Real Time Sketching –> Image Generation
fal.aiThis is really freakin' cool. I don't know that I can think of anything useful to do with it, but seeing real-time updates as I draw new lines is a ton of fun, and I'm sure someone else will find a purpose for it all.
If OP is the author, I'd recommend one UX change - put the prompt above the sketchpad because the prompt seems to be stronger than the sketch in terms of what gets drawn.
thanks for the feedback codingwave! yes there is so much to add! wanted to highlight the potential with this demo
I can think of dozens of use cases for this.
Transforming wireframes into UI / graphics is top of my mind right now.
I’m not but will let the author know!
Nice project! It work very well.
Anyway, I tried some weird cases like a double sun and the AI got very confused. https://imgur.com/a/BAH3666 I expected some confusion like a weird horizon, but the double palm is very strange.
This is indeed a bit weird, one interesting update we released just now is allowying you to change the seed so see different variations of the same prompt+input combination. Also what I have noticed is, if you describe what you meant with a few words (two suns in the sky, etc.) it is actually pretty decent in terms of generational quality.
Yep, fixing the prompt fix the image https://imgur.com/a/io8swAj