Show HN: Draw Fast – Real-time AI image generation based on drawings in a canvas
stablediffusionweb.comI really can't figure out what relation the doodle has to what'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's no predictability. We can call this 'AI', but is there really any intelligence here?
Seems like a call to stable diffusion's API without any real intent.
Made this mistake too. Drew a sunrise behind two mountains, got a cat. Noticed the prompt and changed it to "sunrise behind mountains, lake at bottom".
I am pleasantly surprised how even random sketches generate beautiful mountain sunrises.
please try to change your prompt(textbox on top right) the default prompt is about a cat
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: https://twitter.com/steveruizok/status/1729190769708376295
It is not using fal.ai API or their code for now.
I wasn't able to get perceptibly better results than I usually do with simply prompt engineering with stable diffusion. Maybe my art skills aren't good enough.
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'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.
It looks like this model only knows how to draw specifically kittens in very specific positions?
You can change your prompt (top right corner) to draw other things
I know that. But it should know how to draw a cat laying on its back if the prompt says "cat" and the drawing is on its back.