NVlabs/Sana
SANA & Sol: Efficient Generative Models and Full-Stack Training & Inference Engines for Image, Video, and World Modeling
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
1 release in the last 90 days, the latest 24 days ago, with 26 contributors on GitHub.
Use Cases & Benefits
- Provides an efficient framework for high-resolution image and video synthesis using linear diffusion transformers and advanced attention mechanisms.
- Delivers significantly faster and smaller models enabling 4K image generation and real-time video editing with low GPU memory requirements.
- Use for generating high-quality 4K resolution images with fast inference on limited GPU resources.
- Use for creating controllable 720p, minute-long videos with 6-DoF camera control for embodied AI and world modeling applications.
- Use for real-time streaming video-to-video editing and minute-scale video generation with stable temporal consistency.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Apache 2.0
Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.
Community files
- README: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
ICLR 2025 Oral | ICML 2025 | ICCV 2025 Highlight | ICLR 2026 Oral
SANA is an efficiency-oriented codebase for high-resolution image and video generation, providing complete training and inference pipelines. This repository contains code for SANA, SANA-1.5, SANA-Sprint, SANA-Video, SANA-WM, SANA-Streaming, and Sol-RL. More details can be found in our 📚 documentation.
Join our Discord to engage in discussions with the community! If you have any questions, run into issues, or are interested in contributing, don't hesitate to reach out!
We introduce SANA, a series of efficient diffusion models for high-resolution image and video generation:
In summary, SANA is a fully open-source framework integrating efficient training, fast inference, and flexible deployment for both image and video generation. Deployable on laptop GPUs with < 8GB VRAM via 4-bit quantization.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
793+98
Open issues
135-1
Compared with peers in Machine Learning
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| photoprism/photoprism | 40.4K | — | 65 | 1 day ago |
| huggingface/diffusers | 34.8K | — | 65 | 3 days ago |
| onnx/onnx | 21.6K | — | 63 | 31 days ago |
| lukas-blecher/LaTeX-OCR | 16.6K | — | 18 | — |
| milesial/Pytorch-UNet | 11.7K | — | 18 | — |
| NVlabs/Sana | 9.8K | — | 41 | 24 days ago |
| Category median | 21.6K | — | 63 | — |
Also by NVlabs
Other repositories from this maintainer that GStars tracks
- Python3.8K stars
GR00T-WholeBodyControl
Welcome to GR00T Whole-Body Control (WBC)! This is a unified platform for developing and deploying advanced humanoid controllers. This includes: Decoupled WBC models used in NVIDIA Isaac-Gr00t, Gr00t N1.5 and N1.6 and GEAR-SONIC
- Python3.8K stars
Eagle
Eagle: Frontier Vision-Language Models with Data-Centric Strategies
- Python3.7K stars
FoundationPose
[CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
- Python2.5K stars
ProtoMotions
ProtoMotions is a GPU-accelerated simulation and learning framework for training physically simulated digital humans and humanoid robots.
- Python2.1K stars
alpamayo
NVIDIA Alpamayo 1 Nano is an open 10B reasoning VLA model for autonomous vehicles that pairs driving trajectories with Chain-of-Causation reasoning.
Discover Repositories
Search across tracked repositories by name or description