210:
38:
360:
451:
366:
371:
86:
1023:
303:
on reuse, distribution, commercialization, adaptation" as long as the model is not being intentionally used to cause harm to individuals, for instance, to deliberately mislead or deceive, and the authors of the AI models claim no rights over any image outputs generated, as stipulated by the license.
234:
Riffusion generates 512×512 resolution images which each represent 5 second chunks of looping audio; for the convenience of the reader, the three generated spectrogram images have been merged together in GIMP along the x-axis (which represents time), and the audio files have been merged together in
162:
to approximate phase during audio reconstruction. While the Stable
Diffusion AI model is originally intended to generate visual images from a textual prompt, Riffusion has been retrained from Stable Diffusion v1.5 to instead generate spectrogram images from text prompts describing musical motifs,
226:
52:
48:
42:
97:
65:
412:– You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
227:
225:
1048:
image-generation diffusion model that has been retrained to generate images of audio spectrograms, which can then be converted into audio files. An audio
468:
147:
image-generation diffusion model that has been retrained to generate images of audio spectrograms, which can then be converted into audio files.
1022:
1017:
56:
37:
466:; with no Invariant Sections, no Front-Cover Texts, and no Back-Cover Texts. A copy of the license is included in the section entitled
274:
458:
1066:
856:
802:
698:
681:
645:
1082:
This file contains additional information, probably added from the digital camera or scanner used to create or digitize it.
154:
is a visual representation of an audio clip's frequency content, and images of spectrograms can be converted into audio via
419:
155:
287:
As the creator of the output images and audio, I release this file under the licence displayed within the template below.
951:
914:
877:
822:
786:
752:
629:
601:
586:
573:
463:
209:
849:
718:
665:
546:
529:
593:
381:
1085:
If the file has been modified from its original state, some details may not fully reflect the modified file.
1062:
The following pages on the
English Knowledge (XXG) use this file (pages on other projects are not listed):
418:– If you remix, transform, or build upon the material, you must distribute your contributions under the
378:
300:
325:
1044:
music accompanied by electric guitar, created using , an open-source fine-tuned derivative of the
608:
296:
105:
1040:{{Information |Description= Demonstration of an algorithmically-generated audio track featuring
144:
445:
336:
456:
Permission is granted to copy, distribute and/or modify this document under the terms of the
1045:
1033:
313:
176:
353:
I, the copyright holder of this work, hereby publish it under the following licenses:
263:
218:
92:
151:
172:
136:
1049:
243:
159:
1041:
1071:
180:
316:
and is a derivative model of the Stable
Diffusion v1.5 model checkpoint.
312:
The
Riffusion v1 model, created by Seth Forsgren and Hayk Martiros, is
163:
fine-tuned through the use of Nvidia A10G enterprise datacenter GPUs.
130:
AI-generated audio featuring bossa nova music with electric guitar.png
135:
Demonstration of an algorithmically-generated audio track featuring
990:
Click on a date/time to view the file as it appeared at that time.
223:
208:
140:
80:
699:
Creative
Commons Attribution-ShareAlike 4.0 International
513:
Add a one-line explanation of what this file represents
682:
462:, Version 1.2 or any later version published by the
295:
The Stable
Diffusion AI model is released under the
217:
Spectrograms were then converted to WAV audio using
139:
music accompanied by electric guitar, created using
124:
104:
Commons is a freely licensed media file repository.
70:(1,536 × 512 pixels, file size: 707 KB, MIME type:
314:released under the CreativeML OpenRAIL-M License
206:This resulted in the output spectrogram image:
609:https://commons.wikimedia.org/User:Benlisquare
429:https://creativecommons.org/licenses/by-sa/4.0
143:, an open-source fine-tuned derivative of the
85:
435:Creative Commons Attribution-Share Alike 4.0
359:
183:UI frontend. The following values were used:
8:
395:– to copy, distribute and transmit the work
1087:
992:
509:
494:You may select the license of your choice.
235:Audacity and then converted to OGG Vorbis.
171:The spectrograms were generated using the
382:Attribution-Share Alike 4.0 International
838:46156d04673efe58545be15786f4eb742aa19f73
1105:
1097:
1089:
1064:
965:
949:
928:
912:
891:
875:
836:
820:
800:
784:
766:
750:
732:
716:
696:
679:
663:
643:
627:
560:
544:
527:
524:
505:
498:
7:
474:http://www.gnu.org/copyleft/fdl.html
981:
370:
365:
190:: "bossa nova with electric guitar"
1080:
518:
512:
493:
356:
352:
324:The Riffusion Inference Server is
117:
63:
1067:Music and artificial intelligence
517:
179:diffusion model, paired with the
503:
450:
449:
406:Under the following conditions:
377:This file is licensed under the
369:
364:
358:
301:does not impose any restrictions
231:Audio converted from spectrogram
84:
21:
500:
14:
499:
480:GNU Free Documentation License
469:GNU Free Documentation License
459:GNU Free Documentation License
26:
1:
803:original creation by uploader
337:released under an MIT License
326:released under an MIT License
297:CreativeML OpenRAIL-M License
31:
525:Items portrayed in this file
156:short-time Fourier transform
1127:
420:same or compatible license
320:Riffusion Inference Server
173:Riffusion Inference Server
1107:File change date and time
982:
291:Stable Diffusion AI model
253:
16:
502:
464:Free Software Foundation
386:
91:This is a file from the
1110:21:35, 17 December 2022
1039:
1018:22:23, 17 December 2022
269:
259:
249:
242:
239:
127:
95:. Information from its
232:
214:
98:description page there
41:Size of this preview:
1091:Horizontal resolution
335:The Riffusion App is
230:
212:
167:Procedure/Methodology
160:Griffin-Lim algorithm
850:determination method
1099:Vertical resolution
401:– to adapt the work
47:Other resolutions:
587:Wikimedia username
574:author name string
308:Riffusion v1 model
233:
219:this python script
215:
177:riffusion-model-v1
57:1,536 × 512 pixels
1114:
1113:
1055:
666:copyright license
511:
491:
490:
343:
342:
278:
275:Reusing this file
228:
213:Spectrogram image
113:
112:
93:Wikimedia Commons
1118:
1088:
1046:Stable Diffusion
1030:
970:
933:
896:
859:
854:
734:17 December 2022
630:copyright status
611:
606:
596:
591:
581:
578:
487:
484:
481:
478:
475:
453:
452:
446:
442:
439:
436:
433:
430:
422:as the original.
379:Creative Commons
373:
372:
368:
367:
362:
361:
272:
255:
245:
244:17 December 2022
229:
145:Stable Diffusion
131:
125:
109:
88:
87:
81:
75:
73:
60:
53:640 × 213 pixels
49:320 × 107 pixels
43:800 × 267 pixels
1126:
1125:
1121:
1120:
1119:
1117:
1116:
1115:
1076:
1063:
1056:
1036:
1028:
984:
983:
980:
979:
978:
977:
976:
975:
974:
973:
971:
968:
958:
957:
956:
954:
943:
942:
941:
940:
939:
938:
937:
936:
934:
931:
921:
920:
919:
917:
906:
905:
904:
903:
902:
901:
900:
899:
897:
894:
884:
883:
882:
880:
869:
868:
867:
866:
865:
864:
863:
862:
861:
860:
855:
852:
843:
842:
841:
839:
829:
828:
827:
825:
814:
813:
812:
811:
810:
809:
808:
807:
805:
793:
792:
791:
789:
778:
777:
776:
775:
774:
773:
772:
771:
769:
759:
758:
757:
755:
744:
743:
742:
741:
740:
739:
738:
737:
735:
725:
724:
723:
721:
710:
709:
708:
707:
706:
705:
704:
703:
701:
690:
689:
688:
687:
686:
684:
672:
671:
670:
668:
657:
656:
655:
654:
653:
652:
651:
650:
648:
636:
635:
634:
632:
621:
620:
619:
618:
617:
616:
615:
614:
613:
612:
607:
604:
598:
597:
592:
589:
583:
582:
579:
576:
567:
566:
565:
563:
553:
552:
551:
549:
538:
537:
536:
535:
534:
532:
516:
515:
514:
497:
496:
495:
485:
482:
479:
476:
473:
444:
443:
440:
437:
434:
431:
428:
427:
385:
374:
355:
354:
349:
344:
224:
129:
122:
115:
114:
103:
102:
101:is shown below.
77:
71:
69:
62:
61:
46:
12:
11:
5:
1124:
1122:
1112:
1111:
1108:
1104:
1103:
1100:
1096:
1095:
1092:
1079:
1075:
1074:
1069:
1061:
1060:
1059:
1054:
1053:
1038:
1034:
1031:
1025:
1020:
1015:
1011:
1010:
1007:
1004:
1001:
998:
995:
988:
987:
972:
966:
964:
963:
962:
961:
960:
959:
955:
950:
948:
947:
946:
945:
944:
935:
929:
927:
926:
925:
924:
923:
922:
918:
913:
911:
910:
909:
908:
907:
898:
892:
890:
889:
888:
887:
886:
885:
881:
876:
874:
873:
872:
871:
870:
848:
847:
846:
845:
844:
840:
837:
835:
834:
833:
832:
831:
830:
826:
821:
819:
818:
817:
816:
815:
806:
801:
799:
798:
797:
796:
795:
794:
790:
787:source of file
785:
783:
782:
781:
780:
779:
770:
767:
765:
764:
763:
762:
761:
760:
756:
751:
749:
748:
747:
746:
745:
736:
733:
731:
730:
729:
728:
727:
726:
722:
717:
715:
714:
713:
712:
711:
702:
697:
695:
694:
693:
692:
691:
685:
680:
678:
677:
676:
675:
674:
673:
669:
664:
662:
661:
660:
659:
658:
649:
644:
642:
641:
640:
639:
638:
637:
633:
628:
626:
625:
624:
623:
622:
600:
599:
585:
584:
572:
571:
570:
569:
568:
564:
561:
559:
558:
557:
556:
555:
554:
550:
545:
543:
542:
541:
540:
539:
533:
528:
526:
523:
522:
521:
520:
519:
508:
507:
504:
501:
492:
489:
488:
454:
426:
425:
424:
423:
413:
404:
403:
402:
396:
389:You are free:
376:
375:
357:
351:
350:
348:
345:
341:
340:
334:
333:
322:
321:
310:
309:
293:
292:
285:
284:
279:
267:
266:
261:
257:
256:
251:
247:
246:
241:
237:
236:
204:
203:
197:
191:
169:
168:
132:
123:
121:
118:
116:
111:
110:
89:
79:
78:
40:
36:
35:
34:
29:
24:
19:
13:
10:
9:
6:
4:
3:
2:
1123:
1109:
1106:
1101:
1098:
1093:
1090:
1086:
1083:
1077:
1073:
1070:
1068:
1065:
1057:
1051:
1047:
1043:
1037:
1032:
1026:
1024:
1021:
1019:
1016:
1013:
1012:
1008:
1005:
1002:
999:
996:
994:
993:
991:
985:
953:
916:
879:
858:
851:
824:
804:
788:
754:
720:
700:
683:
667:
647:
631:
610:
603:
595:
588:
575:
548:
531:
471:
470:
465:
461:
460:
455:
448:
447:
432:CC BY-SA 4.0
421:
417:
414:
411:
408:
407:
405:
400:
397:
394:
391:
390:
388:
387:
383:
380:
363:
346:
338:
332:Riffusion App
331:
330:
329:
327:
319:
318:
317:
315:
307:
306:
305:
302:
298:
290:
289:
288:
283:Output images
282:
281:
280:
276:
271:
268:
265:
262:
258:
252:
248:
238:
222:
220:
211:
207:
201:
198:
195:
192:
189:
186:
185:
184:
182:
181:Riffusion App
178:
174:
166:
165:
164:
161:
157:
153:
148:
146:
142:
138:
133:
126:
119:
107:
100:
99:
94:
90:
83:
82:
76:
67:
66:Original file
58:
54:
50:
44:
39:
33:
30:
28:
25:
23:
20:
18:
15:
1084:
1081:
1027:1,536 × 512
989:
986:File history
467:
457:
415:
409:
398:
392:
323:
311:
294:
286:
216:
205:
199:
193:
187:
175:running the
170:
158:, using the
149:
134:
106:You can help
96:
64:
22:File history
1050:spectrogram
1035:Benlisquare
646:copyrighted
594:Benlisquare
580:Benlisquare
416:share alike
410:attribution
264:Benlisquare
152:spectrogram
128:Description
1102:118.11 dpc
1094:118.11 dpc
1058:File usage
1042:bossa nova
1003:Dimensions
753:media type
562:some value
270:Permission
194:Seed Image
137:bossa nova
27:File usage
1072:Riffusion
1000:Thumbnail
997:Date/Time
878:data size
768:image/png
719:inception
347:Licensing
299:, which "
200:Denoising
196:: OG Beat
150:An audio
141:Riffusion
72:image/png
1078:Metadata
1029:(707 KB)
893:724,372
823:checksum
506:Captions
399:to remix
393:to share
384:license.
254:Own work
32:Metadata
1014:current
1009:Comment
547:creator
530:depicts
510:English
120:Summary
68:
967:1,536
915:height
260:Author
250:Source
202:: 0.75
188:Prompt
969:pixel
952:width
932:pixel
857:SHA-1
1052:i...
1006:User
930:512
895:byte
486:true
483:true
477:GFDL
441:true
438:true
240:Date
17:File
602:URL
853::
605::
590::
577::
328:.
221::
55:|
51:|
45:.
472:.
339:.
277:)
273:(
108:.
74:)
59:.
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.