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’ve noticed training flux on Renaissance painting details is polishing the result (giving a slightly plastic feel), not picking up the granular textures of paint, crack etc. Do you know why is this? Is there parameters such as learning rate which will effect this or perhaps it’s the architecture of flux itself? When training the same images on kohya Sdxl, the trained model will clearly be show the texture of painting and canvas surface etc.
Get more from SECourses: Tutorials, Guides, Resources, Training, FLUX, MidJourney, Voice Clone, TTS, ChatGPT, GPT, LLM, Scripts by Furkan Gözü on Patreon