Hello everyone. I am Dr. Furkan Gözükara. PhD Computer Engineer. SECourses is a dedicated YouTube channel for the following topics : Tech, AI, News, Science, Robotics, Singularity, ComfyUI, SwarmUI, ML, Artificial Intelligence, Humanoid Robots, Wan 2.2, FLUX, Krea, Qwen Image, VLMs, Stable Diffusion
Hi everyone. I needed a little help I have a rtx 3070 ti which kind of training suits my pc specs. Specs are ryzen 7 5800x 32gb 3200mhz ram galax rtx3070ti i am trying to teach stable diffusion my face by using textual embedding training but its too slow for some reason even with xformers on.
Thanks for the help I joined the Patreon. I’ll be using most of my time training character Loras. I’ve done decent so far but know I can do better. I don’t necessarily need the notebook I have a computer with a 4090 and one with 4070 and each have 32gb of ram. I’m going to try your stuff, my concern with anime and regularization images using realistic people is anime makes the adult women look like children. I use girl as the class prompt instead of woman for that reason. I’ve never tried woman though so I wouldn’t know the results
@Dr. Furkan Gözükara Furkan hocam is it possible to train SDXL Turbo with kohya? I tried one but after the training turbo model just became as slow as sdxl1.0 :x
So Speccy and Sys Info do not detect the full amount of VRAM your card has. It always detects 4 GB of VRAM regardless of how much your card has. Is there a setting I'm missing here?
Did you find a proper workflow for this? I tried using @Dr. Furkan Gözükara 's Controlnet scripting, thinking it was the most comprehensive, but was still getting blurry or "smudged" results when attempting to upres.
If you are also getting tired of trying to find good images among thousands of generated images you don't have to anymore. By using #DeepFace AI library, you can sort images by their similarity to your target images and quickly find the best Stable Diffusion #DreamBooth LoRA trained model generated images. I am explaining everything step by step...
Thank you! Also do you have any idea how significant the difference between a 4070 and 3090 would be for SDXL? 2x faster, 4x faster, not quite so large?
Updated for SDXL 1.0. How to install #Kohya SS GUI trainer and do #LoRA training with Stable Diffusion XL (#SDXL) this is the video you are looking for. I have shown how to install Kohya from scratch. The best parameters to do LoRA training with SDXL. How to use Kohya SDXL LoRAs with ComfyUI. How to do checkpoint comparison with SDXL LoRAs and m...