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…
Blog
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…
Pop art pattern illustration portrait
Be immersed in the world of patterns. All images are generated with Colab notebook included in the Quick Start Guide. This is a simple yet versatile prompt that Positive prompt: amber heard, (pop art:1.1), colorful spiral patterns, painting, (vibrant color palette:1.2). Intricate. Highly detailed, art by Steve Henderson Keyword “spiral” can be replaced with one of…
Stable Diffusion Models: a beginner’s guide
Stable Diffusion Models, or checkpoint models, are pre-trained Stable Diffusion weights for generating a particular style of images. What kind of images a model generates depends on the training images. A model won’t be able to generate a cat’s image if there’s never a cat in the training data. Likewise, if you only train a…
Happy Thanksgiving!!
Celebrate thanksgiving with your family, and a big festive meal. All images are generated with Colab notebook included in the Quick Start Guide. Positive prompt: still life, thanksgiving turkey meal, fancy candle, wine, gravy, pumpkins, realistic photography, decorative, grapes CFG scale 7 Sampling steps 20 Image size 704×512 Seed -1 Face restoration None Sampling method DPM++…