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
#Kohya SS web GUI DreamBooth #LoRA training full tutorial. You don't need technical knowledge to follow this tutorial. In this tutorial I have explained how to generate professional photo studio quality portrait / self images for free with Stable Diffusion training.
I would like to buy an external GPU or put together a setup. I want to use an eGPU because I want to use the device on different computers. Among other things, also on a Mac Studio M1 and on an Intel Mac i9.
I have now watched various videos, but am still unsure. I only need the GPU for stable diffusion, ML and video editing/rendering 3D - not for gaming....
So would it make sense to buy one of the older Quadro cards and use it? The M6000 is available with 24GB for just under 600EUR, the Tesla M10 with 32GB as well. Does it make sense, due to the huge amount of VRAM, to use one of these older cards and save a lot of money? Does anyone of you use a setup with an external GPU and can advise me in this regard?
Hi guys, I'm trying to follow the last lora tutorial, but I'm having some problem with folders when starting the train, I get "No data found. Please verify arguments (train_data_dir must be the parent of folders with images) "
btw i did at least 3 test and didn't get anything good, I will try again tomorrow... I had the best result with your other video the "standard" one but converting the setup to lora then saving checkpoint
Is anyone else having this issue when generating i2i: FileNotFoundError: [Errno 2] No such file or directory: NEVERMIND: problem occus when adding [prompt] to filename, resulting in too long a filename for python on outputting. Solved by removing the prompt from the name. Anyone know how to preserve the beginning of the prompt in the filename??
I used the doc to change the filename with the prompt in it, but when I send it image to image there's an error because of this change. Anyway, I guess for now I can't include the prompt. I'd like to have it in the filename so I can sort my renders into smart folders in my image browser, which uses the keywords in the prompt. But auto1111 seems to be broken. Cannot image to image when the fjlename is so long. See what I mean?
Has anyone gotten better output on any repo than JoePennas? It's always the best no matter what I've tried. It's just sooo slow relative to newer optimized diffusors repos
getting this error trying to reinstall and cant fix "Error no kernel image is available for execution on the device at line 167 in file D:\ai\tool\bitsandbytes\csrc\ops.cu"
Shit... My A1111 is borked (again). Just suddenly it won't start. I have managed to start it without --xformers, but that has allways worked before. Maybe I need to update to 0.0.19 (I was running 0.0.17 which worked better than 0.0.18), but now for some unknown reason it's not working at all