Originally I wanted to make one big tutorial for training and generating but I'm splitting it into two parts and the second one should come "shortly" after. I know I'm kinda late to the party with it, but perhaps someone would like to use my flow :) (there is an attachment archive with my settings that I cover in this article) Since I train on RTX 3090 with 24 GB VRAM I am not using any memory optimizations, if you wish to try my settings but have less VRAM - you could try applying the known options that can bring the memory requirements down but I do not guarantee the quality of the training results in that scenario. Setup I am using kohya_ss from the branch sd3-flux.1 -> https://github.com/bmaltais/kohya_s If you have a kohya setup already but are training different models and you are not on that branch, I suggest duplicating the environment so that you do not ruin your current one (since the requirements are different and switching back and forth between branches might not be a good idea)
After a brief hiatus, ComfyUI returns stronger than ever with major performance improvements and new node types. This deep dive covers the latest updates and shows you how to build efficient generation workflows.
Join our weekly exploration series where we push Flux to its limits with experimental prompts, unconventional workflows, and creative challenges. Each episode features community submissions and real-time problem solving.
Transform any 2D image into a textured 3D model using our custom ComfyUI workflow. We integrate TripoSR for instant mesh generation and show you how to export directly to Cinema 4D or Blender.
Step-by-step guide to training your own LoRA models using Kohya SS. Covers dataset preparation, optimal settings for different styles, and how to integrate trained models into ComfyUI workflows.