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
Thank you so much to @Dr. Furkan Gözükara and @Sandstormleader after several hours of training and solving some errors the model came as I expected this is definitely a game changer process
If I generated on clip skip 1, the model was inflexible, but on clip skip 2 everything was fine. And I thought right: I trained it with clip skip 2 and then clip skip 1 can be generated well.
If i train my images 1024 x 1024 on dreambooth, will my model have better quality than generated with 512 x 512? Does that also mean that i will have to generate my images 1024 x 1024 with my model?
@Dr. Furkan Gözükara By chance are you planning or you already have a tutorial of the importance and explanation of the image regularization data? how this works also with the caption description?
I'm not sure but I think you can. I'm able to train 512 on 8GB so 12GB should be just enough for 768 (gradient checkpoint ON). Also my experience is if I train (lora) in 768 I get good results on 768 images but worse results on 512 compared to a 512 training.