remybonnav
remybonnav
### Is there an existing issue for this? - [X] I have searched the existing issues and checked the recent builds/commits ### What would your feature do ? Adding training...
I don't know if it is an issue due to Gradio use but when I generate say 5 pictures in a batch. After the generation is done, it takes at...
Hi, I am testing now Dreambooth with colab. I was wondering if we really need to copy the original sd1.4 model to google drive? It takes a lot of space...
most of the time when you want to change a model, the max RAM memory is reached. even if loading a 2gb model. Why is there so much loaded in...
Is it normal that now the Unet is trained first before the text encoder? Before the text encoder was trained before the unet.
There are many models downloaded during inference which is really annoying, can't we just have a download of all models at the beginning?
How can I pass the path of the input audiofile in the pipeline? In the kaggle notebook you are passing a dataset, should we just replace by a path to...
I don't get how I can link to the model on a local indtall. Should I replace /openai/largev2/ by the path of my model on the disk? And should I...
Is it possible to get the predicted aligned error files (PAE.json) when running the RFdiffsuion notebook? Thanks a lot.
Would it be possible to allow the user to select the model Complex_beta_ckpt.pt in order to design binders that are not only helical?