A new method for character design

March 30, 2023 at 2:52 pm, No comments

I have experimented a bit with a new method for character design with NovelAI.

The usual method has the slight disadvantage that pictures with different expressions might be a bit incoherent and "jumpy". Therefore quite a lot of manual work is needed to fix that, as I have described in a previous posting.

An alternative approach is this:

Produce one picture of your character with NovelAI that you really like.
Use that as input for the "image to image" generation, and add just very basic tags like "girl, angry" or "girl, happy". If you set noise fairly low (0.2) and strength in the mid-range, you can obtain a picture where pose, clothes etc. are identical, but the expression changes.

I have tried this out with Patti, using one final character sprite I had produced earlier (left). Unfortunately, the text on her t-shirt confused NovelAI a bit. That explains the "stains" she has on her breast now... (Sorry for that.) Also, her hair ribbon is missing. The general result, however, looks neat and very consistent. (Besides that for the "sleepy" Patti, NovelAI gave her some more comfy trousers... ;-)

I'm not going to redo all my sprites for "Sweet Science", but for future projects this might be the best way to go! Let me know if you try this out and what is your experience with this!

A new method for character design

No comments

Leave a reply

Create your website or online store with Mozello