liuyuan-pal/SyncDreamer

[ICLR 2024 Spotlight] SyncDreamer: Generating Multiview-consistent Images from a Single-view Image

46
/ 100
Emerging

This project helps artists, designers, and e-commerce professionals create stunning 3D models from just one image. You input a single photo of an object, and the system generates multiple consistent views of that object from different angles. This allows you to then reconstruct a full 3D model, useful for visualizations, product showcases, or interactive experiences.

1,030 stars.

Use this if you need to generate multiple consistent images of an object from a single photo to create a 3D model for product visualization, digital art, or virtual environments.

Not ideal if you already have multiple views or a 3D model of your object, or if you require extremely high precision for engineering or medical applications.

3D-modeling product-design e-commerce-imaging digital-art virtual-photography
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

1,030

Forks

51

Language

Python

License

MIT

Last pushed

Oct 26, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/liuyuan-pal/SyncDreamer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.