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
here is the complete error message: 2023-03-23 18:03:19.866094: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /workspace/stable-diffusion-webui/venv/lib/python3.10/site-packages/cv2/../../lib64: 2023-03-23 18:03:19.866207: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /workspace/stable-diffusion-webui/venv/lib/python3.10/site-packages/cv2/../../lib64: 2023-03-23 18:03:19.866225: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
how fast can i expect it work with 10 pictures? I want to show it to some people who are interested and i am wondering how many minutes training will take (RTX 3090)
possible to train for style with a couple hundred images? i saw the recent midjourney video uses thousands of images for the style training... i tested with a few hundred and got decent results but i was not able to drive the output via the prompt (results looked good... but mostly just random images in my style regardless of prompt)
what should i change in my training to get better prompt weight in my outputs?
Hello again, after a fresh install of A1111 and no xformers, I can confirm that everything is running fine, and loading faster than before. But I am not using A1111 for training. Dreambooth has to be installed manually, but it's OK.
When I do it with SD 2.1 or Protogen, it gets worse, no resemblance at all. Also the biggest problem in general is that if use toke + class I get some results, if I just do the usual "closeu portrait photo of...." I get other people!!!
Perhaps a slight side step from current conversation, but I'm interested in training SD on some pixel art characters for use in a platform game. I've tried training it to understand that I want a white background around each image but I haven't had any luck. This was with textual inversion. Does anyone have any suggestions? (The image below is the kind of output I'm after, white background surrounding the subject)
By the way Dr. Furkan, I still seem to have some confusion with numbers of steps/epochs, because the UI says "steps-epochs" and it's confusing. So I trained with values from 150-300 (whatever that is) and got models that go up to 12.000 (whatever that is). Could you please explain this in simple way?