Sign In

Stable Zero123

120

2.1k

28

Updated: Dec 13, 2023

base model

Verified:

PickleTensor

Type

Checkpoint Trained

Stats

2,141

0

Reviews

Published

Dec 13, 2023

Base Model

SD 1.5

Hash

AutoV2
A28D471B0F
default creator card background decoration
Moderator Badge
theally's Avatar

theally

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).

https://stability.ai/news/stable-zero123-3d-generation