You can use stable diffusion. There already extensions where you can generate images bases on existing outlines/drawings you can make
this post was submitted on 12 Nov 2023
1 points (100.0% liked)
Machine Learning
1 readers
1 users here now
Community Rules:
- Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
- Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
- Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
- Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.
founded 1 year ago
MODERATORS
ControlNet Scribble? Re: replicate.com
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
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.