[MrOrelliOReilly]

For me, the killer feature would more be _autocomplete_ for art. I love to cartoon and doodle, but don’t have the time/patience/skillset to build professional digital assets. If I could go from my pencil drawn sketch to a flashy png, that would be awesome! I think it’d be a nice use of AI, since it just allows me to do more with my own creativity.

Unfortunately whenever I’ve tried uploading a sketch to ChatGPT or Gemini, it seems to fixate on details of my sketch, and recreates my mistakes in high fidelity. It fails to take a creative leap toward a good result. I’ve heard some professionals have gotten good results building custom workflows in ComfyUI.

[gedy]

Try https://vizcom.ai, it might be closer to what you are looking for.

[embedding-shape]

No, seems to be about "turns X into Y", while what parent seems to want, is something that just makes making X easier/better, instead of doing those sort of "transformations" which is usually where the human feeling gets lost.

[jolmg]

Got a warning about vizcom.ai wanting to connect to any device on my local network...