Kontent qismiga oʻtish

Fayl:AI-generated audio featuring bossa nova music with electric guitar.ogg

ZiyoSfera, erkin ensiklopediya
AI-generated_audio_featuring_bossa_nova_music_with_electric_guitar.ogg (file size: 262 KB, MIME type: application/ogg)

Ushbu fayl Vikiomborga yuklangan boʻlib, boshqa loyihalarda ham qoʻllanilishi mumkin. Uning tavsif sahifasidan olingan maʼlumot quyida keltirilgan.

Qisqa izoh

Taʼrif

Demonstration of an algorithmically-generated audio track featuring bossa nova music accompanied by electric guitar, created using Riffusion, an open-source fine-tuned derivative of the Stable Diffusion image-generation diffusion model that has been retrained to generate images of audio spectrograms, which can then be converted into audio files.

An audio spectrogram is a visual representation of an audio clip's frequency content, and images of spectrograms can be converted into audio via short-time Fourier transform, using the Griffin-Lim algorithm 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, fine-tuned through the use of Nvidia A10G enterprise datacenter GPUs.

Procedure/Methodology

The spectrograms were generated using the Riffusion Inference Server running the riffusion-model-v1 diffusion model, paired with the Riffusion App UI frontend. The following values were used:

  • Prompt: "bossa nova with electric guitar"
  • Seed Image: OG Beat
  • Denoising: 0.75

This resulted in the output spectrogram image:

Spectrogram image

Spectrograms were then converted to WAV audio using this python script:

Audio converted from spectrogram
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 Audacity and then converted to OGG Vorbis.
Sanasi
Manba Oʻzimning ishim
Muallif Benlisquare
Ruxsat
(Bu faylning takror foydalanilishi)
Output images

As the creator of the output images and audio, I release this file under the licence displayed within the template below.

Stable Diffusion AI model

The Stable Diffusion AI model is released under the CreativeML OpenRAIL-M License, which "does not impose any restrictions 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.

Riffusion v1 model

The Riffusion v1 model, created by Seth Forsgren and Hayk Martiros, is released under the CreativeML OpenRAIL-M License and is a derivative model of the Stable Diffusion v1.5 model checkpoint.

Riffusion Inference Server

The Riffusion Inference Server is released under an MIT License.

Riffusion App
The Riffusion App is released under an MIT License.

Litsenziyalash

I, the copyright holder of this work, hereby publish it under the following licenses:
w:en:Creative Commons
atribut bir xil ulashish
This file is licensed under the Creative Commons Attribution-Share Alike 4.0 International license.
Siz erkinsiz:
  • ulashishga – ishlanmani nusxalash, tarqatish va uzatish
  • remiks qilishga – ishni moslashtirishga
Quyidagi shartlar asosida:
  • atribut – Siz tegishli litsenziyaga havolani taqdim etishingiz va oʻzgartirishlar kiritilganligini koʻrsatishingiz kerak. Siz buni har qanday oqilona yoʻl bilan qilishingiz mumkin, lekin litsenziar Sizni yoki Sizning foydalanishingizni ma'qullashini taklif qiladigan tarzda emas.
  • bir xil ulashish – Agar Siz materialni remiks qilsangiz, oʻzgartirsangiz yoki unga asoslansangiz, oʻz hissalaringizni asl nusxadagi kabi bir xil yoki mos litsenziya ostida tarqatishingiz kerak.
GNU head Ushbu hujjatdan nusxa ko‘chirish, tarqatish va/yoki o‘zgartirish uchun GNU Erkin guvohnoma litsenziyasi (GNU Free Documentation License), 1.2 va har qanday keyingi versiyalar shartlariga muvofiq ruxsat berilgan yoki Ochiq kodli dasturlar jamiyati (Free Software Foundation) tomonidan chop etilgan; oʻzgarmas boʻlimlarsiz, oldingi muqova matnlari va orqa muqova matnlarisiz. Litsenziya nusxasi GNU Erkin guvohnoma litsenziyasi (GNU Free Documentation License) boʻlimiga kiritilgan.
Siz oʻzingiz xohlagan litsenziyani tanlashingiz mumkin.

Captions

Add a one-line explanation of what this file represents

Items portrayed in this file

tasvirlangan obyekt

17 dekabr 2022

application/ogg

checksum inglizcha

a7005e27a53a8c2a562f4eb8da45eed8a2044a68

data size inglizcha

268 288 Bayt

15,2686167800454 soniya

Fayl tarixi

Faylning biror paytdagi holatini koʻrish uchun tegishli sana/vaqtga bosingiz.

Sana/VaqtOʻlchamlariFoydalanuvchiIzoh
joriy03:22, 2022-yil 18-dekabr (262 KB)wikimediacommons>Benlisquare{{Information |Description= Demonstration of an algorithmically-generated audio track featuring bossa nova music accompanied by electric guitar, created using [https://www.riffusion.com/about Riffusion], an open-source fine-tuned derivative of the Stable Diffusion image-generation diffusion model that has been retrained to generate images of audio spectrograms, which can then be converted into audio files. An audio spectrogram i...

Bu faylga quyidagi sahifa bogʻlangan: