zero123plus
zero123plus copied to clipboard
depth control for v1.2 ?
Looking at the documentation for version 1.2, I am not seeing a depth/normal controlnet for the initial view generation. If I understand correctly, the normal controlnet only outputs normals instead of images in this version. Does the old v1 depth controlnet still work with the new model ? Thanks
The v1 controlnet will possibly not work with the new model but you could have a try. Our guess is that the performance of v1.2 will not be much higher than v1.1 if conditioned on geometry but we may add v1.2 controlnets for more control modalities later.