Vincent Type to start searching
Preface: One of the use cases for sdwebui is old photo restoration. Common old photo restoration tools existed before sdwebui, including GFPGAN and CodeFormer. However, combining them with Hires.fix in sdwebui yields even better results.
Preface: PNG Info is a built-in feature of sdwebui that is essential in everyday image generation workflows. It allows you to upload an image, read its meta information, parse the generation parameters, and conveniently send them to other features like txt2img, img2img, and inpainting.
Preface: Embeddings and text inversion both refer to textual embeddings, which can be simply understood as a collection of prompts used in both negative and positive prompts. Using Embeddings: Installation - After downloading embeddings, place them in stablediffusionwebui/embeddings. Usage - Select the desired embeddings under the embeddings tab.
Preface: If checkpoint determines the main effect and style of your generated images, and embeddings mainly serve as negative prompts to avoid undesirable effects, then LoRA is for fine-tuning to achieve the specific effect you want.
A guide to Stable Diffusion Checkpoints — what they are, how to install and use them, visual comparisons of popular checkpoints from Civitai.
Preface: The previous section introduced the algorithm differences in Hires.fix. This section covers the denoising strength parameter of Hires.fix. We keep other parameters fixed for comparison.
Preface: SD generates 512x512 images by default. Setting the width and height too large on the first generation may cause unexpected issues. It is recommended to generate at 512x512 first, then upscale later using high-resolution methods. This section introduces the Hires.fix algorithms.
Preface This chapter introduces the samplers in sdwebui. Sampler A sampler is the sampling method used during the SD image generation process. Using the following prompt for txt2img, with a fixed checkpoint and fixed seed, we compare the results of different samplers. Prompt (Chinese): A boy sitting on a chair, upper body, close to the window, blue shirt, black hair, wearing glasses, facing the camera, with the window on his left side.
Preface This section introduces the sampling steps in sdwebui. Sampling Steps The previous section covered samplers: https://blog.vincentqiao.com/sdsampler Sampling steps refer to the number of noise addition and denoising iterations during image generation. Prompt (Chinese): A boy sitting on a chair, upper body, close to the window, blue shirt, black hair, wearing glasses, facing
Preface After installing sdwebui locally and getting familiar with the interface, you might feel lost about how to actually generate images. You can start by setting a few small goals: 1. Find an IP, anime character, or celebrity you like, and try generating images of them. 2. Take an ordinary photo of yourself and try swapping it into a cool scene.
Preface: The previous chapters covered SD installation. This chapter introduces the sdwebui interface. Introduction: From top to bottom it includes: Model selection area for choosing checkpoint models, main function tabs for switching between features like txt2img, img2img, and PNG info, prompt area, generation parameters area, and image preview area.
Preface: This section introduces the sdwebui file structure. https://github.com/AUTOMATIC1111/stablediffusionwebui. File Structure: configs - configuration files, embeddings - embedding files, extensions-builtin - built-in extensions, extensions - user extensions.