Stable Zero123: Quality 3D Object Generation from Single Images
Generates novel views of an object, demonstrating 3D understanding of the appearance from various angles
Stable Zero123 generates novel views of an object, demonstrating 3D understanding of the object’s appearance from various angles with notably improved quality over Zero1-to-3 or Zero123-XL due to improved training datasets and elevation conditioning.
Based on Stable Diffusion 1.5, this model consumes the same amount of VRAM as SD1.5 to generate 1 novel view. Using Stable Zero123 to generate 3D objects requires more time and memory (24GB VRAM recommended).
This model is being released for non-commercial and research use, and the weights can be downloaded here.
Stable Zero123C can be used commercially with a Stability AI membership.
Comments
None