high-performance inference and serving library for interactive autoregressive video and world models
☆514Oct 14, 2026Updated this week
Alternatives and similar repositories for flashdreams
Users that are interested in flashdreams are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- NVIDIA OmniDreams is a world model that generates photorealistic video for autonomous-driving simulation in real time.☆346Oct 2, 2026Updated last week
- A Minimal and Elegant Framework & Tutorial for Real-Time Interactive World Models☆855Sep 10, 2026Updated last month
- Cameras as Relative Positional Encoding☆761Dec 18, 2025Updated 9 months ago
- [ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactiv…☆1,004Oct 3, 2026Updated last week
- NVIDIA FastGen: Fast Generation from Diffusion Models☆1,030Aug 21, 2026Updated last month
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Infinite Worlds with Versatile Interactions☆1,860Sep 10, 2026Updated last month
- NVIDIA Asset Harvester is a generative AI model for autonomous vehicle simulation that extracts reusable 3D Gaussian assets directly from…☆267Sep 9, 2026Updated last month
- Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence☆969Sep 17, 2026Updated 3 weeks ago
- [NeurIPS 2025 (Spotlight)] The implementation for the paper "4DGT Learning a 4D Gaussian Transformer Using Real-World Monocular Videos"☆491Sep 19, 2025Updated last year
- Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory☆180Sep 7, 2026Updated last month
- DreamX-World: A General-Purpose Interactive World Model☆781Jul 23, 2026Updated 2 months ago
- [CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control☆1,435Jun 15, 2026Updated 3 months ago
- Code Implementation of "WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation"☆185May 9, 2026Updated 5 months ago
- [ICLR2025] A PyTorch implementation for STORM: Spatiotemporal Reconstruction Model for Large-Scale Outdoor Scenes☆372May 22, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Project Lyra: Open Generative 3D World Models☆2,666Jul 20, 2026Updated 2 months ago
- ViPE: Video Pose Engine for Geometric 3D Perception☆2,141Sep 10, 2026Updated last month
- rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale☆821Jun 25, 2026Updated 3 months ago
- Any4D: Unified Feed-Forward Metric 4D Reconstruction☆417Apr 17, 2026Updated 5 months ago
- A 3DGS framework for omni urban scene reconstruction and simulation.☆1,274Aug 27, 2025Updated last year
- 📷 [CVPR'26] Camera-controlled text-to-video generation, now with intrinsics, distortion and orientation control!☆237May 15, 2026Updated 5 months ago
- [CVPR 2026 Highlight & Best Paper of VideoWorldModel Workshop] NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos☆683May 12, 2026Updated 5 months ago
- UE5-based Data Engine used in OmniX☆115Jul 12, 2026Updated 3 months ago
- [NeurIPS 2025] WorldMem: Long-term Consistent World Simulation with Memory☆398Feb 21, 2026Updated 7 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICLR 2026] π^3: Permutation-Equivariant Visual Geometry Learning☆2,211Jul 3, 2026Updated 3 months ago
- [ICML 2026] World-R1: Reinforcing 3D Constraints for Text-to-Video Generation☆428Jun 3, 2026Updated 4 months ago
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆1,379Jun 8, 2026Updated 4 months ago
- [CVPR 2025 Oral & Best Paper Finalist] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models☆1,293Jun 28, 2025Updated last year
- [ICLR 2025 Oral] Official code for "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"☆566Aug 4, 2025Updated last year
- Flow Map OPD for AnyStep Video Diffusion☆441Aug 14, 2026Updated 2 months ago
- [NeurIPS 2026] PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion☆1,074Jul 22, 2026Updated 2 months ago
- InstantNuRec: Feed-Forward 3D Gaussian Reconstruction from Driving Logs☆237Sep 30, 2026Updated 2 weeks ago
- [CVPR 2026 Highlight] Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation☆365Dec 15, 2025Updated 10 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Long Video Gen / World Model / World Action Model (Embodied) Infrastructure☆2,784Updated this week
- [CVPR '26] SceneTok: A Compressed, Diffusable Token Space for 3D Scenes☆214Oct 5, 2026Updated last week
- [ICLR 2026] Official Repo for Rolling Forcing: Autoregressive Long Video Diffusion in Real Time☆461Oct 31, 2025Updated 11 months ago
- Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control in…☆745Jun 30, 2026Updated 3 months ago
- [ICML2026] Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization☆67Jul 26, 2026Updated 2 months ago
- ☆213Oct 22, 2025Updated 11 months ago
- [ICLR 2026] DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving☆43Mar 13, 2026Updated 7 months ago