auto111 lora lion, i can't get my model to look like my subject
auto111 lora lion, i can't get my model to look like my subject
Fi didnt test lora yet
Ftoday i will do another dreambooth hopefully
Lhi, i am looking at the Lora + Dreambooth video and when starting automatic1111 it complains about libnvinfer missing
Lhere 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.
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.
Ldo i just need to do "pip install tensorrt"?
Fyou are on runpod right
Fdid you follow this video?
Lyes
FYouTubeSECourses - Software Engineering Courses
RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. How to install and start using #DreamBooth extension on #RunPod SD Web UI template. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on 
https://www.patreon.com/SECourses
DreamBooth extension: ht...
https://www.patreon.com/SECoursesDreamBooth extension: ht...
Li just edited the requirements.txt and requirements_version.txt files
Fthese are probably only warnings
Fit should work did you test
Fi will start another runpod install and training soon
Lno how do i test if it is only using the CPU vs GPU?
Fgeneration some more class images
Fyou will see from it/sec
Lok
Fwhen training tell me that
Lhow 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)
Lwith LORA
Lif it takes 20 minutes or so it would be too slow to demo
Fi think would take such
Fmake test first
Lyes that's what i am trying today
Lok my next issue is this:
extensions/sd_dreambooth_extension/requirements.txt:discord-webhook~=1.1.0
requirements_versions.txt:clean-fid==0.1.29
but:
clean-fid 0.1.29 requires requests==2.25.1 and
discord-webhook 1.1.0 requires requests<3.0.0,>=2.28.1
extensions/sd_dreambooth_extension/requirements.txt:discord-webhook~=1.1.0
requirements_versions.txt:clean-fid==0.1.29
but:
clean-fid 0.1.29 requires requests==2.25.1 and
discord-webhook 1.1.0 requires requests<3.0.0,>=2.28.1
Lok so i did a "git pull" in the /workspace/stable-diffusion-webui directory, it seems that was a bad idea
Lperhaps not a bad idea after all
Lbut it didn't solve the above issue
Lok so i got past it by changing requirements_version.txt to clean-fid 0.1.34
i hope nothing breaks
i hope nothing breaks
Fye these requirement confliction scks :/
Fimg2img batch controlnet initial test
F
Ldo i need to install tensorrt to get rid of the libnvinfer shared library issue?
Fyou shouldnt be have to
Bpossible 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?
what should i change in my training to get better prompt weight in my outputs?
Fi think possible
Ftoday i will try with 274 images
Fto teach style
Fand 137 images to train myself
Bcool, will there be a video with the results?
Fto get more prompt weight probably more training
Fye
Fi am working on corridor crew style video
Fanimation
Byeah i didn't train much since it takes so damn long. it was looking really good so i stopped the training, i guess i need to try much more
Fyep training takes huge time
Fwhen more images to train
Fi will post more classification images to patreon. aesthetic and photo of man
IHello 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.
IAs to the training, I was able to get 60% of images that look like the subject trained, nothing as good as in your videos.