Sana
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
Master video-to-video editing with Sana Video Refiner. Learn how to achieve high-fidelity results using diffusion and upsampling with this comprehensive guide.
DC-AE Tiling for 4K Resolution Inference with Limited GPU Memory: A Complete GuideLearn DC-AE tiling to perform 4K resolution inference on GPUs with only 8GB VRAM. This guide explains how tiling drastically reduces peak GPU memory usage.
Implementing PAG (Progressive Attention Guidance) in Sana InferenceImplement Progressive Attention Guidance PAG in Sana inference to boost fine detail fidelity. Learn how this plug-in enhances Sana diffusion models without losing global coherence.
How to Configure Mixed Precision Training (BF16/FP16) in SanaLearn to configure mixed precision training (bf16/fp16) in NVlabs/Sana by updating your YAML config. Accelerate your training with automatic mixed precision (AMP).
How to Use the Diffusers Integration with SanaPipelineLearn how to use the diffusers integration with SanaPipeline for seamless loading and inference of native checkpoints. Effortlessly use the familiar pipe API.
Debugging Out of Memory (OOM) Issues During High-Resolution Image Training in SanaLearn to debug Out of Memory OOM issues during high-resolution image training in Sana. Reduce GPU memory by 50% with mixed precision, gradient checkpointing, component offloading, and xformers.
Implementing SANA-WM for Controllable World Modeling with 6-DoF Camera ControlImplement SANA-WM for controllable world modeling and generate 720p videos with precise 6-DoF camera control. Discover its advanced Linear-attention DiT architecture.
Achieving 27FPS for Minute-Length Video Generation with LongSANA: A Complete Technical GuideUnlock 27FPS minute-length video generation with LongSANA. Explore our technical guide on chunk-causal inference, KV-cache reuse, streaming training, and optimized samplers.
Configuring Multi-Scale WebDataset Training with TAR Files in NVIDIA SanaTrain images at multiple scales using TAR files in NVIDIA Sana. Learn to configure heterogeneous resolutions, sample captions by ClipScore, and dynamically select aspect ratios with wids-meta.json.
Using Cosmos-RL for Post-Training SANA-Image and SANA-Video: A Complete GuideMaster post-training SANA-Image and SANA-Video with NVlabs Cosmos-RL. Learn efficient supervised fine-tuning and reinforcement learning using PEFT LoRA adapters and asynchronous reward scoring.
How Sol-RL Achieves 4.64× Faster Convergence with NVFP4 Rollout and BF16 TrainingDiscover how Sol-RL achieves 4.64x faster convergence. Learn about NVFP4 rollout and BF16 training, which eliminate precision-stability trade-offs for efficient diffusion RL.
High-Performance Serving of Sana with SGLang and OpenAI-Compatible APIServe NVlabs Sana diffusion models at scale with SGLang. Enjoy unified runtime, command-line, Python SDK, and OpenAI-compatible API for high performance.
Have a question about this repo?
These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:
curl -s "https://instagit.com/install.md" 
Maintain an open-source project? Get it listed too →