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 actually quite recommend an online ComfyUI running platform called Runinghub. You don't need to worry about ComfyUI environment errors. Basically, the latest technologies can be experienced or there are workflows available on it in a timely manner. The vast majority of them can be used directly and can also be downloaded. Although this may seem like an advertisement, I've actually subscribed to an annual membership myself. I use a 48G 4090 to run workflows and applications. If anyone needs it and it's appropriate, I can send the link.
ive just gone through all this and i think my dataset might be the problem but at the same time i have good pics that should have generated the picture... the page you recomended was pretty good and yes.. opened my eyes abit but at the same time.. made me more confused.. i used your presets so the set up isnt the problem... my images might be..but im still not sure what could be the problem.. i just got more confused and dont know who or how to ask for assistance
I also have another question.. the answer migth be somewhere but i havent come across it yet.. in your video you said one can have as many consepts as theyd like 1. can i have a consept for the face like in your video with the masks and have another consept to do the whole body inclusive of face.. 2. the lora is about 6gb so is it loaded as a checkpoint or using a lora loader..
can someone take a look at my dataset images and tell me if theyre good or not.. im training for SDXL and im running mad why my training isnt even close to okay..im using one trainer but none of my trainings have been good