New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
The difference of Stable-Zero123 and Zero-123-XL #29
Comments
It appears that stable zero123 eliminates the delta radius conditioning and opts for an estimated elevation instead. I didn't find a source that explains the reason for this. |
@echosum Hello, sorry to bother you. May I ask you a question, please? I wonder that, if I want to run the code with Zero123-XL instead of Stable-Zero123, should I switch guidance_3d_type from "stable-zero123-guidance" to "zero123-guidance"? |
I think you should use "zero123-unified-guidance" |
@flyingdoubleG Hello, many thanks to your guidance! I wonder whether there are non-trivial difference between zero123-guidance and zero123-unified-guidance? Because I have run some cases with zero123-guidance and zero123-xl.ckpt and the geometries of the results are reasonable. Thanks a lot! :) |
Ah, I think they are almost same except the way for loading the model, and zero123-unified-guidance also implemented VSD, you can try both |
@flyingdoubleG Thank you for your answer! I will try both of them. |
@flyingdoubleG Hi! |
Hi
Thanks for your excellent work.
I am wondering the slight difference in your stable_zero123_guidance.py and zero123_guidence.py.
Could you please explain why the delta radius is different from zero123?
The text was updated successfully, but these errors were encountered: