Home Projects MagicDrive
MagicDrive
Python

MagicDrive

[ICLR24] Official implementation of the paper “MagicDrive: Street View Generation with Diverse 3D Geometry Control”

by cure-lab · GitHub
Stars
Forks
License
Created
Last commit
Language
autonomous-vehiclesdeep-learningdiffusion-modelsApache-2.0Python
View on GitHub
In plain words

Generate street-view images and videos with 3D geometry control.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
MagicDrive — GitHub preview card
📈 Star history
1 1671 166
2026-07-202026-08-31
📈 Track MagicDrive

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

[ICLR24] Official implementation of the paper “MagicDrive: Street View Generation with Diverse 3D Geometry Control”

MagicDrive has 1.2k stars on GitHub. It has been forked 52 times. MagicDrive is written mainly in Python. It has been in active development since 2023. MagicDrive is available under the Apache-2.0 license. Its main topics are autonomous-vehicles, deep-learning, diffusion-models, image-generation.

Frequently asked questions

What is MagicDrive?

[ICLR24] Official implementation of the paper “MagicDrive: Street View Generation with Diverse 3D Geometry Control”

Is MagicDrive open source?

MagicDrive is an open-source project. It is released under the Apache-2.0 license.

Is MagicDrive free?

Yes. MagicDrive is free and open source — you can use, modify and self-host it.

What license does MagicDrive use?

MagicDrive is available under the Apache-2.0 license.

What language is MagicDrive written in?

MagicDrive is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — MagicDrive

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=cure-lab-magicdrive)](https://olud.ai/project/cure-lab-magicdrive.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →
FireRed-Image-Edit
FireRed-Image-Edit is a powerful image editing foundation model achieving open-source state-of-…
1.3k · aigc
sharesimage-generationdiffusion-models
storyteller
Multimodal AI Story Teller, built with Stable Diffusion, GPT, and neural text-to-speech
537 · ddpm
sharesimage-generationdiffusion-models
story-iter
[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization
961 · diffusion-models
sharesimage-generationdiffusion-models
HunyuanImage-2.1
HunyuanImage-2.1: An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generatio…
672 · aigc
sharesimage-generationdiffusion-models
NOVA
[ICLR 2025] Autoregressive Video Generation without Vector Quantization
655 · autoregressive-models
sharesimage-generationdiffusion-models
Voost
[SIGGRAPH Asia 25] Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtua…
340 · diffusion-models
sharesimage-generationdiffusion-models
MagicBrush
[NeurIPS'23] "MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing".
411 · diffusion-models
sharesimage-generationdiffusion-models
ZenCtrl
In-context subject-driven image generation while preserving foreground fidelity
351 · diffusion-models
sharesimage-generationdiffusion-models
MultiDiffusion
Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Imag…
1.1k · diffusion-models
sharesimage-generationdiffusion-models
Awesome-Try-On-Models
A repository for organizing papers, codes and other resources related to Virtual Try-on Models
436 · 3d-generation
sharesimage-generationdiffusion-models

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.