this post was submitted on 12 Nov 2023
1 points (100.0% liked)

Machine Learning

1 readers
1 users here now

Community Rules:

founded 1 year ago
MODERATORS
 

Hi, I am an industrial design student and as part of my project, I need to make an AI that enhances drawing. It is not expected of me to make something from scratch I can use already existing models. However, I need to add something to it of course. I don’t have sufficient knowledge in programming to get started and I could use any advice. I want to spend time on this but i would go with a simple option as I don’t have time to learn everything. I would be super happy if someone could help

top 4 comments
sorted by: hot top controversial new old
[–] blazingasshole@alien.top 1 points 1 year ago

You can use stable diffusion. There already extensions where you can generate images bases on existing outlines/drawings you can make

[–] Rejg@alien.top 1 points 1 year ago

ControlNet Scribble? Re: replicate.com

[–] loadsamuny@alien.top 1 points 1 year ago

easiest entry point is use one of the controlnet options at replicate eg, https://replicate.com/jagilley/controlnet-canny

canny edges may need you to invert your line art first, a bit of trial and error, try out the other options, seg (segmentation map) is probably the most powerful, will require you to color in your lineart with specific colors, definitely worth testing that one as gives you excellent control of your output

[–] slashdave@alien.top 1 points 1 year ago

These models suffer from a lack of training data in specific domains. If you could provide that for your use case, it could be a significant contribution, especially in bulk.