Wiki-Quellcode von Riffusion APP Hobby
Zuletzt geändert von René Schmidt am 2025/03/31 00:53
Verstecke letzte Bearbeiter
| author | version | line-number | content |
|---|---|---|---|
![]() |
1.1 | 1 | = [[https:~~/~~/github.com/riffusion/riffusion-app-hobby.git>>https://github.com/riffusion/riffusion-app-hobby.git]] = |
| 2 | |||
![]() |
3.1 | 3 | [[https:~~/~~/github.com/huggingface/diffusers>>https://github.com/huggingface/diffusers]] bei ärger damit |
![]() |
2.1 | 4 | |
![]() |
1.1 | 5 | = = |
| 6 | |||
| 7 | = Riffusion App = | ||
| 8 | |||
| 9 | |||
| 10 | ⛔ This project is no longer actively maintained. | ||
| 11 | |||
| 12 | Riffusion is an app for real-time music generation with stable diffusion. | ||
| 13 | |||
| 14 | This repository contains the interactive web app that powers the website. | ||
| 15 | |||
| 16 | It is built with Next.js, React, Typescript, three.js, Tailwind, and Vercel. | ||
| 17 | |||
| 18 | == Run == | ||
| 19 | |||
| 20 | |||
| 21 | This is a [[Next.js>>url:https://nextjs.org/]] project bootstrapped with [[create-next-app>>url:https://github.com/vercel/next.js/tree/canary/packages/create-next-app]]. | ||
| 22 | |||
| 23 | First, make sure you have Node v18 or greater installed using node ~-~-version. | ||
| 24 | |||
| 25 | Install packages: | ||
| 26 | |||
| 27 | {{{npm install}}} | ||
| 28 | |||
| 29 | Run the development server: | ||
| 30 | |||
| 31 | {{{npm run dev | ||
| 32 | # or | ||
| 33 | yarn dev}}} | ||
| 34 | |||
| 35 | Open [[http:~~/~~/localhost:3000>>url:http://localhost:3000]] with your browser to see the app. | ||
| 36 | |||
| 37 | The app home is at pages/index.js. The page auto-updates as you edit the file. The about page is at pages/about.tsx. | ||
| 38 | |||
| 39 | The pages/api directory is mapped to /api/*. Files in this directory are treated as [[API routes>>url:https://nextjs.org/docs/api-routes/introduction]] instead of React pages. | ||
| 40 | |||
| 41 | == Inference Server == | ||
| 42 | |||
| 43 | |||
| 44 | To actually generate model outputs, we need a model backend that responds to inference requests via API. If you have a large GPU that can run stable diffusion in under five seconds, clone and run the instructions in the [[inference server>>url:https://github.com/hmartiro/riffusion-inference]] to run the Flask app. | ||
| 45 | |||
| 46 | You will need to add a .env.local file in the root of this repository specifying the URL of the inference server: | ||
| 47 | |||
| 48 | {{{RIFFUSION_FLASK_URL=http://127.0.0.1:3013/run_inference/ | ||
| 49 | }}} | ||
| 50 | |||
| 51 | == Citation == | ||
| 52 | |||
| 53 | |||
| 54 | If you build on this work, please cite it as follows: | ||
| 55 | |||
| 56 | {{{@article{Forsgren_Martiros_2022, | ||
| 57 | author = {Forsgren, Seth* and Martiros, Hayk*}, | ||
| 58 | title = {{Riffusion - Stable diffusion for real-time music generation}}, | ||
| 59 | url = {https://riffusion.com/about}, | ||
| 60 | year = {2022} | ||
| 61 | } | ||
| 62 | }}} |
