I’m Vignesh Kaushik. I curate and write articles on Thank God It’s Computational to help architects, designers, and urban planners leverage cutting-edge technologies on AEC projects.
TGIC is a community-driven platform providing concise technology education to students and professionals in the AEC industry to learn at their own pace. If you’re not a member, consider joining the community and supporting our work.
Stable Diffusion is an advanced AI text-to-image generator that can create incredibly coherent images from a text prompt. Created by the researchers and engineers from Stability AI, CompVis, and LAION, “Stable Diffusion” claimed the crown from Craiyon, formerly known as DALL·E-Mini, to be the new state-of-the-art, text-to-image, open-source model. It is primarily used to generate detailed images conditioned on text descriptions, though it can also be applied to other tasks such as inpainting, outpainting, and generating image-to-image translations guided by a text prompt. Stable Diffusion is growing up so fast. Barely three months after Stability AI introduced the image generator to the world, version 2.0 is out.
Let’s look at how you can get your hands dirty with Stable Diffusion for Free, both locally on your computer and on the web.
Diffusion Bee • Generate AI Art Locally On Mac
ARTIFICIAL INTELLIGENCE
Diffusion Bee is the easiest way to run Stable Diffusion locally on your Intel / M1 Mac. It comes with a one-click installer, is free, and runs locally on your computer. Once downloaded and properly installed, it requires no internet connection, and nothing gets sent to the cloud — ensuring complete data privacy. For optimal performance, it is best to install Diffusion Bee on Mac computers with 16GB of RAM. You can use Text to Image, Image to Image, In-painting, Out-painting, and Generation history features. Check out the source on Github to learn more about how all this works.
Stable Diffusion UI • Generate AI Art Locally On Windows
ARTIFICIAL INTELLIGENCE
Stable Diffusion UI is an easy-to-install distribution of Stable Diffusion, the leading open-source text-to-image AI software. Stable Diffusion UI installs all required software components required to run Stable Diffusion plus its own user-friendly and powerful web interface for free. No dependencies or technical knowledge is required. This version supports Text to Image, Image to Image, In-Painting, and Task Queueing feature.
Sponsored Link
Drive Digital Transformation
Eager to accelerate digital transformation at your company? Get started today → check out IT Brew’s latest guide: 5 tips for creating a successful digital transformation strategy.
DreamStudio Beta • Generate AI Art On the Web
ARTIFICIAL INTELLIGENCE
While the Stable Diffusion model has been made open source by Stability AI, the DreamStudio website is a service to enable anyone to access this powerful creative tool without the need for software installation, coding knowledge, or a heavy-duty local GPU. The fees charged on DreamStudio cover the compute costs to create each image and offer 200 free points to new users. Beyond 200 free points, you have to purchase credits. Each credit costs ~$0.01 and allows you to create an image. At default settings, it’s one credit per image. Depending on the image resolution & step count you choose, this can go as low as 0.2 credits per image or as high as 28.2 credits per image. A more detailed table of credit costs is posted in the FAQ section of the website.
Replicate OpenJourney • Generate AI Art With Cloud API
ARTIFICIAL INTELLIGENCE
Replicate lets you run machine learning models with a cloud API, without having to understand the intricacies of machine learning or manage your own infrastructure. You can run open-source models that other people have published, or package and publish your own models. The web interface is great for getting acquainted with a model, but when you're ready to integrate a model into something like a chat bot, website, or mobile app, that's when the API comes into play. As a free user, you get a little bit of free compute time to try out the web interface and the API. Open Journey is simply Stable Diffusion model fine-tuned on Midjourney v4 images. Every model has different performance characteristics, so the number of predictions that you can run with your free compute time varies. Predictions run on Nvidia A100 GPU hardware and typically completes within 13 seconds. Just make sure to add "mdjrny-v4 style" at the beginning of each prompt.
Prompt Hero • Search the Best Prompts for Stable Diffusion & More
ARTIFICIAL INTELLIGENCE
Prompthero is the biggest prompt database for Stable Diffusion, DALL-E, Midjourney, and other AI image generation models. Search millions of AI-generated art images, and discover the exact words that generated them. Writing prompts for artificial intelligence is not easy. Does everything feel overwhelming and new? Dont worry! We have got this comprehensive Stable Diffusion prompt guide (also featuring other AI models like Midjourney and DALL-E!). This guide contains everything you need to know to get you from absolute zero to creating amazing images, including Stable Diffusion tips and plenty of Stable Diffusion examples.