OpenDriveLab/Nexus
[ICCV 2025] Nexus: Decoupled Diffusion Sparks Adaptive Scene Generation
Decouples noise prediction from content generation in diffusion to enable real-time reaction alongside goal-directed control for autonomous driving scenarios. Integrates NeRF-based rendering with adversarial traffic generation to synthesize safety-critical driving scenes with flexible state conditioning. Targets the nuPlan dataset ecosystem and includes the Nexus-Data benchmark derived from real-world map topology and hazardous interaction patterns.
109 stars.
Stars
109
Forks
10
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 06, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/OpenDriveLab/Nexus"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PaddlePaddle/PaddleMIX
Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks,...
UCSC-VLAA/story-iter
[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization
keivalya/mini-vla
a minimal, beginner-friendly VLA to show how robot policies can fuse images, text, and states to...
adobe-research/custom-diffusion
Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)
byliutao/1Prompt1Story
🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation...