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

Dive Into ClipDrop Try DreamStudio 
 
0
Skip to Content
Stability AI
Stability AI
Models
Audio
Image
Language
Video
API
API Platform /
API Documentation /
API Pricing /
Self-hosted
Membership
Enterprise
Company
About
Partners
Research
Careers
News
Ri Ben Yu 
Contact Us
Open Menu Close Menu
Stability AI
Stability AI
Models
Audio
Image
Language
Video
API
API Platform /
API Documentation /
API Pricing /
Self-hosted
Membership
Enterprise
Company
About
Partners
Research
Careers
News
Ri Ben Yu 
Contact Us
Open Menu Close Menu
 
Folder: Models
Back
 
Audio
 
Image
 
Language
 
Video
 
Folder: API
Back
API Platform /
API Documentation /
API Pricing /
 
Folder: Self-hosted
Back
 
Membership
 
Enterprise
 
Folder: Company
Back
 
About
 
Partners
 
Research
 
Careers
 
News
Ri Ben Yu 
Login Account
Contact Us

Introducing Stable Zero123: Quality 3D Object Generation from Single
Images

Product
13 Dec
Written By Anel Islamovic

Key Takeaways

  * 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.

Sample 3D models reconstructed using score distillation on the Stable
Zero123 model. 

Today we're releasing Stable Zero123, our in-house trained model for
view-conditioned image generation. Stable Zero123 produces notably
improved results compared to the previous state-of-the-art,
Zero123-XL. This is achieved through 3 key innovations: 

 1. An improved training dataset heavily filtered from Objaverse, to
    only preserve high quality 3D objects, that we rendered much more
    realistically than previous methods

 2. During training and inference, we provide the model with an
    estimated camera angle. This elevation conditioning allows it to
    make more informed, higher quality predictions.

 3. A pre-computed dataset (pre-computed latents) and improved
    dataloader supporting higher batch size, that, combined with the
    1st innovation, yielded a 40X speed-up in training efficiency
    compared to Zero123-XL.

This model is now released on Hugging Face to enable researchers and
non-commercial users to download and experiment with it.

[Stable-Zero123-SAI]

Comparing Stable Zero123 (Stability AI) and Zero123-XL predictions
across different views from a sample input image shown on top-right

Creating 3D objects using Stable Zero123

To enable open research in 3D object generation, we've improved the
open-source code of threestudio open-source code to support Zero123
and Stable Zero123. This simplified version of the Stable 3D process
is currently in private preview. In technical terms, this uses Score
Distillation Sampling (SDS) to optimize a NeRF using the Stable
Zero123 model, from which we can later create a textured 3D mesh.
This process can be adapted for text-to-3D generation by first
generating a single image using SDXL and then using Stable Zero123 to
generate the 3D object.

[Stable_Zero123_Comparison]

Comparing 3D objects using Stable Zero123 (Stability AI) and
Zero123-XL models

Non-commercial use

This model is released exclusively for research purposes and is not
intended for commercial use. 

If you want to use our 3D solutions for your commercial products or
purposes, please contact us to learn more.                 
                 

Stay updated on our progress by signing up for our newsletter, and
learn more about commercial applications by contacting us here.

Follow us on X (Twitter), Instagram, LinkedIn, and join our Discord
Community.

Anel Islamovic
 
Previous
Previous

Introducing the Stability AI Membership

 
Next
Next

Behind the Compute: Building the New AI Supercomputer

Stability AI

Home
Careers
Stable Digest
HPC Center
Press

Membership

Stability AI Membership
Professional Membership Agreement

Legal

Acceptable Use Policy
Privacy Policy
Terms of Use
Discord Terms of Service
AI Act Suggested Amendments

Contact Us

press@stability.ai
partners@stability.ai

Join Our Newsletter

 
 
 
 

(c) STABILITY AI LTD, 2023