AI & Creativity
4 min read
Endless Automated Refactoring with Codex and Temporal
How I built a self-healing, automated refactoring pipeline using Codex's subscription capacity and Temporal on a home Kubernetes cluster.
Categories
AI & Creativity
Guides and experiment notes on image, video, and music generation AI — ComfyUI, Stable Diffusion, and more
#ComfyUI
#StableDiffusion
#Generative AI
#Image Generation
#Study Notes
#AI
#Video Generation
#Container
AI & Creativity
3 min read
Run on 6GB VRAM! Trying the 'FramePack' Video Gen AI Demo
Generate high-quality AI videos on low-spec PCs with FramePack. This guide covers the official demo setup, requirements, and generation results on 6GB VRAM.
Series
AI & Creativity
2 min read
Stable Diffusion Guide: Image Generation Links
Series: comfyui-image-guide
A curated link collection systematizing Stable Diffusion image generation techniques with ComfyUI, including LoRA, ControlNet, upscaling, and image editing.
Series
AI & Creativity
1 min read
Stable Diffusion Guide: Video Generation Links
Series: comfyui-video-guide
A curated link collection of Stable Diffusion video generation techniques using ComfyUI, covering AnimateDiff, SVD, RIFE, and vid2vid.
Series
AI & Creativity
2 min read
Stable Diffusion Guide: Paper Reading Links
Series: stable-diffusion-survey
A curated link collection of Stable Diffusion paper explanations, covering foundational models to applied techniques for image and video generation.
Series
AI & Creativity
2 min read
Person Extraction with ComfyUI and Impact Pack: Mask to Inpaint
Series: comfyui-image-guide
Automatically generate masks and perform inpainting with ComfyUI and Impact Pack. Learn how to extract people and objects from images efficiently.
AI & Creativity
1 min read
StableDiffusion i2i Comparison: Latent vs ControlNet vs IPAdapter
Compare Latent, ControlNet, and IPAdapter for i2i generation in Stable Diffusion. Discover the best method for composition and reproducibility.
Series
AI & Creativity
6 min read
Verifying 'Flux.1' with ComfyUI: Installation and Results
Series: comfyui-image-guide
Overview of the open-source image generation model Flux.1 and how to use it with ComfyUI. Ideal for those looking to try Flux.1 locally.
AI & Creativity
2 min read
Apply LoRA to Flux.1 in ComfyUI: Steps and Results
A guide to using LoRA with the Flux.1 model in ComfyUI, including setup steps and a compilation of generation results.
Series
AI & Creativity
1 min read
Video Generation AI with ComfyUI: RIFE Edition
Series: comfyui-video-guide
Master RIFE Frame Interpolation in ComfyUI for ultra-smooth AI videos. Learn to configure RIFE VFI nodes and optimize fps multipliers for high-quality results.
AI & Creativity
4 min read
Stable Diffusion Speedup: LoRA for Turbo, Lightning, LCM, Hyper
Summary of LoRA models for faster inference in Stable Diffusion. Comparing Turbo, Lightning, LCM, and Hyper methods for optimal speedup.
Series
AI & Creativity
2 min read
Image Generation AI with ComfyUI: InstantID Edition
Series: comfyui-image-guide
Fix person's face using InstantID with ComfyUI. This guide covers setup, necessary models, and generating consistent faces from reference images.