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
@Furkan Gözükara SECourses I'm on that page atm. I ask because the hours are much longer then expected. To confirm the 48gb config should be 40 repeats and 200 epochs? (48GB_GPU_28200MB_6.4_second_it_Tier_1)
@Furkan Gözükara SECourses I appreciate the confirmation. I would recommend double checking the epoch and repeat for your config, it might have mistakes in this area.
@Furkan Gözükara SECourses I see. That makes the results even more impressive! But the images are all of your face. Do you know if its recommended for styles like oil paintings?
That's actually impressive. I always see in your videos pictures of yourself. Have you tried mixing it up with styles to see if you get more views/subscriptions?
I would recommend it. Training the images of the face is good for people who make celebrity loras etc, but most of us want to train on styles, concepts etc.
Hi @Furkan Gözükara SECourses I use your Batch_Size_7_48GB_GPU_46250MB_28.9_second_it_Tier_1. In the config I only see 1 GPU not multi GPU, so you only increase the batch file to 7 right. What about the time and quality if I use your batch 7, does it save me 7 times less than your batch 1 config and the quality is the same ?
@Furkan Gözükara SECourses saw your Flux 15 images vs 256 analysis and it was very insightful. Obviously 256 images may not be practical in many cases and would take a long time on Batch 1. Let's say I have the more realistic option of using 30 or 40 images. Do you think that is better than 15?