#1717th of 42 in Image and video
sana
Efficient diffusion models and training code for high-resolution image and video
- Stars
- 9.7k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Jun 2026
- Language
- Python
4,991 on 3 Apr 20269,736 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
SANA is NVIDIA's research codebase for linear-attention diffusion models, covering text-to-image up to 4K, one/few-step SANA-Sprint, and video models (SANA-Video, SANA-Video 2.0, SANA-WM, SANA-Streaming). It includes training and inference pipelines, DDP/FSDP, LoRA, ControlNet, and RL post-training recipes. Weights are on Hugging Face, with diffusers, ComfyUI and SGLang integrations.
Who it is for: ML engineers and researchers training or running diffusion image/video models
Strengths
- Full training and inference code, not only weights, including DDP/FSDP and RL post-training
- Runs in diffusers, ComfyUI and SGLang (OpenAI-compatible serving)
- 4-bit and 8-bit variants; README says SANA runs within 8GB VRAM
- Public demos for image, ControlNet, Sprint and SANA-Video 2.0
Weaknesses
- Research repo with many sub-projects; no single UI or one-command install
- Some newer pieces (Sol-Engine, H3) live on a separate branch
- Large video and world models need high-end GPUs; exact VRAM is not stated
- Docs are spread across project pages and a separate docs site
What it needs
- GPU required
- Docker
- Needs PyTorch, diffusers, Hugging Face weights
- Models: SANA, SANA-1.5, SANA-Sprint, SANA-Video, SANA-Video 2.0
Quick answers
Is sana open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Can you run sana with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does sana need a GPU?
Yes, it needs a GPU.
Also in Image and video
See all 42| Rank | Project | Score |
|---|---|---|
| 1 | frigateLocal NVR with realtime object detection for IP cameras | 91 out of 100 |
| 2 | MoneyPrinterTurboGenerates short videos from a topic, with script, footage, voiceover and subtitles | 87 out of 100 |
| 3 | ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows | 86 out of 100 |
| #4 | InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows | 83 out of 100 |
| #5 | toonflow-appInfinite-canvas tool for AI short drama and comic video production | 83 out of 100 |