AudioLDM 2
Free.ai (self-hosted)
·
music
·
~5000 tokens per track
·
3.9
kubva 8 Vashandisi vemutauro wechiGerman munyaya iyi
AudioLDM 2 is a music generation model built by Haohe Liu. Strongest at Music generation from text. Self-inotarisirwa pa Free.ai GPUs - inofamba zvakasununguka pazuva rako re token pool (5,000 tokens patrack). Yakaburitswa pasi peApache 2.0 - kushandiswa kwekutengesa kwakabvumirwa pasi peFree.ai.
Usati washandisa
OpenAI-inowirirana REST API. Kugadzira chiratidzo uye kukumbira iyi model mumasekondi.
curl -X POST https://api.free.ai/v1/music/generate/ \
-H "Authorization: Bearer sk-free-..." \
-H "Content-Type: application/json" \
-d '{"model":"audioldm2","prompt":"your prompt here"}'Semuenzaniso mamodheru
Zvimwe zvinobvunzwa kakawanda
AudioLDM 2 inogadzira musika wekutanga weinstrumental (uye pazvimwe zvirongwa, mavondo) kubva pabhokisi remashoko. Dzivisa pfungwa, genre, mazvombo, kana BPM uye AudioLDM 2 inodzokera ku audio track yakati wandei.
10 kusvika 60 masekondi pagore rinouya zvichienderana nechigadzirwa. Kuti uwane zvikamu zvirefu, shandisa makore akawanda anouya kuburikidza ne /music/stitch/ kana kuburitsa muzvikamu zve30-sekondi uye kutambanudza.
Zvimwe zvirongwa zvinogadzira mavhesi kubva pamazwi aunotipa (pedza mavhesi mufomu); zvimwe zvinogadzira mavhesi kubva pamazwi aunotipa chete. Cheka mufomu pane iyi peji - a Lyrics field zvinoreva kuti mavhesi anotsigirwa.
Pop, rock, EDM, jazz, ambient, classical, lo-fi, hip-hop instrumentals zvese zvinopa zvakakwana. Niche genres (gamelan, Carnatic, throat singing) zvinopesana - nyora zvakajeka zvinhu zvaunofarira kuti uwane zvinoshamisa zvibodzwa.
AudioLDM 2 runs on our own GPUs against your daily free pool first; $5 → 200,000 paid tokens after that. About ~5,000 tokens per track.
WAV sezvakafanotaurwa (sina kukuvadza, kugadzirira kutambanudza). MP3 inowanikwa musarudzo yemufananidzo yemafaira akaderera.
No. AudioLDM 2 anodzokera a mixed track. Kuti kuparadzana muzvipfuyo, kutamba kubuda kuburikidza / music / stem- muzvipfuyo /, iyo inobvisa vocals, drums, bass uye vamwe.
Yes - /batch/ accepts a list of prompts. Every track lands in /account/?tab=history with the prompt as the filename. For more control, use the API.
Yeah - POST yako kukumbira kuti /v1/music/generate/ with model="AudioLDM 2". /api/ ane yakazara reference kusanganisira lyrics, nguva, uye tempo parameters.
AudioLDM 2 haina kuburitsazve zvinongedzo zvine kodzero dzemunyori - zvinongedzo zvinogadzirwa zvakatsva. Free.ai inobvumira kushandiswa kwekutengesa; iwe unochengeta kodzero dzezvinyorwa zvako zvakagadzirwa. Kutaura zita remuimbi mubvunzo unobvunza "mu style of" - zvinongedzo zvinobva pakutanga.
15 masekondi kusvika 2 maminitsi patrack zvichienderana nenguva yekushanda + injini. Premium models inotanga nekukurumidza. Usashandisa bhatani rekumirira kuti uvhure tab - iyo result inosvika mu /account/?tab=history kana yapera.
Yechokwadi - failed renders auto-refund. For tracks that ran but sound bad, email contact@free.ai with the share link and we will review case-by-case.