Disco Diffusion

Master Stable Diffusion with step-by-step courses

Anaconda https://ift.tt/GgOQmD8 Stable Diffusion https://ift.tt/JcUGzLv Stable Diffusion Model https://ift.tt/uC31RBn SD Helper Files + OptimizedSD https://ift.tt/YjoFBw0 Commands conda env create -f environment.yaml

Ready for some more advanced Stable Diffusion? Want to turn your kid's doodles into artistic master pieces? Maybe you'd like to GoBig with high resolution images, or perhaps run your own web interface locally with Gradio? It's time to put your nerd on, because all this and more awaits you! Chapters: 00:00 - Intro and Image 2 Image 10:28 - Image Inpainting 13:08 - Low VRAM / Weights / Web GUI 18:41 - HD Images / GOBIG Links: https://ift.tt/h2F5VB0 https://ift.tt/MJceOKf https://ift.tt/UmWTMkA https://ift.tt/gcFVwbe https://ift.tt/TMrXjRv https://ift.tt/JkRECTA https://ift.tt/JAgQxNX https://ift.tt/d2OJqiQ

The Stable Diffusion prompt search engine

In this video I give you a full tour for generating images in Stable Diffusion. Glibacord Link: https://ift.tt/tXYRg5B Stable Diffusion Website: https://ift.tt/Ed7m8eI Artist Resource: https://ift.tt/u2Yz5QI #StableDiffusion #Dalle2

Comparing three different AI art programs.

Create Disco Diffusion artworks in one line. Contribute to jina-ai/discoart development by creating an account on GitHub.

Artists 🦜🦾,This here spreadsheet is used and maintained by @sureailabs, @proximasan, @EErratica, and @KyrickYoung as part our ongoing Disco Diffusion artist studies. NEW ✨ Stable Diffusion Artist Studies can be viewed here: a href="https://www.notion.so/proximacentaurib/e2537cbf42c34b7e9a9a...

AI art created using stable diffusion

All prompts are “Artwork by [Artist Name]”. Each has artist has 3 examples (click-through to see). Seeds are random. Default settings. No tags at the moment - might do it later. This is a visual reference guide for artist styles that I, @sureailabs, personally enjoy, it is not meant to house all possible recognized artists. Happy prompting.

Time to dive into diffusion models and see what is going on underneath the magic that is making the news at the moment :) If you'd prefer a slightly longer, more conversational version, the livestream recording is up here: https://youtu.be/jkSoMlfuUm0 (this also covers a few additional topics thanks to questions from the twitch chat). Lesson notebook: https://ift.tt/ngptx7o Github (includes discord invite) : https://ift.tt/lvEuAy0

Welcome back to AIAIART! This lesson recaps some of the core ideas from part 1 (lessons 1-4) and sets us up for the next few weeks, where we'll look into some advanced new techniques like transformers for image synthesis and the recently-famous diffusion models. The live stream of this lesson ran a little long and had a couple of technical hiccups, so this video is a re-recording that tries to do a more high-level summary. If you'd prefer to follow along with the full-length video in which I actually run all the code and explain in more depth, that video is up on https://ift.tt/bMYi7rx and as an unlisted video here: https://youtu.be/BHkLbzspdt8 See links to past lessons and our Discord where you can ask questions and share your projects via the aiaiart github repository: https://ift.tt/AKGc1ZW The colab link for lesson 5: https://ift.tt/IKPSQ63

Informal chat where we read through a few papers and look at a recent project. No central notebook for this lesson, but some resources we'll be talking about: - A brief shoutout to https://multimodal.art/ as a great way to keep up with things - CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers (https://ift.tt/QgkA92Y) - Denoising Diffusion GAN (https://ift.tt/J4wdPlS) - My project, CLOOB Conditioned Latent Denoising Diffusion GANs (https://ift.tt/WIfpH7a) and specifically the demo notebook (https://ift.tt/xmiLsDy) I forgot to mention a few things: 1) If you're curious how I organised the code into that library with nice docs and such: check out NBDev. 2) The demo grids shown run from no conditioning (left) to fairly extreme conditioning (right) using classifier free guidance. -- Watch live at https://ift.tt/bMYi7rx

AIAIART Lesson 6, diving into transformer models and their application to image synthesis. We'll start by playing with text generation and build all the way up to creating our own version of the original 'dall-e' model for text-to-image synthesis. Github: https://ift.tt/lvEuAy0 The Colab notebook for this lesson: https://ift.tt/Ejvemku The original live-streamed version of this lesson isn't actually all that much longer than this video, coming in just over an hour! You can find it on https://ift.tt/bMYi7rx and I'll also upload it to YouTube at some point and update this description then.

Ongoing list with modifiers and tips for image generation

Google's latest research leaps toward resolving the diffusion models' image resolution issue through linking SR3 and CDM.

Disco Diffusion is a free tool that you can use to create "AI" generated art. You can create machine learning generated images and videos with it.