Jesse Andrews

I also want to get AIT supported. Which will require this style of generation. Whether yield or all at once is orthogonal On Sat, Apr 1, 2023 at 7:41 PM...

I've implemented this for canny in https://github.com/anotherjesse/dream-templates/commit/efa6bb903c1c1926a4f19aa881779d297a21366b

cv2 is used to generate sample input files, I wonder if it could be an option that isn't required? If cv2 isn't installed and a video is required, we can...

To test this, I'm running inference on my dev machine with: docker run -ti -p 5000:5000 --gpus=all r8.im/cloneofsimo/lora@sha256:fce477182f407ffd66b94b08e761424cabd13b82b518754b83080bc75ad32466 alternatively I could run a dev version using cog + checkout: cog...

Andreas 0:  Andreas 100:  Andreas 999: 

Zeke 0:  Zeke 100:  Zeke 999: 

@cloneofsimo I have all 1000 pngs of zeke/andreas if this is useful.

I was able to compile and run it on the CLI by doing: ``` % swiftc transcribe/main.swift % ./main {"isFinal":false,"text":"Hey"} {"text":"This","isFinal":false} {"text":"This is","isFinal":false} {"text":"This is a test","isFinal":false} ``` I love...