AudioLDM 2
Free.ai (self-hosted)
·
music
·
~5000 Ii-token track
·
4.0
I- 4 Abathathi nxaxheba
AudioLDM 2 yi an Imodeli yokudala umculo eyenziwe ngu Haohe Liu. Enamandla kakhulu kwi Music generation from text. I-self-hosted kwi-Free.ai GPUs — iqhuba ngokukhululekileyo kwi-token pool yakho yosuku (5,000 tokens Ingoma nganye). Ikhutshwe phantsi kwe Apache 2.0 — ukusetyenziswa korhwebo kuvunyelwe kwi Free.ai.
Sebenzisa nge-API
I-REST API ehambelana ne-OpenAI. Yenza iqhosha kwaye unxulumane nale modeli kwimizuzu.
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"}'Iimodeli ezifanayo
Imibuzo ebuzwa rhoqo
AudioLDM 2 ivelisa iingoma eziphambili (kunye kwezinye iinjini, iingoma) ukusuka kumyalezo okhawulezayo. Chaza i-mood, i-genre, i-instrumentation, okanye i-BPM kwaye AudioLDM 2 ibuyisela umkhondo wesandi ogqityiweyo.
10 ukuya kwi 60 imizuzwana nganye yohlobo luxhomekeke kwi-injini. Kwiinxalenye ezide, dibanisa iintlobo ezininzi nge /music/stitch/ okanye yenza kwicandelo le 30-imizuzu kwaye utshintshe umbala.
Ezinye iinjini zidibanisa iingoma ezivela kwiingoma ozinikayo (cofa iingoma kwifomu); ezinye zii-instrumental kuphela. Khangela ifomu kule phepha - indawo yengoma ithetha ukuba iingoma zixhaswe.
I-pop, i-rock, i-EDM, i-jazz, i-ambient, i-classical, i-lo-fi, i-hip-hop isixhobo sonke sibonisa ngokufanelekileyo. Ii-genres ze-niche (i-gamelan, i-Carnatic, ukubiza nge-throat) zibuthathaka — chaza isixhobo ngokucacileyo ukuze ufumane iziphumo ezilungileyo.
AudioLDM 2 iqhuba kwi-GPU yethu ye-GPU echaphazela i-pool yakho yasimahla yansuku zonke kuqala; $5 → 200,000 i-token ehlawulweyo emva koko. malunga ne-~5,000 i-token nganye.
WAV ngokumiselweyo (engenalahleko, ilungile ukuxuba okungaphezulu). I-MP3 ifumaneka kwi-output picker yeefayile ezincinci.
Hayi — AudioLDM 2 ibuyisela umculo oxhumeneyo. Ukuwahlula ngezijungqu, qhuba i-output nge /music/separate/ esebenzisa i-Demucs ukutsala iingoma, i-drums, i-bass, nezinye.
Ewe — /batch/ ivuma uluhlu lweempendulo. Ingoma nganye iwela kwi /account/?tab=history ngempendulo njengegama lefayili. Ulawulo oluninzi, sebenzisa i-API.
Ewe — UTHENGA umyalezo wakho okhawulezayo ku /v1/music/generate/ ngemodeli "AudioLDM 2". /api/ inesiqendu esipheleleyo esiquka amagama engoma, ixesha lokuphila, kunye neeparamitha zexesha.
AudioLDM 2 ayiphindanga iinkomfa ezikhuselwe yi-copyright — iimveliso zidityanisiwe ngokutsha. Free.ai inikezela ngenkonzo yorhwebo; ugcina ilungelo lemihlaba yakho eyenziweyo. Ukunika igama lomculi kwi-prompt icela "kwisimo se" — isandi sangempela siyindawo yokuqala.
15 imizuzwana ukuya kwimizuzu emibini ngengoma nganye kuxhomekeke kuxesha lokuphila + injini. Iimodeli eziphezulu zigqiba ngokukhawuleza. Sebenzisa iqhosha lofolo ukuvala i-tab — i-result iwela kwi-/account/?tab=history xa igqityiwe.
Ewe - i-failed renders auto-refund. Kwiingoma eziqhube kodwa zithetha kakubi, thumela i-imeyili kwi contact@free.ai ngekhonkco lokuzonwabisa kwaye siza kujonga iimeko nganye ngenye.