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 deployed runpod/stable-diffusion:comfy-ui-5.0.0 but it won't let me open the checkpoint folder. I'd like to load in my dreambooth safetensors. Any idea how to do this?
was updated yesterday just getting the new update transferred to all the servers. still transferring this morning.
Basically when you rent and start the Notebook in the terminal you will see a URL that is the IP address of your vm. Copy the whole thing including the token part of the URL and then you can paste it into your own computer browser
@Dr. Furkan Gözükara hey again, I haven't downloaded a safetensor from huggingface to runpod before and don't think i'm doing it correctly. I've uploaded the safetonsor to huggingface and have typed wget with the hugging face link. However when this is installed in the lora folder, it installs the whole hugging face folder, when I only need the safetensor. Do you know how I can just instal the safetensor?
@Dr. Furkan Gözükara thanks for the response, but something is not right I did this training many times and I never seen a base model to get so cooked so fast, 30 repetitions 320 imágenes and the model brakes , may be is my dataset and nobregularization but probabably for my case I need to reduce de learning rate or something , this images were used like a sanity check, thanks
I train locally on a 3090, I use your last 24gb slow preset, I was changing some parameters like crossatention for a speed up with no gradient checkpointing, I dont remember changing anything else
other questions did you tried this new learning rates on the base model for a run at least, may be works perfect on realvis4 but is too high for the base model
thanks for your great work, may be, be good if you make a run with your dataset, same settings and samples on the base model to be sure that is consistent on all scenarios.