- Oct 29, 2017
- 812
- 2,200
I tried, it depends on the pose, some weird poses won't work at all if your model is not friendly for them.Has anyone played around with using 3D posing to help direct generation?
You must be registered to see the links
For what you want to do my advice is creating a character in many poses like it's shown here in the beginning part.If you figure it out, please share. What I'm thinking is to generate a bunch of images of a specific character and train a Lora model for it, but I lack the vram to train Loras. Maybe I will with google collab at some point.
You must be registered to see the links
After that, you can see the guy cuts all those headshots of the character. In your case, cut all those parts and go and train a lora of your character, after that you can generate new poses using your lora and then retrain if you want to refine as Elefy said.