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
I thought because OneTrainer allows different resolutions, it would be the same for regularization images. I'm not to that part of the tutorial yet lol.
Just for clarification, your regularization images are mostly of people of color, and I'm training an east Asian and white person mostly. The ethnicity of the people in the regularization images don't have an effect on the training, right? Regularization images are for help with poses?
Edit: just looked at the latest folder of regularization images and it's a really good mix of different ethnicities, so I guess you can ignore this question, lol.
With an RTX 4070 12gb, training 1024x at float16 using your tier1sdxl 10gb config, do you know a rough estimate of how long it would take to train using 25 images? Just a ballpark figure. I'm wondering if I should I set it and leave the house to run errands for a few hours, or if I should set it and leave it to run overnight.
So I stopped the training at 3100 and tested the saved model, and if I use all the common tags from the training in the same prompt, I get a pretty damned good result. But if I remove all or even just some of those common tags, or if I try to use any kind of creative prompt (like "sitting in a golden throne wearing golden armor"), the face likeness goes away.
Get more from SECourses: Tutorials, Guides, Resources, Training, MidJourney, Voice Clone, TTS, ChatGPT, GPT, LLM, Scripts by Furkan Gözükara on Patreon
Yes, that means the model you're using for inference of that word "boob" is still trained "stronger" than your LoRA concept. If you're training say the concept "girlfriend woman" with captions on your dataset you could leave out any reference to breasts. However it may make your LoRA less flexible. You could also experiment with doing the caption dropout option (available in Kohya) or for an experiment train your LoRA with no captions and see if the accuracy increases...
Ahhh, that makes sense! I created the training data before watching the tutorial, so I forgot that the caption text was included in the folder with the training images already. Damn it, back to the drawing board, lol.
Seriously though you’re probably sick of me saying this over and over but I and I’m sure this community is very thankful for everything you do. I’ve learned a ton here.