dall-e-baby
dall-e-baby copied to clipboard
Generate and use CLIP generate images
Hello again! I trained my model now and i'm wondering if I have overseen something:
Does your code provide the possibility to generate Images (e.g. 512 like in the original DALL-E paper) and pick the 12 best generated images with the CLIP method? If yes, in which file is it hidden?
Thanks a lot again for you help!
You can pass --res=512
but the convnet is something you will have to get good configuration. In my case it's a bit hacky, if you can see the architecture once and suggest changes it would be great.