Kandinsky-2
Kandinsky-2 copied to clipboard
added k-style callback, mac compatibility, v-ram optimization (should merge with PR36)
Added callbacks, Mac Compatibility added Added model offloads to cpu (tested by @Thaevil1 on RTX A2000- 512x512: 6Gb VRAM)
You can test my fork of Kandinsky utilizing these changes in my node engine as well: aiNodes Engine