Show HN: Draw Fast – Real-time AI image generation based on drawings in a canvas

I really can&#x27;t figure out what relation the doodle has to what&#x27;s generated. I draw a dot, I get a cat as per the prompt. I add another dot, or a line; the newly generated image changes, but there&#x27;s no predictability. We can call this &#x27;AI&#x27;, but is there really any intelligence here?<p>Seems like a call to stable diffusion&#x27;s API without any real intent.

The sketch perturbs the generation, but that’s about it. Going with the kitten prompt, I’m unable to get any given pose or positioning of the kitty. Drawing a second cat only changes the pose of the only one again. Mirror image the sketch: the tail curve changes. Add a random dot: get a whole new pose.

Probably related tweet: <a href="https:&#x2F;&#x2F;twitter.com&#x2F;steveruizok&#x2F;status&#x2F;1729190769708376295" rel="nofollow noreferrer">https:&#x2F;&#x2F;twitter.com&#x2F;steveruizok&#x2F;status&#x2F;1729190769708376295</a>

I wasn&#x27;t able to get perceptibly better results than I usually do with simply prompt engineering with stable diffusion. Maybe my art skills aren&#x27;t good enough.<p>I drew a face with a beard and a hat and I got someone off in the distance. I had to really enforce common stable diffusion terms to get it to be a portrait and not a woman. You&#x27;d think a long beard and a hat would have been enough of an indication without me having to express it in text

I drew a cat laying on its back and got back a head with a donut-shaped tail on top.<p>It looks like this model only knows how to draw specifically kittens in very specific positions?

Another very similar project: <a href="https:&#x2F;&#x2F;github.com&#x2F;flowtyone&#x2F;flowty-realtime-lcm-canvas">https:&#x2F;&#x2F;github.com&#x2F;flowtyone&#x2F;flowty-realtime-lcm-canvas</a>