AI & Creativity
Guides and experiment notes on image, video, and music generation AI — ComfyUI, Stable Diffusion, and more
IPAdapter adds image prompt functionality to Stable Diffusion. We explain its architecture, benefits, and impressive evaluation results.
Master Inpainting with Stable Diffusion in ComfyUI. This guide provides a workflow for masking, prompt adjustment, and adding new elements to images.
Extend your images naturally with Outpainting in Stable Diffusion using ComfyUI. Learn to expand your canvas using Feathering and Padding nodes.
Control art style and composition freely using IPAdapter with Stable Diffusion. We introduce the specific settings and usage in ComfyUI.
AnimateDiff enables video generation in SD models. We explain Domain Adapters, Motion Modules, and the mechanism for high-quality animation.
Control Stable Diffusion outputs through language vectors. We explain the mechanism for beginners and compare it with LoRA for better image control.
ControlNet enhances Stable Diffusion by enabling precise control over character postures. An introduction to its basic concepts for AI beginners.
Learn how LoRA adds small layers to large models to achieve high performance while reducing computational costs. A brief introduction to the method.
Master Textual Inversion in Stable Diffusion using ComfyUI. This guide explains how to use embeddings for goblin-style outputs and improved negative prompts.
Explore the inner workings of Stable Diffusion, from basic diffusion concepts to Latent Diffusion Models (LDM) and the theoretical process.
Maximize ChatGPT's potential with Custom Instructions. Learn how to automate prompts, set personas, and improve response accuracy with practical tips.
Generate videos using AnimateDiff with Stable Diffusion. We cover model roles, ComfyUI setup, and specific workflow steps for high-quality video.
