A few city portraits generated with the Inkpunk Diffusion, a custom Stable Diffusion model with a unique illustration style. Promise me, if this is the end of us, let it be the beginning of the revolution. Carl Novakovich, The Watchers: The Tomb All images are generated with Colab notebook included in the Quick Start Guide. Positive…
Blog
How put anything in Stable Diffusion (Dreambooth Colab notebook)
Dreambooth is a way to put anything — your loved one, your dog, your favorite toy — into a Stable Diffusion model. We will introduce what Dreambooth is, how it works, and how to perform the training. This tutorial is aimed at people who have used Stable Diffusion but have not used Dreambooth before. You…
How to use VAE to improve eyes and faces
VAE is a partial update to Stable Diffusion 1.4 or 1.5 models that will make rendering eyes better. I will explain what VAE is, what you can expect, where you can get it, and how to install and use it. Table of ContentsWhat is VAE?Do I need a VAE?What is the effect of using VAE?Should…
How to use img2img in Stable Diffusion
Not a born-artist? Stable Diffusion can help. Img2img (image-to-image) can improve your drawing while keeping the color and composition. Table of ContentsWhat is img2img?Software setupStep-by-step guide to Img2imgStep 1: Create a backgroundStep 2: Draw an appleStep 3: Enter img2img settingsStep 4: Second img2img What is img2img? Image-to-image (img2img for short) is a method to generate…
Realistic human street portrait
A simple prompt to generate some realistic city people. The cities and mansions that people dream of are those in which they finally live. Lewis Mumford All images are generated with Colab notebook included in the Quick Start Guide. Positive prompt: a young female, highlights in hair, sitting outside restaurant, brown eyes, wearing a dress, side…
How to use AI image upscaler to improve details
AI Image upscalers like ESRGAN are indispensable tools to improve the quality of AI images generated by Stable Diffusion. It is so commonly used that many Stable Diffusion GUIs have built-in support. Here, we will learn what image upscalers are, how they work, and how to use them. Table of ContentsWhy do we need an…
A town by the river
Realistic illustration of a nineteen century town. Live your life. Take chances. Be crazy. Don’t wait. Because right now is the oldest you’ve ever been and the youngest you’ll ever be again. Suzanne Collins All images are generated with Colab notebook included in the Quick Start Guide. Positive prompt: town architecture, river, highly detailed, hyper-detailed architecture,…
Decorative gemstone pattern
Some close-ups of expensive things. Fashion’s finest gems brought to life by Stable Diffusion All images are generated with Colab notebook included in the Quick Start Guide. Positive prompt: close up angled view of glistening oiled, gemstones on dark blue silk with golden threads, ornate, intricate Exquisite details textures highly detailed digital painting, bokeh, dramatic lighting…
How to run Stable Diffusion 2.0 and a first look
Stable Diffusion 2.0 was released. Improvements include among other things, using a larger text encoder (which improves image quality) and increased default image size to 768×768 pixels. Click here if you are look for install guide for Stable Diffusion 2.1 Different from 1.5, NSFW filter was applied to the training data so you can expect…
Fantasy game or RPG characters
Some prompts for generating full-body character graphics for fantasy games or RPG. Our journey will never end. All images are generated with Colab notebook included in the Quick Start Guide. Positive prompt: (mage :1.3) in spiral lightning background, perfect beautiful face, realistic, full body, standing on ground, circuit board, in intricate clothing, elegant pose, fantasy, illustration, artstation…
