Content
@
0 reply
0 recast
2 reactions
Chinmay 🕹️🍿
@chinmay.eth
Create a stable diffusion prompt (or a similar tool) that can create more poses for the given character -- it's a jester. Amount: 69000 MOXIE Deadline: 12/07/2024 Ps. I'll test the prompt to make sure it works as expected before giving away the bounty. @bountybot
10 replies
7 recasts
47 reactions
Max
@anakvad
This seems to me to be a typical task for using ControlNet. The point is that you take an image where you need to change the pose of the character. Then you give the ControlNet model the new pose in a special format, or an image from where it will take the pose itself. And as a result you get the original image, but with the character in a different pose. Poses can be taken ready-made (ex: openposes.com) or you can use OpenPose Editor extension for SD. It takes a bit of practice, but there are many videos on YouTube, for example this one: https://youtu.be/fJsi-swa5ZY?si=_awn1w99BIL5mE3l.
1 reply
0 recast
1 reaction
Chinmay 🕹️🍿
@chinmay.eth
Good stuff. The major problem is that I need something similar to the existing character. Is that possible?
1 reply
0 recast
0 reaction
Max
@anakvad
Yes, that's what this method is used for. In SD you can generate an image based on another image - Img2Img. The output image can either be very different from the original image or identical. The point is that you insist on getting an identical image, but ControlNet changes the pose of the character on it.
0 reply
0 recast
0 reaction
