Mirrors
/
riffusion-app
mirror of https://github.com/riffusion/riffusion-app.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Tweak about page

This commit is contained in:
Hayk Martiros 2022-12-22 20:40:59 -08:00
parent 732bfb0e5f
commit 0f8e64834c
2 changed files with 24 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -4,8 +4,8 @@ Riffusion is an app for real-time music generation with stable diffusion.
Read about it at https://www.riffusion.com/about and try it at https://www.riffusion.com/. Read about it at https://www.riffusion.com/about and try it at https://www.riffusion.com/.
* Web app: https://github.com/hmartiro/riffusion-app * Web app: https://github.com/riffusion/riffusion-app
* Inference server: https://github.com/hmartiro/riffusion-inference * Inference server: https://github.com/riffusion/riffusion
* Model checkpoint: https://huggingface.co/riffusion/riffusion-model-v1 * Model checkpoint: https://huggingface.co/riffusion/riffusion-model-v1
* Google Colab notebook: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1FhH3HlN8Ps_Pr9OR6Qcfbfz7utDvICl0?usp=sharing) * Google Colab notebook: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1FhH3HlN8Ps_Pr9OR6Qcfbfz7utDvICl0?usp=sharing)
* Gradio Web Demo: [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/fffiloni/spectrogram-to-music) * Gradio Web Demo: [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/fffiloni/spectrogram-to-music)

31
pages/about.tsx
View File

@ -102,6 +102,19 @@ export default function Home() {
All the same web UIs and techniques like img2img, inpainting, All the same web UIs and techniques like img2img, inpainting,
negative prompts, and interpolation work out of the box. negative prompts, and interpolation work out of the box.
</p> </p>
<p className="mt-3">
Code:{" "}
<a href="https://github.com/riffusion/riffusion">
https://github.com/riffusion/riffusion
</a>
<br />
Discord:{" "}
<a href="https://discord.gg/yu6SRwvX4v">
https://discord.gg/yu6SRwvX4v
</a>
</p>
<h2 className="pt-10 pb-5 text-3xl font-bold">Spectrograms</h2> <h2 className="pt-10 pb-5 text-3xl font-bold">Spectrograms</h2>
<p> <p>
An audio{" "} An audio{" "}
@ -175,7 +188,7 @@ export default function Home() {
</a> </a>
, which has excellent modules for efficient audio processing on the , which has excellent modules for efficient audio processing on the
GPU. Check out our audio processing code{" "} GPU. Check out our audio processing code{" "}
<a href="https://github.com/hmartiro/riffusion-inference/blob/main/riffusion/audio.py"> <a href="https://github.com/riffusion/riffusion/blob/main/riffusion/audio.py">
here here
</a> </a>
. .
@ -289,7 +302,7 @@ export default function Home() {
<p className="mt-3"> <p className="mt-3">
To address this, we smoothly interpolate between prompts and seeds To address this, we smoothly interpolate between prompts and seeds
<em> in the latent space of the model</em>. In diffusion models, the{" "} <em> in the latent space of the model</em>. In diffusion models, the{" "}
<a href="https://github.com/hmartiro/riffusion-inference/blob/main/riffusion/audio.py"> <a href="https://github.com/riffusion/riffusion/blob/main/riffusion/audio.py">
latent space latent space
</a>{" "} </a>{" "}
is a feature vector that embeds the entire possible space of what is a feature vector that embeds the entire possible space of what
@ -355,14 +368,14 @@ export default function Home() {
</audio> </audio>
</div> </div>
<p className="mt-3"> <p className="mt-3">
The huggingface{" "} The Hugging Face{" "}
<a href="https://github.com/huggingface/diffusers">diffusers</a>{" "} <a href="https://github.com/huggingface/diffusers">diffusers</a>{" "}
library implements a wide range of pipelines including library implements a wide range of pipelines including
image-to-image and prompt interpolation, but we needed an image-to-image and prompt interpolation, but we needed an
implementation for interpolation combined with image-to-image implementation for interpolation combined with image-to-image
conditioning. We implemented this pipeline, along with support for conditioning. We implemented this pipeline, along with support for
masking to limit generation to only parts of an image. Code{" "} masking to limit generation to only parts of an image. Code{" "}
<a href="https://github.com/hmartiro/riffusion-inference/blob/main/riffusion/riffusion_pipeline.py"> <a href="https://github.com/riffusion/riffusion/blob/main/riffusion/riffusion_pipeline.py">
here here
</a> </a>
. .
@ -409,20 +422,20 @@ export default function Home() {
<ul className="mt-3 ml-10 list-disc"> <ul className="mt-3 ml-10 list-disc">
<li> <li>
Web app:{" "} Web app:{" "}
<a href="https://github.com/hmartiro/riffusion-app"> <a href="https://github.com/riffusion/riffusion-app">
https://github.com/hmartiro/ riffusion-app https://github.com/riffusion/riffusion-app
</a> </a>
</li> </li>
<li> <li>
Inference server:{" "} Inference server:{" "}
<a href="https://github.com/hmartiro/riffusion-inference"> <a href="https://github.com/riffusion/riffusion">
https://github.com/hmartiro/ riffusion-inference https://github.com/riffusion/riffusion
</a> </a>
</li> </li>
<li> <li>
Model checkpoint:{" "} Model checkpoint:{" "}
<a href="https://huggingface.co/riffusion/riffusion-model-v1"> <a href="https://huggingface.co/riffusion/riffusion-model-v1">
https://huggingface.co/ riffusion/riffusion-model-v1 https://huggingface.co/riffusion/riffusion-model-v1
</a> </a>
</li> </li>
</ul> </ul>