Vibeke Bertelsen /Udart

l-bfgs and memory issues

1

I am trying to get as large an output image as possible running on an AWS with multiple GPUs. The bottleneck seems to always be the l-bfgs optimiser stage. I...

My script fails if I run in Tensorflow mode (on the cpu) and define the --a-scale=2 parameter. Without this parameter I can run. also --a-scale=1 seems to work ``` My...

Hi I just wanted to let you know that I forked vvopensource in order to be able to control ISF Editor via OSC and use it for performances. Feel free...

can't pickle local object in train_dreambooth.py

3

### Describe the bug When trying dream booth training I get this error ### Reproduction accelerate launch train_dreambooth.py --mixed_precision="fp16" --pretrained_model_name_or_path="stabilityai/stable-diffusion-2-1-base" --train_text_encoder --instance_data_dir="C:\Users\VERTIGO\Documents\my_concept" --class_data_dir="C:\Users\VERTIGO\Documents\classdata" --output_dir="C:\Users\VERTIGO\dreambooth-concept" --with_prior_preservation --prior_loss_weight=1.0 --instance_prompt="a graphical illustration by...

LC_RPATH @executable_path error or libnvrtc-builtins.dylib error

5

When trying to run with gnu support I get two errors. ``` dyld: warning, LC_RPATH @executable_path/ in /Developer/NVIDIA/CUDA-9.2/lib/libcublas.9.2.dylib being ignored in restricted program because of @executable_path dyld: warning, LC_RPATH @executable_path/...

reportedly you cannot run multiple instances of the app and send to syphon. Problably because the name of the Syphon server is hardcoded into CefWithSyphon

Could you give a hint as to how I install glfw? Im on OS X using Xcode.

in0.jpg Traceback (most recent call last): File "/usr/local/lib/python3.10/dist-packages/gradio/routes.py", line 401, in run_predict output = await app.get_blocks().process_api( File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1302, in process_api result = await self.call_function( File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1025,...

any gains to be had on sdxl-turbo?

1

Hi there, I tried compiling a cdxl-model but only get a 0.005 sec speedup or thereabouts. Is there anything to consider when using sd-turbo and sdxl-turbo. My script boils down...