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 was using prior preservation but it never seemed to train the model, i went in the dreambooth chat and one of the mods said i didn't need to use class images to train
i was using images generated by class, but it never seemeed to train the model correctly, their faces were either blurry, or looked nothing liek the subject