Versatile-Diffusion
Versatile-Diffusion copied to clipboard
Versatile Diffusion: Text, Images and Variations All in One Diffusion Model, 2022
For people only interested in the variation part, it would be good to have the VD-Basic checkpoint public.
Hey guys, Thanks for the amazing work! I am trying to run versatile diffusion inside a docker container and I got the following error ``` ImportError: /opt/conda/lib/python3.8/site-packages/fused_layer_norm_cuda.cpython-38-x86_64-linux-gnu.so: undefined symbol: _ZN8pybind116detail11type_casterIN3c108ArrayRefIlEEvE4loadENS_6handleEb...
Thanks for your great work. Could you share your ControlNet architecture mentioned in Appendices? I find that VD's Unet isn't the same as SD. For example, number of downsampling blocks...
I can't find the parameters of the training
I don't find this file and evaluator.py in lib, could you give them to me? my e-mail is [email protected], thank you very much.
Hello! After setup I ran the app.py but get the following error: `######## # v1.0 # ######## ####################### # Running in eps mode # ####################### making attention of type 'vanilla'...
Thank you for your work! I didn't find the inference.py file.
Hi, Is there an example script to combine VD with ControlNet as mentioned in the paper?. Thanks
For the case when x_t is given as input there was a typo breaking the code.
Are you going to add in-painting?