125:
1292:
1261:
1241:
210:
Riffusion is classified within a subset of AI text-to-music generators. In
December 2022, Mubert similarly used Stable Diffusion to turn descriptive text into music loops. In January 2023, Google published a paper on their own text-to-music generator called MusicLM.
137:
1135:
138:
977:
383:
323:
1357:
270:
203:" (otherworldly), although unlikely to replace man-made music. The model was made available on December 15, 2022, with the code also freely available on
309:
1333:
493:
124:
252:
1352:
376:
1166:
1267:
818:
555:
234:
1079:
706:
513:
369:
1034:
168:, designed by Seth Forsgren and Hayk Martiros, that generates music using images of sound rather than audio. It was created as a
1221:
1161:
759:
754:
443:
75:
1196:
550:
503:
498:
52:
1326:
1247:
543:
469:
169:
871:
806:
407:
1272:
1130:
769:
600:
423:
181:
165:
1171:
428:
1362:
1299:
1216:
1201:
854:
849:
749:
617:
398:
324:"Mubert launches Text-to-Music interface – a completely new way to generate music from a single text prompt"
192:
different files together. This is accomplished using a functionality of the Stable
Diffusion model known as
1319:
1176:
936:
655:
650:
1206:
1191:
1156:
844:
744:
612:
184:
and converted into audio files. While these files are only several seconds long, the model can also use
1074:
287:
180:. This results in a model which uses text prompts to generate image files, which can be put through an
1226:
1181:
627:
572:
418:
413:
801:
779:
528:
523:
481:
433:
87:
82:
1240:
1186:
764:
593:
1252:
1044:
696:
567:
560:
1303:
337:
997:
987:
794:
588:
538:
533:
476:
464:
173:
94:
1110:
1054:
876:
518:
438:
310:"El generador de imágenes AI también puede producir música (con resultados de otro mundo)"
152:
1084:
1049:
1039:
864:
622:
448:
1346:
1029:
1009:
926:
605:
189:
1115:
946:
185:
58:
271:"Essayez "Riffusion", un modèle d'IA qui compose de la musique en la visualisant"
136:
1291:
1211:
982:
891:
886:
508:
486:
177:
1105:
1064:
1059:
972:
881:
789:
701:
681:
148:
25:
1100:
1069:
967:
811:
774:
711:
665:
660:
645:
176:, an existing open-source model for generating images from text prompts, on
361:
351:
288:"文章に沿った楽曲を自動生成してくれるAI「Riffusion」登場、画像生成AI「Stable Diffusion」ベースで誰でも自由に利用可能"
1002:
834:
1125:
962:
916:
839:
739:
734:
686:
193:
1140:
1120:
992:
784:
204:
235:"Try 'Riffusion,' an AI model that composes music by visualizing it"
941:
921:
911:
906:
901:
896:
859:
691:
931:
365:
253:"Riffusion: creare tracce audio con l'intelligenza artificiale"
352:"5 Reasons Google's MusicLM AI Text-to-Music App is Different"
207:. It is one of many models derived from Stable Diffusion.
155:" (top), and the resulting audio after conversion (bottom)
108:
1307:
1149:
1093:
1022:
955:
827:
727:
720:
674:
638:
581:
457:
397:
103:
93:
81:
71:
51:
43:
24:
1327:
377:
8:
303:
301:
246:
244:
228:
226:
224:
19:
199:The resulting music has been described as "
1334:
1320:
724:
384:
370:
362:
282:
280:
18:
220:
147:Generated spectrogram from the prompt "
16:Music-generating machine learning model
338:"MusicLM: Generating Music From Text"
308:Llano, Eutropio (December 15, 2022).
233:Coldewey, Devin (December 15, 2022).
7:
1288:
1286:
1222:Generative adversarial network (GAN)
1358:Deep learning software applications
251:Nasi, Michele (December 15, 2022).
1306:. You can help Knowledge (XXG) by
14:
1290:
1260:
1259:
1239:
134:
123:
1172:Recurrent neural network (RNN)
1162:Differentiable neural computer
1:
1353:Artificial intelligence stubs
1217:Variational autoencoder (VAE)
1177:Long short-term memory (LSTM)
444:Computational learning theory
1197:Convolutional neural network
1192:Multilayer perceptron (MLP)
1379:
1285:
1268:Artificial neural networks
1182:Gated recurrent unit (GRU)
408:Differentiable programming
1235:
601:Artificial neural network
424:Automatic differentiation
182:inverse Fourier transform
429:Neuromorphic engineering
392:Differentiable computing
1300:artificial intelligence
1202:Residual neural network
618:Artificial Intelligence
1302:-related article is a
1157:Neural Turing machine
745:Human image synthesis
1248:Computer programming
1227:Graph neural network
802:Text-to-video models
780:Text-to-image models
628:Large language model
613:Scientific computing
419:Statistical manifold
414:Information geometry
326:. December 21, 2022.
273:. December 15, 2022.
65:/riffusion-inference
594:In-context learning
434:Pattern recognition
354:. January 27, 2023.
340:. January 26, 2023.
188:between outputs to
88:Text-to-image model
21:
1187:Echo state network
1075:Jürgen Schmidhuber
770:Facial recognition
765:Speech recognition
675:Software libraries
1315:
1314:
1283:
1282:
1045:Stephen Grossberg
1018:
1017:
139:
117:
116:
47:December 15, 2022
1370:
1336:
1329:
1322:
1294:
1287:
1273:Machine learning
1263:
1262:
1243:
998:Action selection
988:Self-driving car
795:Stable Diffusion
760:Speech synthesis
725:
589:Machine learning
465:Gradient descent
386:
379:
372:
363:
356:
355:
348:
342:
341:
334:
328:
327:
320:
314:
313:
305:
296:
295:
284:
275:
274:
267:
261:
260:
248:
239:
238:
230:
174:Stable Diffusion
141:
140:
127:
113:
110:
67:
64:
62:
60:
22:
1378:
1377:
1373:
1372:
1371:
1369:
1368:
1367:
1343:
1342:
1341:
1340:
1284:
1279:
1231:
1145:
1111:Google DeepMind
1089:
1055:Geoffrey Hinton
1014:
951:
877:Project Debater
823:
721:Implementations
716:
670:
634:
577:
519:Backpropagation
453:
439:Tensor calculus
393:
390:
360:
359:
350:
349:
345:
336:
335:
331:
322:
321:
317:
307:
306:
299:
286:
285:
278:
269:
268:
264:
250:
249:
242:
232:
231:
222:
217:
159:
158:
157:
156:
153:electric guitar
144:
143:
142:
135:
130:
129:
128:
107:
57:
44:Initial release
39:
17:
12:
11:
5:
1376:
1374:
1366:
1365:
1363:Computer music
1360:
1355:
1345:
1344:
1339:
1338:
1331:
1324:
1316:
1313:
1312:
1295:
1281:
1280:
1278:
1277:
1276:
1275:
1270:
1257:
1256:
1255:
1250:
1236:
1233:
1232:
1230:
1229:
1224:
1219:
1214:
1209:
1204:
1199:
1194:
1189:
1184:
1179:
1174:
1169:
1164:
1159:
1153:
1151:
1147:
1146:
1144:
1143:
1138:
1133:
1128:
1123:
1118:
1113:
1108:
1103:
1097:
1095:
1091:
1090:
1088:
1087:
1085:Ilya Sutskever
1082:
1077:
1072:
1067:
1062:
1057:
1052:
1050:Demis Hassabis
1047:
1042:
1040:Ian Goodfellow
1037:
1032:
1026:
1024:
1020:
1019:
1016:
1015:
1013:
1012:
1007:
1006:
1005:
995:
990:
985:
980:
975:
970:
965:
959:
957:
953:
952:
950:
949:
944:
939:
934:
929:
924:
919:
914:
909:
904:
899:
894:
889:
884:
879:
874:
869:
868:
867:
857:
852:
847:
842:
837:
831:
829:
825:
824:
822:
821:
816:
815:
814:
809:
799:
798:
797:
792:
787:
777:
772:
767:
762:
757:
752:
747:
742:
737:
731:
729:
722:
718:
717:
715:
714:
709:
704:
699:
694:
689:
684:
678:
676:
672:
671:
669:
668:
663:
658:
653:
648:
642:
640:
636:
635:
633:
632:
631:
630:
623:Language model
620:
615:
610:
609:
608:
598:
597:
596:
585:
583:
579:
578:
576:
575:
573:Autoregression
570:
565:
564:
563:
553:
551:Regularization
548:
547:
546:
541:
536:
526:
521:
516:
514:Loss functions
511:
506:
501:
496:
491:
490:
489:
479:
474:
473:
472:
461:
459:
455:
454:
452:
451:
449:Inductive bias
446:
441:
436:
431:
426:
421:
416:
411:
403:
401:
395:
394:
391:
389:
388:
381:
374:
366:
358:
357:
343:
329:
315:
297:
276:
262:
240:
219:
218:
216:
213:
166:neural network
146:
145:
133:
132:
131:
122:
121:
120:
119:
118:
115:
114:
105:
101:
100:
97:
91:
90:
85:
79:
78:
73:
69:
68:
55:
49:
48:
45:
41:
40:
38:
37:
34:
30:
28:
15:
13:
10:
9:
6:
4:
3:
2:
1375:
1364:
1361:
1359:
1356:
1354:
1351:
1350:
1348:
1337:
1332:
1330:
1325:
1323:
1318:
1317:
1311:
1309:
1305:
1301:
1296:
1293:
1289:
1274:
1271:
1269:
1266:
1265:
1258:
1254:
1251:
1249:
1246:
1245:
1242:
1238:
1237:
1234:
1228:
1225:
1223:
1220:
1218:
1215:
1213:
1210:
1208:
1205:
1203:
1200:
1198:
1195:
1193:
1190:
1188:
1185:
1183:
1180:
1178:
1175:
1173:
1170:
1168:
1165:
1163:
1160:
1158:
1155:
1154:
1152:
1150:Architectures
1148:
1142:
1139:
1137:
1134:
1132:
1129:
1127:
1124:
1122:
1119:
1117:
1114:
1112:
1109:
1107:
1104:
1102:
1099:
1098:
1096:
1094:Organizations
1092:
1086:
1083:
1081:
1078:
1076:
1073:
1071:
1068:
1066:
1063:
1061:
1058:
1056:
1053:
1051:
1048:
1046:
1043:
1041:
1038:
1036:
1033:
1031:
1030:Yoshua Bengio
1028:
1027:
1025:
1021:
1011:
1010:Robot control
1008:
1004:
1001:
1000:
999:
996:
994:
991:
989:
986:
984:
981:
979:
976:
974:
971:
969:
966:
964:
961:
960:
958:
954:
948:
945:
943:
940:
938:
935:
933:
930:
928:
927:Chinchilla AI
925:
923:
920:
918:
915:
913:
910:
908:
905:
903:
900:
898:
895:
893:
890:
888:
885:
883:
880:
878:
875:
873:
870:
866:
863:
862:
861:
858:
856:
853:
851:
848:
846:
843:
841:
838:
836:
833:
832:
830:
826:
820:
817:
813:
810:
808:
805:
804:
803:
800:
796:
793:
791:
788:
786:
783:
782:
781:
778:
776:
773:
771:
768:
766:
763:
761:
758:
756:
753:
751:
748:
746:
743:
741:
738:
736:
733:
732:
730:
726:
723:
719:
713:
710:
708:
705:
703:
700:
698:
695:
693:
690:
688:
685:
683:
680:
679:
677:
673:
667:
664:
662:
659:
657:
654:
652:
649:
647:
644:
643:
641:
637:
629:
626:
625:
624:
621:
619:
616:
614:
611:
607:
606:Deep learning
604:
603:
602:
599:
595:
592:
591:
590:
587:
586:
584:
580:
574:
571:
569:
566:
562:
559:
558:
557:
554:
552:
549:
545:
542:
540:
537:
535:
532:
531:
530:
527:
525:
522:
520:
517:
515:
512:
510:
507:
505:
502:
500:
497:
495:
494:Hallucination
492:
488:
485:
484:
483:
480:
478:
475:
471:
468:
467:
466:
463:
462:
460:
456:
450:
447:
445:
442:
440:
437:
435:
432:
430:
427:
425:
422:
420:
417:
415:
412:
410:
409:
405:
404:
402:
400:
396:
387:
382:
380:
375:
373:
368:
367:
364:
353:
347:
344:
339:
333:
330:
325:
319:
316:
311:
304:
302:
298:
293:
289:
283:
281:
277:
272:
266:
263:
258:
257:IlSoftware.it
254:
247:
245:
241:
236:
229:
227:
225:
221:
214:
212:
208:
206:
202:
201:de otro mundo
197:
195:
191:
187:
183:
179:
175:
171:
167:
163:
154:
150:
126:
112:
106:
102:
98:
96:
92:
89:
86:
84:
80:
77:
74:
70:
66:
56:
54:
50:
46:
42:
36:Hayk Martiros
35:
33:Seth Forsgren
32:
31:
29:
27:
23:
1308:expanding it
1297:
1116:Hugging Face
1080:David Silver
728:Audio–visual
582:Applications
561:Augmentation
406:
346:
332:
318:
291:
265:
256:
209:
200:
198:
186:latent space
178:spectrograms
161:
160:
26:Developer(s)
1264:Categories
1212:Autoencoder
1167:Transformer
1035:Alex Graves
983:OpenAI Five
887:IBM Watsonx
509:Convolution
487:Overfitting
190:interpolate
170:fine-tuning
99:MIT License
1347:Categories
1253:Technology
1106:EleutherAI
1065:Fei-Fei Li
1060:Yann LeCun
973:Q-learning
956:Decisional
882:IBM Watson
790:Midjourney
682:TensorFlow
529:Activation
482:Regression
477:Clustering
215:References
149:bossa nova
72:Written in
53:Repository
1136:MIT CSAIL
1101:Anthropic
1070:Andrew Ng
968:AlphaZero
812:VideoPoet
775:AlphaFold
712:MindSpore
666:SpiNNaker
661:Memristor
568:Diffusion
544:Rectifier
524:Batchnorm
504:Attention
499:Adversary
162:Riffusion
109:riffusion
63:/hmartiro
20:Riffusion
1244:Portals
1003:Auto-GPT
835:Word2vec
639:Hardware
556:Datasets
458:Concepts
292:GIGAZINE
1126:Meta AI
963:AlphaGo
947:PanGu-Σ
917:ChatGPT
892:Granite
840:Seq2seq
819:Whisper
740:WaveNet
735:AlexNet
707:Flux.jl
687:PyTorch
539:Sigmoid
534:Softmax
399:General
194:img2img
104:Website
95:License
1141:Huawei
1121:OpenAI
1023:People
993:MuZero
855:Gemini
850:Claude
785:DALL-E
697:Theano
205:GitHub
76:Python
59:github
1298:This
1207:Mamba
978:SARSA
942:LLaMA
937:BLOOM
922:GPT-J
912:GPT-4
907:GPT-3
902:GPT-2
897:GPT-1
860:LaMDA
692:Keras
164:is a
151:with
1304:stub
1131:Mila
932:PaLM
865:Bard
845:BERT
828:Text
807:Sora
111:.com
83:Type
61:.com
872:NMT
755:OCR
750:HWR
702:JAX
656:VPU
651:TPU
646:IPU
470:SGD
172:of
1349::
300:^
290:.
279:^
255:.
243:^
223:^
196:.
1335:e
1328:t
1321:v
1310:.
385:e
378:t
371:v
312:.
294:.
259:.
237:.
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.