| Hey together with wife we took part in AssemblyAI hackathon and although we didn't win we felt good enough about our inital MVP that we took it a bit further. You can describe your characters and give a title and however long/detailed description you want, the gpt-3 will generate a children's story from it, dall-e will generate images. Images are postprocessed with stable-diffusion custom model (for stylisation) and that's the final result. It's still early as it was done in about 2 weeks, but I count on your feedback. I am software engineer and did basically all of the engineering work myself. Feel free to ask question regarding implementation plans, etc. cannot wait to learn what you think. I'll appriciate any feedback. |
Maybe show a short preview page/chapter for free, based on the real character and prompt? Hard to pay for something when you have no idea what you're getting, or the quality of it.
Other than that, the process was pretty straightforward and simple! Minor quibble: Maybe make the form fields clearer, like what they influence (is the title important?), and which are optional or vs required. The gender/age/hair color etc. had dark grey backgrounds for me and I wasn't sure what that meant.