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 Dr, I had everything working well until yesterday. I tried using the earlier version of automatic, but never worked properly. After this new video I went carefully step by step several times with new runpods everything the same that you used. Last night before this video I was always getting Cuda related errors. Dreambooth wasn't using GPU properly... Now I am getting this error:
Yes. I think I followed the video exactly. If no one else has the same issue, it must be me who made a mistake. I will try again. I am using RTX A4500, 62 GB RAM, 10GB Disk, 150GB Volume. I notice the server log says some interesting things
One thing iv noticed with learning rate .000001 is when you generate ur image, we will see preview and it looks like a perfect face from your data set. However, when generating is done they don't actually look like what u see during generating stage. What could be an indication or hope to make this improve. Training in dreambooth still not getting better precise look from ur subject at least 5 images from hundreds of generation clicks Anyone share your experience?