[mkummer]

https://dreamandcolor.com/ has been a fun solo bootstrapped side project for me for the past 2.5ish years - (specialize in converting photos to coloring pages for parents, educators, etc)

I started it primarily wanting to take a shot at productizing an image diffusion model (Stable Diffusion 1.5 when I started) in a novel (at the time) way and it ended up growing legs of it's own.

She's steadily chugging along, growing about 10-20% per month with minimal marketing, exceeding all expectations I had for the project when I set out

[pillefitz]

Well done! How does it compare to using built-in image models like nano banana?

[mkummer]

You can get great results with nano banana nowadays (ex: "convert this image to a coloring page") - I'd say we focus on 1. consistency with our base style from image to image, 2. likeness (still really tough to get 100% right but we've come a long way since our MVP) and 3. offering fun alternatives (South Park inspired coloring pages, Minecraft style, etc)

We also handle all the post-processing (upscaling, image cleaning, etc) that you need in order to get great printed results - with Gemini (Nano Banana) or ChatGPT you've got to pull each image out, possibly remove the watermark, set the curves/levels in photoshop/gimp, upscale it, etc then print the page - you can just hit Export and download a pdf ready to print from our site

[jama211]

This is fantastic, a perfect example. Good stuff!