notnanton / diffusion_gen Goto Github PK

TypeError: Descriptors cannot not be created directly. If this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc >= 3.19.0. If you cannot immediately regenerate your protos, some other possible workarounds are: 1. Downgrade the protobuf package to 3.20.x or lower. 2. Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python (but this will use pure-Python parsing and will be much slower).

I got all the dependencies installed successfully, but hit this error, which I haven't been able to find a solution for.

Hello, and thank you so much for this project!

I've been using it a lot and I'd like to know how I can change how often it saves to partials folder.

I find way more useful to see progress on lower rates (%)

Thanks!

I am attempting to install this in a JupyterLab notebook on JarvisLabs.ai. I put all the files into the home directory and run
ipython3 diffuse.py

I get this error first:

When I run it again, I get the following:

Any suggestions? I am pretty new to this but want to be able to use an A100 consistently, which you can't do in Colab.

My directory looks like this. I noticed that /out_diffusion/models is empty

Hi,

I can't seem to get initial image to work, any ideas on where I'm going wrong?

Hello, thanks for your project, after the first generation, at the end of processing (250/250) i had this error message, but i am a very newbie in python so i don't really know what to do to fix it :

OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized.█████████████████████████████████████████████████████████████| 250/250 [05:20<00:00,  1.54s/it]
OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://www.intel.com/software/products/support/.

I seem to be stuck here without any progress, any ideas?

I installed IPython as a PIP package, and then ran the diffuse.py file with the --setup argument, but it just gives me this.