Downloads · 30 days
0
NYCU-MLLab/State-Space-Flow-Matching-for-Shortcut-Generation
State-Space-Flow-Matching-for-Shortcut-Generation is a machine learning model from NYCU-MLLab. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for diffusers.
This repository contains four SSFM student transformer checkpoints for the Sana 1024px pipeline. The repository contains student transformer weights only; the base pipeline is downloaded separately.
Downloads · 30 days
0
Access
Public
Updated Aug 24, 2026
Repo size
11.9 GB
Likes
0
Public
Click a slice to open those files.
.safetensors9.5 GB · 100%
From the Hugging Face model README
This repository contains four SSFM student transformer checkpoints for the Sana 1024px pipeline. The repository contains student transformer weights only; the base pipeline is downloaded separately.
| Directory | Variant | Supported steps | Notes |
|---|---|---|---|
SSFM_fixed_2 | Fixed-step SSFM | 2 | EMA student checkpoint |
SSFM_fixed_4 | Fixed-step SSFM | 4 | EMA student checkpoint |
SSFM_unified_24 | Unified SSFM | 2, 4 | EMA student checkpoint |
SSFM_unified_124 | Unified SSFM | 1, 2, 4 | EMA student checkpoint |
Use the official Sana Sprint teacher pipeline:
Efficient-Large-Model/Sana_Sprint_0.6B_1024px_teacher_diffusers
The official base model is not duplicated in this repository.
Each model directory contains:
config.json
diffusion_pytorch_model.safetensors
Use the selected directory as the STUDENT_MODEL_DIR, FIXED2_MODEL_DIR, or
FIXED4_MODEL_DIR path in the SSFM GitHub code.
These checkpoints are derived from the Sana/Sana-Sprint model family. Please follow the upstream model license and terms when using or redistributing the weights:
https://huggingface.co/Efficient-Large-Model/Sana_Sprint_0.6B_1024px_teacher_diffusers