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 there. I am asking myself (and you here) what would be the best way to chieve the best results when I have a trained image like this (https://huggingface.co/plasmo/woolitize-768sd1-5) and want to ake a woolitized picture of myself. I trained that image on my face, but it seems to loose its "woolitizing skills". what could i try instead?
Hi all, I'm new on Stable Diffusion, I'm following the Dr. Furkan Gözükar to install it using A1111 WebUI. Amazing job, thank you. I can generate images, but I'm more interesting in training the IA (I have a 3090 gpu). But the extension Dreamboot it not working for me. I can install it, but when I reset the webUI the prompt give me some error.s For example: "NameError: name 'DreamboothConfig' is not defined". And the Dreambooth tap is not there. I've reinstalled A111 WebUI several times with 1.5 and 2.1 model and it is always the same error. Anyone knows why? There is another alternative extension I can use? Thank you.
The command is already there: set "REQS_FILE=.\extensions\sd_dreambooth_extension\requirements.txt". Nothing, same problem. Is there any alternative extension I can use? Is Dreambooth the most popular?
"We also need a newer version of diffusers, as SD-WebUI uses version 0.3.0, while DB training requires >= 0.10.0. Not having the right diffusers version is the cause of the 'UNet2DConditionModel' object has no attribute ' enable_gradient_checkpointing' error message, as well as safety checker warnings"
@Furkan Gözükara SECourses I had to reinstall auto1111 and followed the steps on downgrading cuda. But when i downgrade and start webui i get this error
:\A1111\stable-diffusion-webui\venv\Scripts>pip show diffusers WARNING: Ignoring invalid distribution -rotobuf (c:\a1111\stable-diffusion-webui\venv\lib\site-packages) WARNING: Package(s) not found: diffusers
Yes, 1.5, but also others. Same results. I spent all night trying different settings. In my case changing bf16 to fp16 fixed it. The wizard may suggest one option, but you have to test it first to see if it actually works, before you do the whole training.
You are getting much better results than I got, even with more steps, and so on. Can you resume your the settings that work for you? I know they can't be replicated, but it helps us understand how training works.
I don't think that is necessary anymore, I think even --xformers are not needed. Major changes happened last night while I was working, so I did a fresh reinstall of A1111 too, and it worked much much better without any downgrade, without --xformers. The only problem is the damn Dreambooth, so we have to wait for Dr. Furkan's new tutorial for that.