MAGI-2-preview: Scaling Video Generation Models Efficiently
☆638Aug 6, 2026Updated 2 months ago
Alternatives and similar repositories for MAGI-2-preview
Users that are interested in MAGI-2-preview are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [NeurIPS 2026] Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence☆81Updated this week
- [Tech Report] Context Scaling: Scaling Properties of Text Conditioning in Visual Generation☆187Aug 7, 2026Updated 2 months ago
- [ECCV2026] This is the official implementation of Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models☆42Jul 2, 2026Updated 3 months ago
- [Arxiv 2026] WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory☆511Updated this week
- Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control☆170Sep 17, 2026Updated last month
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- SolarRenderer: Few-Step Generative Reference Rendering☆107Updated this week
- Source-linked examples of AI models used for 3D modeling, industrial design and CAD, and robot control, with archived media and the model…☆82Updated this week
- [Official Repo] JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion☆1,955Updated this week
- Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion☆87Aug 25, 2026Updated last month
- Official implementation of the paper "VGGT-Diff: Visual Geometry Meets Diffusion for Sparse-View Novel View Synthesis."☆87Updated this week
- Official Implemenation for V-RAE: Rethinking Video Latent Spaces for Generation☆133Aug 26, 2026Updated last month
- 4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes☆159Oct 8, 2026Updated last week
- SCoPE: Sightline-Coordinate Positional Encoding for 3D-Aware Video Generation☆214Sep 27, 2026Updated 2 weeks ago
- ☆116Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Self Gradient Forcing (SGF) recovers the missing context-gradient path for self-generated causal memory through a bounded two-pass replay…☆159Updated this week
- Naive-N0.5-Flash is an open-weight 309B MoE model with 15.5B active parameters, built for coding and AI R&D.☆178Sep 27, 2026Updated 2 weeks ago
- FLUX 3 Action: open weights 7B world action model from Black Forest Labs. Train, fine-tune and run action prediction for robots (DROID, S…☆184Updated this week
- MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts☆1,182Updated this week
- DMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation☆185Updated this week
- AgentGarten: Code Worlds for Evolving Agents☆193Oct 9, 2026Updated last week
- Official PyTorch Implementation of "MeshFlow: Mesh Generation with Equivariant Flow Matching" (SIGGRAPH 2026)☆96Sep 28, 2026Updated 2 weeks ago
- ☆49Aug 11, 2026Updated 2 months ago
- Generative Reconstruction with Test-Time Input Alignment☆100Oct 9, 2026Updated last week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- [Science Robotics 2026] Official Implementation of the paper RL-100☆381Oct 1, 2026Updated 2 weeks ago
- This repository contains the code for "Qwen-Video-Edit: Instruction-Based Video Editing by Repurposing an Image Editing Model"☆129Sep 1, 2026Updated last month
- ☆250Aug 11, 2026Updated 2 months ago
- [NeurIPS 2025] AutoPartGen: Autoregressive 3D Part Generation and Discovery. This is a re-implementation of original model.☆68Jun 28, 2026Updated 3 months ago
- Encoder-Free Unified Image and Video Understanding and Generation☆211Oct 2, 2026Updated 2 weeks ago
- HarnessEval-W: Agentifying the Evaluation of Visual Worlds☆307Sep 7, 2026Updated last month
- Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation☆354Updated this week
- ☆96Aug 10, 2026Updated 2 months ago
- Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene Reconstruction☆210Updated this week
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Programmable World Model: explicit world state, generative rendering.☆205Updated this week
- [Tech Report] A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing☆259Aug 10, 2026Updated 2 months ago
- DeepGEMM-Ascend: clean and efficient matrix multiplication kernel library for Huawei Ascend NPUs☆585Updated this week
- ☆10,044Aug 15, 2026Updated 2 months ago
- Instella MoE is a fully open state-of-the-art Mixture-of-Experts language model, trained end-to-end on AMD Instinct™ GPUs.☆80Sep 2, 2026Updated last month
- Mixture-of-experts (MoE) training megakernel for NVL72s☆620Oct 1, 2026Updated 2 weeks ago
- Official implementation of FlowHMR, a generative model for physically plausible motion capture from monocular video.☆148Oct 5, 2026Updated last week