liuyuan-pal/SyncDreamer

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

39
/ 100
Emerging

Leverages a diffusion-based architecture built on Zero123-XL to synthesize geometrically-consistent multi-view images while conditioning on elevation angles and camera poses. Integrates with NeuS and NeRF renderers for downstream 3D reconstruction from the generated views, and includes full training pipelines on Objaverse data with classifier-free guidance for controllable generation quality.

1,030 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 14 / 25

How are scores calculated?

Stars

1,030

Forks

51

Language

Python

License

MIT

Category

image-to-3d-generation

Last pushed

Oct 26, 2025

Commits (30d)

0

GitHub
Image-to-3D Generation · 129 models

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.

Higher-rated alternatives

jayin92/Skyfall-GS

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

53

Tencent-Hunyuan/Hunyuan3D-2

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

52

deepseek-ai/DreamCraft3D

[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with...

49

ashawkey/stable-dreamfusion

Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

45

ActiveVisionLab/gaussctrl

[ECCV 2024] GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing

45

Explore Diffusion Models

All categories Trending Diffusion directory Insights