At its core, Stable Diffusion is a deep learning model that can generate pictures. Together with some other models and UI, you can consider that as a tool to help you create pictures in a new dimension that not only you can provide instructions on how the picture looks like, but also the generative model to brainstorm what you didn’t specify. In this 7-part crash course, you will learn from examples how to make use of Stable Diffusion to finish […]

Photography has been around for more than a century. There are many old photos around, and probably your family has some, too. Limited by the camera and film of the time, you may have photos of low resolution, blurry, or with folds or scratches. Restoring these old photos and making them like new ones taken with today’s camera is a challenging task, but even you can do that with photo editing software such as Photoshop. In this post, you will […]

Stable Diffusion has taken the AI art world by storm, empowering users to generate stunning and imaginative visuals with just a few text prompts. This opens exciting possibilities for creatives, including crafting impactful commercial posters. In this post, we’ll delve into using Stable Diffusion to design a compelling poster for a product. After finishing this post, you will learn: How to prepare a photo of a product for use in Stable Diffusion How to create an appealing commercial poster without […]

Many people write in their jobs. Not everyone is a novel writer; some write technical documentation, business plans, news articles, and even blog posts. In those writings, illustrations are not essential but often good to have. They are decorations, interpretations, or visual explanations of the text. However, you probably do not want to spend too much time or do not have the drawing skills to create the illustration. Stable Diffusion is here to help! In this post, you will see […]

Stable Diffusion is a powerful tool that helps you generate pictures. It is fun to play with the generative AI tool. But it would be useful if the tool could help you in a real job. In this post, you will see how you can leverage the power of Stable Diffusion to work on something realistic and practical. After finishing this post, you will learn: The reasoning process to decide how to use Stable Diffusion Augmenting other tools with Stable […]

Stable Diffusion can generate an image based on your input. There are many models that are similar in architecture and pipeline, but their output can be quite different. There are many ways to adjust their behavior, such as when you give a prompt, the output will be in a certain style by default. LoRA is one technique that does not require you to recreate a large model. In this post, you will see how you can create a LoRA on […]

Stable Diffusion is trained on LAION-5B, a large-scale dataset comprising billions of general image-text pairs. However, it falls short of comprehending specific subjects and their generation in various contexts (often blurry, obscure, or nonsensical). To address this problem, fine-tuning the model for specific use cases becomes crucial. There are two important fine-tuning techniques for stable Diffusion: Textual inversion: This technique focuses on retraining the text embeddings of a model to inject a word as a subject. DreamBooth: Unlike textual inversion, […]

Stable Diffusion is a deep learning model that can generate pictures. In essence, it is a program in which you can provide input (such as a text prompt) and get back a tensor that represents an array of pixels, which, in turn, you can save as an image file. There’s no requirement that you must use a particular user interface. Before any user interface is available, you are supposed to run Stable Diffusion in code. In this tutorial, we will […]

There are many ways you can access Stable Diffusion models and generate high-quality images. One popular method is using the Diffusers Python library. It provides a simple interface to Stable Diffusion, making it easy to leverage these powerful AI image generation models. The diffusers lowers the barrier to using cutting-edge generative AI, enabling rapid experimentation and development. This library is very powerful. Not only you can use it to generate pictures from text prompts, but also to leverage LoRA and […]

Inpainting and outpainting are popular image editing techniques. You have seen how to perform inpainting and outpainting using the WebUI. You can do the same using code as well. In this post, you will see how you can use the diffusers library from Hugging Face to run Stable Diffusion pipeline to perform inpainting and outpainting. After finishing this tutorial, you will learn How to perform inpainting using the corresponding pipeline from diffusers How to understand a outpainting problem as a […]