LinearVSR-SFT-22113408

<p align="center" style="border-radius: 10px"> <img src="asset/logo.png" width="35%" alt="logo"/> </p>

⚡️Sana: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

<div align="center"> ICLR 2025 Oral Presentation <div>

<div align="center"> <a href="https://nvlabs.github.io/Sana/"><img src="https://img.shields.io/static/v1?label=Project&message=Github&color=blue&logo=github-pages"></a> &ensp; <a href="https://hanlab.mit.edu/projects/sana/"><img src="https://img.shields.io/static/v1?label=Page&message=MIT&color=darkred&logo=github-pages"></a> &ensp; <a href="https://arxiv.org/abs/2410.10629"><img src="https://img.shields.io/static/v1?label=Arxiv&message=Sana&color=red&logo=arxiv"></a> &ensp; <a href="https://hanlab.mit.edu/blog/infinite-context-length-with-global-but-constant-attention-memory"><img src="https://img.shields.io/static/v1?label=Blog&message=MIT&color=darkred&logo=github-pages"></a> &ensp; <a href="https://nv-sana.mit.edu/"><img src="https://img.shields.io/static/v1?label=Demo:6x3090&message=SANA&color=yellow"></a> &ensp; <a href="https://nv-sana.mit.edu/4bit/"><img src="https://img.shields.io/static/v1?label=Demo:1x3090&message=4bit&color=yellow"></a> &ensp; <a href="https://nv-sana.mit.edu/ctrlnet/"><img src="https://img.shields.io/static/v1?label=Demo:1x3090&message=ControlNet&color=yellow"></a> &ensp; <a href="https://nv-sana.mit.edu/sprint/"><img src="https://img.shields.io/static/v1?label=Demo:1x3090&message=SANA-Sprint&color=yellow"></a> &ensp; <a href="https://huggingface.co/spaces/Efficient-Large-Model/SanaSprint"><img src="https://img.shields.io/static/v1?label=Huggingface Demo&message=SANA-Sprint&color=yellow"></a> &ensp; <a href="https://replicate.com/chenxwh/sana"><img src="https://img.shields.io/static/v1?label=API:H100&message=Replicate&color=pink"></a> &ensp; <a href="https://discord.gg/rde6eaE5Ta"><img src="https://img.shields.io/static/v1?label=Discuss&message=Discord&color=purple&logo=discord"></a> &ensp; </div> <p align="center" border-radius="10px"> <img src="asset/Sana.jpg" width="90%" alt="teaser_page1"/> </p>

💡 TLDR: Explore everything you want here!

🚶 Basic:

Demo: SANA-1.5 | SANA-ControlNet | SANA-4bit | SANA-Sprint | SANA-Sprint (HF) | SANA-Video<br> ComfyUI: ComfyUI Guidance <br> Model Zoo: Model Card Collects All Models <br> Env Preparation: One-Click Env Install <br> Blog: Infinite Context for LLM and Video Generation <br> Inference: <br>      1) diffusers:SanaPipeline <br>      2) diffusers:SanaPAGPipeline <br>      3) Ours:SanaPipeline <br>      4) Inference with Docker <br>      5) Inference with TXT or JSON Files <br>      6) Inference SANA-Video <br>      6) Inference LongSANA <br> Training and Data: <br>      1) Image-Text Pairs <br>      2) Multi-Scale Webdataset <br>      3) TAR File Multi-Scale Webdataset <br>      4) FSDP Launch <br>      5) LoRA Training <br>      6) SANA-Sprint Diffusers Training <br>      7) SANA-Video Training <br>      8) LongSANA Training <br>

🏃 Applications:

2K & 4K Resolution Generation: SANA is Capable to Generate 2K & 4K Images (Only 8BG) <br> ControlNet: Train&Inference Guidance | Model Zoo | Demo <br> Dreambooth / LoRA Training: Train&Inference Guidance <br> Quantization: Inference with 8bit | Inference with 4bit (8BG) | 4bit Model | 4bit Demo | 4bit Demo2 <br> 8bit Optimizer: How to Config <br> Inference Scaling: SANA Generate VILA Pick Inference Scaling <br> Metrics: Metric Toolkit: (FID, CLIP-Score, GenEval, DPG-Bench) <br>

🚗 Advance:

SANA-Sprint: One-Step Diffusion: Arxiv | Train&Inference Guidance | Model Zoo | HF Weights <br> SANA-1.5: Efficient Model Scaling: Arxiv | Model Zoo | HF Weights <br> SANA-Video: Efficient Video Gen: Arxiv | Train&Inference Guidance | Model Zoo | HF Weights <br> LongSANA: SANA-Video + LongLive: Train&Inference Guidance | Model Zoo | HF Weights <br>

🚀 Future:

Mission: TODO

🔥🔥 News

• (🔥 New) [2025/12/09] 🎬 LongSANA training and inference code are all released. Thanks to LongLive Team. Refer to: [Train] | [Test] | [Weight]
• (🔥 New) [2025/11/21] 🎬 LongSANA: 27FPS real-time minute-length video generation model is released. Thanks to LongLive. [Weight]
• (🔥 New) [2025/11/24] 🪶 Blog: how Causal Linear Attention unlocks infinite context for LLMs and long video generation.
• (🔥 New) [2025/11/9] 🎬 Introduction video shows how Block Causal Linear Attention and Causal Mix-FFN work?
• (🔥 New) [2025/11/6] 📺SANA-Video is merged into diffusers. How to use.
• (🔥 New) [2025/10/27] 📺SANA-Video is released. [README] | [Weights] support Text-to-Video, TextImage-to-Video.
• (🔥 New) [2025/10/13] 📺SANA-Video is coming, 1). a 5s Linear DiT Video model, and 2). real-time minute-length video generation (with LongLive). [paper] | [Page]
• (🔥 New) [2025/8/20] We release a new DC-AE-Lite for faster inference and smaller memory. [How to config] | [diffusers PR] | [Weight]
• (🔥 New) [2025/6/25] SANA-Sprint was accepted to ICCV'25 🏖️
• (🔥 New) [2025/6/4] SANA-Sprint ComfyUI Node is released [Example].
• (🔥 New) [2025/5/8] SANA-Sprint (One-step diffusion) diffusers training code is released [Guidance].
• (🔥 New) [2025/5/4] SANA-1.5 (Inference-time scaling) is accepted by ICML-2025. 🎉🎉🎉
• (🔥 New) [2025/3/22] 🔥SANA-Sprint demo is hosted on Huggingface, try it! 🎉 [Demo Link]
• (🔥 New) [2025/3/22] 🔥SANA-1.5 is supported in ComfyUI! 🎉: ComfyUI Guidance | ComfyUI Work Flow SANA-1.5 4.8B
• (🔥 New) [2025/3/22] 🔥SANA-Sprint code & weights are released! 🎉 Include: Training & Inference code and Weights / HF are all released. [Guidance]
• (🔥 New) [2025/3/21] 🚀Sana + Inference Scaling is released. [Guidance]

<details> <summary>Click to show all updates</summary>

• (🔥 New) [2025/3/16] 🔥SANA-1.5 code & weights are released! 🎉 Include: DDP/FSDP | TAR file WebDataset | Multi-Scale Training code and Weights | HF are all released.
• (🔥 New) [2025/3/14] 🏃SANA-Sprint is coming out! 🎉 A new one/few-step generator of Sana. 0.1s per 1024px image on H100, 0.3s on RTX 4090. Find out more details: [Page] | [Arxiv]. Code is coming very soon along with diffusers
• (🔥 New) [2025/2/10] 🚀Sana + ControlNet is released. [Guidance] | [Model] | [Demo]
• (🔥 New) [2025/1/30] Release CAME-8bit optimizer code. Saving more GPU memory during training. [How to config]
• (🔥 New) [2025/1/29] 🎉 🎉 🎉SANA 1.5 is out! Figure out how to do efficient training & inference scaling! 🚀[Tech Report]
• (🔥 New) [2025/1/24] 4bit-Sana is released, powered by SVDQuant and Nunchaku inference engine. Now run your Sana within 8GB GPU VRAM [Guidance] [Demo] [Model]
• (🔥 New) [2025/1/24] DCAE-1.1 is released, better reconstruction quality. [Model] [diffusers]
• (🔥 New) [2025/1/23] Sana is accepted as Oral by ICLR-2025. 🎉🎉🎉
• (🔥 New) [2025/1/12] DC-AE tiling makes Sana-4K inferences 4096x4096px images within 22GB GPU memory. With model offload and 8bit/4bit quantize. The 4K Sana run within 8GB GPU VRAM. [Guidance]
• (🔥 New) [2025/1/11] Sana code-base license changed to Apache 2.0.
• (🔥 New) [2025/1/10] Inference Sana with 8bit quantization.[Guidance]
• (🔥 New) [2025/1/8] 4K resolution Sana models is supported in Sana-ComfyUI and work flow is also prepared. [4K guidance]
• (🔥 New) [2025/1/8] 1.6B 4K resolution Sana models are released: [BF16 pth] or [BF16 diffusers]. 🚀 Get your 4096x4096 resolution images within 20 seconds! Find more samples in Sana page. Thanks SUPIR for their wonderful work and support.
• (🔥 New) [2025/1/2] Bug in the diffusers pipeline is solved. Solved PR
• (🔥 New) [2025/1/2] 2K resolution Sana models is supported in Sana-ComfyUI and work flow is also prepared.
• ✅ [2024/12] 1.6B 2K resolution Sana models are released: [BF16 pth] or [BF16 diffusers]. 🚀 Get your 2K resolution images within 4 seconds! Find more samples in Sana page. Thanks SUPIR for their wonderful work and support.
• ✅ [2024/12] diffusers supports Sana-LoRA fine-tuning! Sana-LoRA's training and convergence speed is super fast. [Guidance] or [diffusers docs].
• ✅ [2024/12] diffusers has Sana! All Sana models in diffusers safetensors are released and diffusers pipeline SanaPipeline, SanaPAGPipeline, DPMSolverMultistepScheduler(with FlowMatching) are all supported now. We prepare a Model Card for you to choose.
• ✅ [2024/12] 1.6B BF16 Sana model is released for stable fine-tuning.
• ✅ [2024/12] We release the ComfyUI node for Sana. [Guidance]
• ✅ [2024/11] All multi-linguistic (Emoji & Chinese & English) SFT models are released: 1.6B-512px, 1.6B-1024px, 600M-512px, 600M-1024px. The metric performance is shown here
• ✅ [2024/11] Sana Replicate API is launching at Sana-API.
• ✅ [2024/11] 1.6B Sana models are released.
• ✅ [2024/11] Training & Inference & Metrics code are released.
• ✅ [2024/11] Working on diffusers.
• [2024/10] Demo is released.
• [2024/10] DC-AE Code and weights are released!
• [2024/10] Paper is on Arxiv!

</details>

💡 Introduction

We introduce Sana, a text-to-image framework that can efficiently generate images up to 4096 × 4096 resolution. Sana can synthesize high-resolution, high-quality images with strong text-image alignment at a remarkably fast speed, deployable on laptop GPU. Core designs include:

(1) DC-AE: unlike traditional AEs, which compress images only 8×, we trained an AE that can compress images 32×, effectively reducing the number of latent tokens.
(2) Linear DiT: we replace all vanilla attention in DiT with linear attention, which is more efficient at high resolutions without sacrificing quality.
(3) Decoder-only text encoder: we replaced T5 with a modern decoder-only small LLM as the text encoder and designed complex human instruction with in-context learning to enhance the image-text alignment.
(4) Efficient training and sampling: we propose Flow-DPM-Solver to reduce sampling steps, with efficient caption labeling and selection to accelerate convergence.

As a result, Sana-0.6B is very competitive with modern giant diffusion models (e.g. Flux-12B), being 20 times smaller and 100+ times faster in measured throughput. Moreover, Sana-0.6B can be deployed on a 16GB laptop GPU, taking less than 1 second to generate a 1024 × 1024 resolution image. Sana enables content creation at low cost.

<p align="center" border-raduis="10px"> <img src="asset/model-incremental.jpg" width="90%" alt="teaser_page2"/> </p>

Performance

| Methods (1024x1024) | Throughput (samples/s) | Latency (s) | Params (B) | Speedup | FID 👇 | CLIP 👆 | GenEval 👆 | DPG 👆 |

<details> <summary><h4>Click to show all performance</h4></summary>

| Methods | Throughput (samples/s) | Latency (s) | Params (B) | Speedup | FID 👆 | CLIP 👆 | GenEval 👆 | DPG 👆 |

</details>

Contents

• Env
• Demo
• Model Zoo
• Training
• Testing
• TODO
• Citation

🔧 1. Dependencies and Installation

• Python >= 3.10.0 (Recommend to use Anaconda or Miniconda)
• PyTorch >= 2.0.1+cu12.1

git clone https://github.com/NVlabs/Sana.git
cd Sana

./environment_setup.sh sana
# or you can install each components step by step following environment_setup.sh

💻 2. How to Play with Sana (Inference)

💰Hardware requirement

• 9GB VRAM is required for 0.6B model and 12GB VRAM for 1.6B model. Our later quantization version will require less than 8GB for inference.
• All the tests are done on A100 GPUs. Different GPU version may be different.

🔛 Choose your model: Model card

🔛 Quick start with Gradio

# official online demo
DEMO_PORT=15432 \
python app/app_sana.py \
    --share \
    --config=configs/sana_config/1024ms/Sana_1600M_img1024.yaml \
    --model_path=hf://Efficient-Large-Model/Sana_1600M_1024px_BF16/checkpoints/Sana_1600M_1024px_BF16.pth \
    --image_size=1024

1. How to use SanaPipeline with 🧨diffusers

[!IMPORTANT] [!IMPORTANT] Upgrade your diffusers>=0.32.0.dev to make the SanaPipeline and SanaPAGPipeline available!

pip install git+https://github.com/huggingface/diffusers

Make sure to specify pipe.transformer to default torch_dtype and variant according to Model Card.

Set pipe.text_encoder to BF16 and pipe.vae to FP32 or BF16. For more info, docs are here.

# run `pip install git+https://github.com/huggingface/diffusers` before use Sana in diffusers
import torch
from diffusers import SanaPipeline

pipe = SanaPipeline.from_pretrained(
    "Efficient-Large-Model/SANA1.5_1.6B_1024px_diffusers",
    torch_dtype=torch.bfloat16,
)
pipe.to("cuda")

pipe.vae.to(torch.bfloat16)
pipe.text_encoder.to(torch.bfloat16)

prompt = 'a cyberpunk cat with a neon sign that says "Sana"'
image = pipe(
    prompt=prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    num_inference_steps=20,
    generator=torch.Generator(device="cuda").manual_seed(42),
)[0]

image[0].save("sana.png")

2. How to use SanaPAGPipeline with 🧨diffusers

<details> <summary>Click to show all</summary>

# run `pip install git+https://github.com/huggingface/diffusers` before use Sana in diffusers
import torch
from diffusers import SanaPAGPipeline

pipe = SanaPAGPipeline.from_pretrained(
  "Efficient-Large-Model/SANA1.5_1.6B_1024px_diffusers",
  torch_dtype=torch.bfloat16,
  pag_applied_layers="transformer_blocks.8",
)
pipe.to("cuda")

pipe.text_encoder.to(torch.bfloat16)
pipe.vae.to(torch.bfloat16)

prompt = 'a cyberpunk cat with a neon sign that says "Sana"'
image = pipe(
    prompt=prompt,
    guidance_scale=5.0,
    pag_scale=2.0,
    num_inference_steps=20,
    generator=torch.Generator(device="cuda").manual_seed(42),
)[0]
image[0].save('sana.png')

</details>

3. How to use Sana in this repo

<details> <summary>Click to show all</summary>

import torch
from app.sana_pipeline import SanaPipeline
from torchvision.utils import save_image

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
generator = torch.Generator(device=device).manual_seed(42)

sana = SanaPipeline("configs/sana1-5_config/1024ms/Sana_1600M_1024px_allqknorm_bf16_lr2e5.yaml")
sana.from_pretrained("hf://Efficient-Large-Model/SANA1.5_1.6B_1024px/checkpoints/SANA1.5_1.6B_1024px.pth")
prompt = 'a cyberpunk cat with a neon sign that says "Sana"'

image = sana(
    prompt=prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    pag_guidance_scale=1.0,
    num_inference_steps=20,
    generator=generator,
)
save_image(image, 'output/sana.png', nrow=1, normalize=True, value_range=(-1, 1))

</details>

4. Run Sana (Inference) with Docker

<details> <summary>Click to show all</summary>

# Pull related models
huggingface-cli download google/gemma-2b-it
huggingface-cli download google/shieldgemma-2b
huggingface-cli download mit-han-lab/dc-ae-f32c32-sana-1.1
huggingface-cli download Efficient-Large-Model/Sana_1600M_1024px

# Run with docker
docker build . -t sana
docker run --gpus all --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 \
    -v ~/.cache:/root/.cache \
    sana

</details>

5. Run inference with TXT or JSON files

# Run samples in a txt file
python scripts/inference.py \
      --config=configs/sana_config/1024ms/Sana_1600M_img1024.yaml \
      --model_path=hf://Efficient-Large-Model/Sana_1600M_1024px/checkpoints/Sana_1600M_1024px.pth \
      --txt_file=asset/samples/samples_mini.txt

# Run samples in a json file
python scripts/inference.py \
      --config=configs/sana_config/1024ms/Sana_1600M_img1024.yaml \
      --model_path=hf://Efficient-Large-Model/Sana_1600M_1024px/checkpoints/Sana_1600M_1024px.pth \
      --json_file=asset/samples/samples_mini.json

where each line of asset/samples/samples_mini.txt contains a prompt to generate

🔥 3. How to Train Sana

💰Hardware requirement

• 32GB VRAM is required for both 0.6B and 1.6B model's training

1). Train with image-text pairs in directory

We provide a training example here and you can also select your desired config file from config files dir based on your data structure.

To launch Sana training, you will first need to prepare data in the following formats. Here is an example for the data structure for reference.

asset/example_data
├── AAA.txt
├── AAA.png
├── BCC.txt
├── BCC.png
├── ......
├── CCC.txt
└── CCC.png

Then Sana's training can be launched via

# Example of training Sana 0.6B with 512x512 resolution from scratch
bash train_scripts/train.sh \
  configs/sana_config/512ms/Sana_600M_img512.yaml \
  --data.data_dir="[asset/example_data]" \
  --data.type=SanaImgDataset \
  --model.multi_scale=false \
  --train.train_batch_size=32

# Example of fine-tuning Sana 1.6B with 1024x1024 resolution
bash train_scripts/train.sh \
  configs/sana_config/1024ms/Sana_1600M_img1024.yaml \
  --data.data_dir="[asset/example_data]" \
  --data.type=SanaImgDataset \
  --model.load_from=hf://Efficient-Large-Model/Sana_1600M_1024px/checkpoints/Sana_1600M_1024px.pth \
  --model.multi_scale=false \
  --train.train_batch_size=8

2). Train with Multi-Scale WebDataset

We also provide conversion scripts to convert your data to the required format. You can refer to the data conversion scripts for more details.

python tools/convert_ImgDataset_to_WebDatasetMS_format.py

Then Sana's training can be launched via

# Example of training Sana 0.6B with 512x512 resolution from scratch
bash train_scripts/train.sh \
  configs/sana_config/512ms/Sana_600M_img512.yaml \
  --data.data_dir="[asset/example_data_tar]" \
  --data.type=SanaWebDatasetMS \
  --model.multi_scale=true \
  --train.train_batch_size=32

3). Train with TAR file

We prepared a toy TAR dataset containing 100 random images from Journey-DB, duplicated for testing purposes. Note that this dataset is not intended for training.

huggingface-cli download Efficient-Large-Model/toy_data --repo-type dataset --local-dir ./data/toy_data --local-dir-use-symlinks False

Then, you are ready to run with FSDP or DDP:

# DDP
# Example of training Sana 1.6B with 512x512 resolution from scratch
bash train_scripts/train.sh \
      configs/sana1-5_config/1024ms/Sana_1600M_1024px_allqknorm_bf16_lr2e5.yaml \
      --data.data_dir="[data/toy_data]" \
      --data.type=SanaWebDatasetMS \
      --model.multi_scale=true \
      --data.load_vae_feat=true \
      --train.train_batch_size=2

# FSDP
# Example of training Sana 1.6B with 512x512 resolution from scratch
bash train_scripts/train.sh \
      configs/sana1-5_config/1024ms/Sana_1600M_1024px_AdamW_fsdp.yaml \
      --data.data_dir="[data/toy_data]" \
      --data.type=SanaWebDatasetMS \
      --model.multi_scale=true \
      --data.load_vae_feat=true \
      --train.use_fsdp=true \
      --train.train_batch_size=2

💻 4. Metric toolkit

Refer to Toolkit Manual.

🚀 5. Inference Scaling

We trained a specialized NVILA-2B model to score images, which we named VISA (VIla as SAna verifier). By selecting the top 4 images from 2,048 candidates, we enhanced the GenEval performance of SD1.5 and SANA-1.5-4.8B v2, increasing their scores from 42 to 87 and 81 to 96, respectively. Details refer to Inference Scaling Manual.

| Method | Overall | Single | Two | Counting | Colors | Position | Color Attribution |

🏃 6. SANA-Sprint

Our SANA-Sprint models focus on timestep distillation, achieving high-quality generation with 1-4 inference steps. Refer to SANA-Sprint Manual for more details.

<div align="center"> <a href="https://www.youtube.com/watch?v=nI_Ohgf8eOU" target="_blank"> <img src="https://img.youtube.com/vi/nI_Ohgf8eOU/0.jpg" alt="Demo Video of SANA-Sprint" style="width: 60%; margin: 0 auto; display: block"> </a> </div>

🎬 7. SANA-Video

SANA-Video is a small diffusion model designed for efficient video generation, capable of synthesizing high-resolution videos (up to $720 \times 1280$) and minute-length duration with strong text-video alignment, while maintaining a remarkably fast speed.It enables low-cost, high-quality video generation and can be deployed efficiently on consumer GPUs like the RTX 5090. Refer to SANA-Video Manual for more details.

<div align="center"> <a href="https://www.youtube.com/watch?v=ztdkfIMkdJ4" target="_blank"> <img src="https://img.youtube.com/vi/ztdkfIMkdJ4/0.jpg" alt="Demo Video of SANA-Sprint" style="width: 60%; margin: 0 auto; display: inline-block"> </a> </div>

💪To-Do List

We will try our best to achieve

• [✅] Training code
• [✅] Inference code
• [✅] Model zoo
• [✅] ComfyUI Nodes(SANA, SANA-1.5, SANA-Sprint)
• [✅] DC-AE Diffusers
• [✅] Sana merged in Diffusers(https://github.com/huggingface/diffusers/pull/9982)
• [✅] LoRA training by @paul(diffusers: https://github.com/huggingface/diffusers/pull/10234)
• [✅] 2K/4K resolution models.(Thanks @SUPIR to provide a 4K super-resolution model)
• [✅] 8bit / 4bit Laptop development
• [✅] ControlNet (train & inference & models)
• [✅] FSDP Training
• [✅] SANA-1.5 (Larger model size / Inference Scaling)
• [✅] SANA-Sprint: Few-step generator
• [✅] Faster DCAE-Lite weight
• [✅] Better re-construction F32/F64 VAEs.
• [✅] SANA-Video: Linear DiT Video model, and real-time minute-length video generation
• [🚀] See you in the future

🤗Acknowledgements

Thanks to the following open-sourced codebase for their wonderful work and codebase!

• PixArt-α
• PixArt-Σ
• diffusers
• Efficient-ViT
• ComfyUI_ExtraModels
• SVDQuant and Nunchaku
• Open-Sora
• Wan
• LongLive

Thanks Paper2Video for generating Jeason presenting SANA😊. Refer to Paper2Video for more details.

<div align="center"> <a href="https://showlab.github.io/Paper2Video/assets/huang/huang.mp4" target="_blank"> <img src="asset/paper2video.jpg" alt="Presenting Video of SANA" style="width: 60%; margin: 0 auto; display: block"> </a> </div>

Contribution

Thanks goes to these wonderful contributors:

<a href="https://github.com/NVlabs/Sana/graphs/contributors"> <img src="https://contrib.rocks/image?repo=NVlabs/Sana" /> </a>

🌟 Star History

📖BibTeX

@misc{xie2024sana,
      title={Sana: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer},
      author={Enze Xie and Junsong Chen and Junyu Chen and Han Cai and Haotian Tang and Yujun Lin and Zhekai Zhang and Muyang Li and Ligeng Zhu and Yao Lu and Song Han},
      year={2024},
      eprint={2410.10629},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2410.10629},
    }
@misc{xie2025sana,
      title={SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer},
      author={Xie, Enze and Chen, Junsong and Zhao, Yuyang and Yu, Jincheng and Zhu, Ligeng and Lin, Yujun and Zhang, Zhekai and Li, Muyang and Chen, Junyu and Cai, Han and others},
      year={2025},
      eprint={2501.18427},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2501.18427},
    }
@misc{chen2025sanasprint,
      title={SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation},
      author={Junsong Chen and Shuchen Xue and Yuyang Zhao and Jincheng Yu and Sayak Paul and Junyu Chen and Han Cai and Song Han and Enze Xie},
      year={2025},
      eprint={2503.09641},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2503.09641},
    }
@misc{chen2025sana,
      title={SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer},
      author={Chen, Junsong and Zhao, Yuyang and Yu, Jincheng and Chu, Ruihang and Chen, Junyu and Yang, Shuai and Wang, Xianbang and Pan, Yicheng and Zhou, Daquan and Ling, Huan and others},
      year={2025},
      eprint={2509.24695},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2509.24695},
    }