Jader Martins
Jader Martins
A hack I found is to copy the output html and generate the svg with: https://www.hiqpdf.com/demo/ConvertHtmlToSvg.aspx
Your parallelization should be done under GPU-level, not system-level. The GPU is blocked until it finishes each inference. You should change the guidance function in a manner that it can...
As I mentioned before, guidance cannot do this at the moment; you would need to rebuild a lot of guidance's source code to allow batched inference. My suggestion is to...