identify the","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6SSGJPREZKCZGJPG9WWE7DM","api_url":"https://veyrul.com/v1/records/dsc_01M6SSGJPREZKCZGJPG9WWE7DM","updated_at":"2026-11-07T01:21:00.749Z","score":1.0033}},{"kind":"record","record":{"id":"src_01M569EHE6M9QRWJ4NEKSDA8HG","type":"source","title":"AudioCraft (MusicGen, AudioGen, EnCodec)","summary":"AudioCraft is a PyTorch library for deep learning research on audio generation, with inference and training code for models including MusicGen and AudioGen.","snippet":"AudioCraft is a PyTorch library for deep learning research on audio <b>generation</b>, with inference and training code for models including <b>MusicGen</b> and AudioGen. What it supplies: AudioCraft","status":"active","categories":["T14"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EHE6M9QRWJ4NEKSDA8HG","api_url":"https://veyrul.com/v1/records/src_01M569EHE6M9QRWJ4NEKSDA8HG","updated_at":"2026-11-07T13:45:25.690Z","score":0.9708}},{"kind":"record","record":{"id":"src_01M6SK9CYD2BXYZYP04J9C5T0G","type":"source","title":"Sonilo in ComfyUI: video to music and text to music templates","summary":"Two templates: soundtrack generated to fit an uploaded video (optional style prompt) and prompt-only music generation; output saved to output/audio.","snippet":"templates: soundtrack <b>generated</b> to fit an uploaded video (optional style prompt) and prompt-only <b>music</b> <b>generation</b>; output saved to output/audio. What it supplies: Two templates: soundtrack <b>generated</b>","status":"active","categories":["T08"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SK9CYD2BXYZYP04J9C5T0G","api_url":"https://veyrul.com/v1/records/src_01M6SK9CYD2BXYZYP04J9C5T0G","updated_at":"2026-11-06T23:32:17.961Z","score":0.0121}},{"kind":"record","record":{"id":"src_01M6VQZEFR4NQR4W0YF3J5CQKA","type":"source","title":"Bark: transformer text-to-audio model for speech and sound, README overview","summary":"The README presents Bark as a generative text-to-audio model for speech, music and sound, not a conventional TTS system.","snippet":"README presents Bark as a <b>generative</b> <b>text</b>-to-audio model for speech, <b>music</b> and sound, not a conventional TTS system. What it supplies: The README presents Bark","status":"active","categories":["T13"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6VQZEFR4NQR4W0YF3J5CQKA","api_url":"https://veyrul.com/v1/records/src_01M6VQZEFR4NQR4W0YF3J5CQKA","updated_at":"2026-11-07T19:32:43.606Z","score":0.0848}},{"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":0.0318}},{"kind":"record","record":{"id":"dsc_01M6V9BATGDAQF8NFQ2H7FWHYY","type":"discussion","title":"Creative practice with Generate short narration clips with Bark: install from the Suno repo, pick a voice preset, add sound cues and write WAV files","summary":null,"snippet":"creative experiment. State the intention, choose a contrasting alternative and inspect actual outputs if <b>generated</b>. Preserve technical observations separately from taste. Produce a usable sample, test package or informative experiment","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6V9BATGDAQF8NFQ2H7FWHYY","api_url":"https://veyrul.com/v1/records/dsc_01M6V9BATGDAQF8NFQ2H7FWHYY","updated_at":"2026-11-07T15:17:00.684Z","score":0.0448}},{"kind":"record","record":{"id":"src_01M6VESXKVYQ8AZPV3QPMWSGY0","type":"source","title":"bsienkiewicz/ConceptCaps","summary":"Hugging Face dataset bsienkiewicz/ConceptCaps at revision 31aed55ba9ff: modalities audio, text; declared licence cc-by-4.0; not gated. Metadata-only index entry; not tested guidance.","snippet":"uploader, not verified): <b>music</b>, audio, captions, <b>text</b>-to-audio, <b>music</b>-<b>generation</b>, interpretability, synthetic, <b>musicgen</b>, concepts, tcav, audio-captioning\ncreated","status":"active","categories":["T14"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6VESXKVYQ8AZPV3QPMWSGY0","api_url":"https://veyrul.com/v1/records/src_01M6VESXKVYQ8AZPV3QPMWSGY0","updated_at":"2026-11-07T16:52:25.306Z","score":0.0358}},{"kind":"record","record":{"id":"dsc_01M569J6HD9DMT7SMXX14S9H6Y","type":"discussion","title":"Which open music-generation models are safe for commercial scoring, and what evidence supports their training-data claims?","summary":null,"snippet":"weights are Apache-2.0, YuE2 weights are CC BY-NC with creator-monetization permission, <b>MusicGen</b> weights are CC-BY-NC, Stable Audio Open uses a gated community license with","status":"open","categories":["T14","T20"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569J6HD9DMT7SMXX14S9H6Y","api_url":"https://veyrul.com/v1/records/dsc_01M569J6HD9DMT7SMXX14S9H6Y","updated_at":"2026-10-18T01:21:04.546Z","score":0.0745}},{"kind":"record","record":{"id":"src_01M569EHP0RDXM2P6QVER8CCBP","type":"source","title":"MusicCaps (text-music captions dataset)","summary":null,"snippet":"second AudioSet <b>music</b> <b>clips</b> with English aspect lists and free-<b>text</b> captions written by musicians, introduced with MusicLM; distributed as YouTube IDs and timestamps only (no audio), under","status":"active","categories":["T14"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EHP0RDXM2P6QVER8CCBP","api_url":"https://veyrul.com/v1/records/src_01M569EHP0RDXM2P6QVER8CCBP","updated_at":"2026-10-18T01:19:04.884Z","score":0.0153}},{"kind":"record","record":{"id":"dsc_01M683Q7KEWSC4RT04AAD79FSS","type":"discussion","title":"Connecting reusable workflows: How a prompt for a performance clip is written as a cut map tied to a music track, and which of its nine timecoded beats 26 stills show (sound claims not verified)","summary":null,"snippet":"Compare this method with a relevant existing workflow. Identify the","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M683Q7KEWSC4RT04AAD79FSS","api_url":"https://veyrul.com/v1/records/dsc_01M683Q7KEWSC4RT04AAD79FSS","updated_at":"2026-10-31T04:33:08.220Z","score":0.0179}},{"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":"definitions, pre-trained weights and inference and sampling code for HunyuanVideo, a large video <b>generation</b> model. The README's news lists later releases (HunyuanVideo-I2V for image-to-video, HunyuanCustom","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":0.0095}},{"kind":"record","record":{"id":"src_01M6VBE90ZEWRKJHP8BGHD5380","type":"source","title":"Flowblade: multitrack non-linear video editor for Linux","summary":"Flowblade is a multitrack non-linear video editor for Linux, released under the GPL 3 license. The README lists six editing tools, several clip insertion methods, up to 21 video and audio tracks, track and compositor-based compositing with 19 blend modes and 40+ pattern wipes, 50+ image filters and 30+ audio filters, generators, a range log, a G'Mic tool, a text tool, batch encoding, media re-linking, USB shuttle control, and GPU VAAPI and NVENC encoding.","snippet":"Linux, released under the GPL 3 license. The README lists six editing tools, several <b>clip</b> insertion methods, up to 21 video and audio tracks, track and compositor-based compositing with","status":"active","categories":["T10"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6VBE90ZEWRKJHP8BGHD5380","api_url":"https://veyrul.com/v1/records/src_01M6VBE90ZEWRKJHP8BGHD5380","updated_at":"2026-11-07T15:53:37.995Z","score":0.0505}},{"kind":"record","record":{"id":"src_01M6SKMHDRM364G5BREDYSDATV","type":"source","title":"Stable Audio 3 ComfyUI workflow example (Medium and Medium Base templates)","summary":"Two templates via a dedicated subgraph node: Medium (idea text, duration, seed, category Music/Instrument/SFX/One-shot, optional Qwen reprompt) and Medium Base (full prompt, duration, seed).","snippet":"Base (full prompt, duration, seed).\n\nUseful for: <b>Music</b> and SFX creators wanting local <b>generation</b> including one-shots and instruments.\n\nFirst action: Place stable_audio_3_medium.safetensors in models/checkpoints, t5gemma_b_b_ul2.safetensors in models/text_encoders (plus","status":"active","categories":["T08"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SKMHDRM364G5BREDYSDATV","api_url":"https://veyrul.com/v1/records/src_01M6SKMHDRM364G5BREDYSDATV","updated_at":"2026-11-06T23:38:22.996Z","score":0.0217}},{"kind":"record","record":{"id":"src_01M569CP69S5APGRZTEJ1B7CB2","type":"source","title":"AI Short Film: Full Prompt Library (8-scene, 8-style animated short, Seedance 2.0)","summary":null,"snippet":"Nano Banana Pro, structured prompt with Claude, animate in Seedance 2.0 extending the previous <b>clip</b>; one prop recurs in every scene","status":"active","categories":["T07","T06","T16"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569CP69S5APGRZTEJ1B7CB2","api_url":"https://veyrul.com/v1/records/src_01M569CP69S5APGRZTEJ1B7CB2","updated_at":"2026-10-18T01:18:03.965Z","score":0.0303}},{"kind":"record","record":{"id":"src_01M6SGR1JSDC75GN6G05RXYZT1","type":"source","title":"HeartMuLa: A Family of Open Sourced Music Foundation Models","summary":"Open lyrics-and-tags song generation (3B released), a 12.5 Hz codec, a Whisper-based lyrics transcriber and an audio-text alignment model; example script, low-memory options and a separate MuLaCover cover model noted in news.","snippet":"Open lyrics-and-tags song <b>generation</b> (3B released), a 12.5 Hz codec, a Whisper-based lyrics transcriber and an audio-<b>text</b> alignment model; example script, low-memory options","status":"active","categories":["T14","T09"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SGR1JSDC75GN6G05RXYZT1","api_url":"https://veyrul.com/v1/records/src_01M6SGR1JSDC75GN6G05RXYZT1","updated_at":"2026-11-06T22:47:52.116Z","score":0.0199}},{"kind":"record","record":{"id":"src_01M569G9KT8VEESJSCXXF4D26Y","type":"source","title":"Make Viral AI Short Films With This Exact Workflow (pirate short tutorial)","summary":null,"snippet":"hero sheet to prevent Seedance identity drift; 21:9, 4K, 15 s, audio on; <b>music</b> added later in the edit","status":"active","categories":["T16","T03","T06"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569G9KT8VEESJSCXXF4D26Y","api_url":"https://veyrul.com/v1/records/src_01M569G9KT8VEESJSCXXF4D26Y","updated_at":"2026-10-18T01:20:02.160Z","score":0.0242}},{"kind":"record","record":{"id":"src_01M6SGG6SK5QBB7S9FK7NYRC0V","type":"source","title":"Stable Audio 1.0 text-to-audio workflow in ComfyUI","summary":"Core-node text-to-audio graph: CheckpointLoaderSimple, CLIPTextEncode, EmptyLatentAudio (default 47.6 s), KSampler, VAE decode, save to output/audio.","snippet":"output/audio.\n\nUseful for: Sound designers wanting <b>short</b> loops, ambience or <b>music</b> <b>clips</b> locally with no custom nodes.\n\nFirst action: Put stable-audio-open-1.0.safetensors (2.3 GB) in checkpoints and t5-base.safetensors","status":"active","categories":["T08"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SGG6SK5QBB7S9FK7NYRC0V","api_url":"https://veyrul.com/v1/records/src_01M6SGG6SK5QBB7S9FK7NYRC0V","updated_at":"2026-11-06T22:43:35.312Z","score":0.0189}},{"kind":"record","record":{"id":"src_01M6V4ASD6P0RFHKCHY9FZ1SMS","type":"source","title":"Demucs: music source separation into drums, bass, vocals and other stems","summary":"Demucs is a music source separation model that splits a track into drums, bass, vocals and the remaining accompaniment.","snippet":"Demucs is a <b>music</b> source separation model that splits a track into drums, bass, vocals and the remaining accompaniment. What it supplies: Demucs is a <b>music</b> source separation","status":"active","categories":["T14"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V4ASD6P0RFHKCHY9FZ1SMS","api_url":"https://veyrul.com/v1/records/src_01M6V4ASD6P0RFHKCHY9FZ1SMS","updated_at":"2026-11-07T13:49:23.716Z","score":0.0195}},{"kind":"record","record":{"id":"src_01M6WCMY3409K4BGEH8T95TW1E","type":"source","title":"StreamingT2V / StreamingSVD: autoregressive long video generation","summary":"The README presents StreamingSVD, an autoregressive method that turns Stable Video Diffusion into a long video generator for text-to-video and image-to-video, as part of the StreamingT2V family (accepted at CVPR 2025). The inference script runs an image-to-video pipeline that includes video enhancement with randomised blending and frame interpolation. A memory-optimised version was released in November 2024.","snippet":"presents StreamingSVD, an autoregressive method that turns Stable Video Diffusion into a long video <b>generator</b> for <b>text</b>-to-video and image-to-video, as part of the StreamingT2V family","status":"active","categories":["T06"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6WCMY3409K4BGEH8T95TW1E","api_url":"https://veyrul.com/v1/records/src_01M6WCMY3409K4BGEH8T95TW1E","updated_at":"2026-11-08T01:33:59.233Z","score":0.0067}},{"kind":"record","record":{"id":"src_01M569G9C6X937RY4N3B80XYZP","type":"source","title":"clip-retrieval","summary":null,"snippet":"toolkit to compute <b>CLIP</b> embeddings for images and <b>text</b> and build a searchable index and web front end; an open route to semantic search over private or open reference","status":"active","categories":["T16","T20"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569G9C6X937RY4N3B80XYZP","api_url":"https://veyrul.com/v1/records/src_01M569G9C6X937RY4N3B80XYZP","updated_at":"2026-10-18T01:24:36.350Z","score":0.0227}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6V0E4930EFEW2VNARN5W72A","type":"article","revision":1,"title":"Generate short music clips from text on your own GPU with MusicGen","coverage":"For creators who want quick text-to-music cue sketches made locally. You end with short loudness-normalised WAV files. The model weights carry a non-commercial licence, and the guide is based on the documentation and was not run.","example":"A not-run example makes two ten-second clips with the small model from two short text descriptions.","tips":["If you run out of GPU memory, use the smallest model or shorter clips.","Check licensing before any commercial use: the model weights are published under CC-BY-NC 4.0.","Model downloads may land in an unexpected cache folder; a documented environment variable lets you move it."],"categories":["T14","T09"],"tags":["musicgen","audiocraft","text-to-music","music-generation","local-audio","gpu","licence-check"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6VV0JCMXY865FF4ZPRRJ8YW","type":"article","revision":1,"title":"Generate a short music cue from text with AudioCraft MusicGen, and what the weights licence allows","coverage":"For creators who want a quick mood cue for a story or game scene on their own GPU. You end with a short WAV clip from a text description, plus a clear view of the non-commercial weights licence. Based on the AudioCraft documentation; it was not run.","example":"A not-run example makes one 8-second cue with the small model from a one-line ghost-story description and saves it as a loudness-normalised WAV.","tips":["The code is MIT but the model weights are CC-BY-NC 4.0, so check the licence before commercial use; this is not legal advice.","Running out of GPU memory: use the small model or a shorter duration, which the documentation says smaller GPUs can handle.","Install torch 2.1.0 first, before the other packages, as the README requires."],"categories":["T14","T09"],"tags":["audiocraft","musicgen","text-to-music","gpu","wav","non-commercial","licence"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}}],"truncated":true,"has_more":true,"next_cursor":"eyJyZWZlcmVuY2UiOiJNakEiLCJwcmV2aWV3IjpudWxsLCJxIjoiR2VuZXJhdGUgc2hvcnQgbXVzaWMgY2xpcHMgZnJvbSB0ZXh0IG9uIHlvdXIgb3duIEdQVSB3aXRoIE11c2ljR2VuIiwidHlwZXMiOltdLCJjYXRlZ29yaWVzIjpbXX0","ordering":"bounded_reference_and_preview_lanes"}