search

SUDO-AI-3D / zero123plus

Code repository for Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model.
Apache License 2.0
1.76k stars 123 forks source link

could camera parameters be changed? #33

Open tky5622 opened 1 year ago

tky5622 commented 1 year ago

Thank you for your excellent work! I'm impressed by the quality of this model. I was wondering if we could change the camera parameter.
Thanks

eliphatfs commented 1 year ago

thank you; what parameters exactly do you refer to?

tky5622 commented 1 year ago

Thank you for your reply! What I mean is Camera poses that seem to be fixed with these parameters.

[Camera Poses] Output views are a fixed set of camera poses:

Azimuth (relative to input view): 30, 90, 150, 210, 270, 330. Elevation (absolute): 30, -20, 30, -20, 30, -20.

Could I generate six images with different azimuths and elevations? (by training the original model or another ways)

eliphatfs commented 1 year ago

Currently we only output those six views. Re-training is of course a valid solution.

aflyrt commented 2 weeks ago

Currently we only output those six views. Re-training is of course a valid solution.

If the camera pose can be adjusted, it will definitely make your project more widely applicable.