Junsong Chen

[docs] add doc for PixArtSigmaPipeline

4

# What does this PR do? This PR adds docs for PixArtSigmaPipeline. Cc: @sayakpaul @yiyixuxu

training time

2

Thanks a lot for your work! I wanna ask about the total training time on 8 3090s?

[DC-AE] Add the official Deep Compression Autoencoder code(32x,64x,128x compression ratio);

1

# What does this PR do? This PR will add the official DC-AE (Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models) into the `diffusers` lib. DC-AE first makes the Autoencoder...

1. update readme; 2. update CI test code;

🎉Glad to announce SANA-Sprint is available!

9

Our SANA-Sprint models focus on timestep distillation, achieving high-quality generation with 1-4 inference steps. Refer to [SANA-Sprint Manual](https://github.com/NVlabs/Sana/blob/main/asset/docs/sana_sprint.md) for more details. After the PR merged: https://github.com/huggingface/diffusers/pull/11074 pip install git+https://github.com/huggingface/diffusers ```python...

Sana-ControlNet inference and demo are out! 🚀

11

Refer to: [Guidance](https://nv-sana.mit.edu/ctrlnet/) [Model Zoo](https://github.com/NVlabs/Sana/blob/main/asset/docs/model_zoo.md) [Demo](https://github.com/NVlabs/Sana/blob/main/asset/docs/sana_controlnet.md)

1. add longlive inference code; 2. clean longlive flow euler code; 3. run success; Ref: [LongLive](https://github.com/NVlabs/LongLive) Cc: Thank to @HeliosZhao for supporting this part. ```bash # LongSANA Text to Video...

[feat] LongSANA: a minute-length real-time video generation model

6

This PR supports LongSANA: a minute-length real-time video generation model ## Related links: project: https://nvlabs.github.io/Sana/Video code: https://github.com/NVlabs/Sana paper: https://arxiv.org/pdf/2509.24695 ## PR feature: LongSANA uses Causal Linear Attention KV Cache during...