Sun Yat-sen University Open Source Diffusion Model Framework

Sun Yat-sen University Open Source Diffusion Model Framework

Machine Heart Column Machine Heart Editorial Department In recent years, image generation models based on Diffusion Models have emerged one after another, showcasing stunning generation effects. However, the existing research model code frameworks suffer from excessive fragmentation, lacking a unified framework system, leading to challenges such as “difficult migration,” “high barriers,” and “poor quality” in … Read more

Getting Started with Stable Diffusion WebUI

Getting Started with Stable Diffusion WebUI

This article mainly introduces the practical operation methods of Stable Diffusion WebUI, covering prompt derivation, LoRA models, VAE models, and ControlNet applications, along with actionable examples of text-to-image and image-to-image generation. It is suitable for students interested in Stable Diffusion but feeling confused about using Stable Diffusion WebUI. We hope this article can reduce the … Read more

The Powerful Ability of Stable Diffusion to Change Lighting

The Powerful Ability of Stable Diffusion to Change Lighting

In the era before Stable Diffusion, post-processing lighting in photos relied heavily on Photoshop. For example, adding an exposure layer. This technique is convenient for simple-shaped objects because lighting effects can be well simulated. However, for complex subjects like humans, achieving a natural lighting effect requires a good artistic background and a graphics tablet. The … Read more

Recommended Versatile StableDiffusion Models

Recommended Versatile StableDiffusion Models

Today, we’re going to discuss an incredibly interesting topic in the field of AI painting: why can Midjourney easily handle various styles with a 5.2 model, while Stable Diffusion requires us to switch between countless models? 🧐 In Stable Diffusion, creating an image might require you to choose from models like Realistic, Anime, 2.5D, etc. … Read more