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
A few weeks ago I generated a Lora from ~40 training images, at 150 steps per image (which should be around 6000 steps in total), but the final model it generated says it has about 30k those steps. I didn't use any class images. The training was really quick too (less than 2hr on 8gb VRAM). Is there a setting that I accidentally clicked to do all of those steps? Now when I try training, 5k steps stays 5k steps, and 30k steps takes 6+ hours
I also ran into an issue while lora training, set everything up but it gave an oserror 28 ran out of disk space when it’s just starting up. Decided to install python elsewhere but now both automatic1111 and kohyass can’t find python. I tried the instructions here but still not working. Do I need to set up automatic1111 and kohya ss again?
How to install Python, have multiple Python installations, set system wide default Python version. How to compose venv for any Python installation, change Python default path, and install SD web UI properly. Discord: https://bit.ly/SECoursesDiscord.
If I have been of assistance to you and you would like to show your support for my work, please...
Discord : https://bit.ly/SECoursesDiscord. Torch 2 / Pytorch 2 is now supported along with new DreamBooth Automatic1111 Web UI extension. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on https://www.patreon.com/SECourses
@Furkan Gözükara SECourses hey there! I managed to get decent results with the model we made yesterday for some reason it did 20 checkpoints so I had to run xyz plot on 20 different checkpoints 2 of them were incredible, it was pretty hard to get the eyes looking normal and not twisted.
If I wanna update the model I need to retrain the model ? Or is there an easier way
And another question I watched olivio’s video and he doesn’t say much about the technique he used but how did he create this picture with realistic vision 2.0?