Doodles — the entertainment brand behind illustrator Scott Martin's iconic pastel artwork — is launching Doodles AI, powered by PRISM 1.0, a generative model trained on their entire visual body of work. The engineering is by @thesystms , built on ComfyUI open-source infrastructure. The model that makes this work isn't just technical. It's philosophical: → Users don't just consume the brand — they co-create it → Every generation feeds back into the model via reinforcement learning → Community members become collaborators shaping the brand's visual DNA They're calling it "open story" — and it reframes how creative IP can work in the age of generative AI. For artists watching from the sidelines: the infrastructure is here. Read the full story here >