Text to cartoon model
#200
by freeb - opened
I want to speed up the stable diffusion 3 model by reducing the output image's resolution and dumbing it down. The input would be text, and the output would be four(4) cartoon images about 300kB-600kB in size and 640x480 pixels.
Any thoughts and suggestions around this would be much appreciated.
I am happy to collaborate with whoever is interested.