Instructions to use torpedo2003/SAD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use torpedo2003/SAD with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("torpedo2003/SAD", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Model card: arXiv 2611.22458
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ tags:
|
|
| 14 |
<sup>1</sup>Institute of Computing Technology, Chinese Academy of Sciences<br>
|
| 15 |
<sup>2</sup>University of Chinese Academy of Sciences <sup>3</sup>Tsinghua University
|
| 16 |
|
| 17 |
-
[Project page](https://torpedo2003.github.io/SAD/) 路 [Code](https://github.com/torpedo2003/SAD)
|
| 18 |
|
| 19 |
These are drop-in decoders for latent generative models. Each file holds only the decoder (`decoder.*`, `post_quant_conv.*`) of
|
| 20 |
the original autoencoder. It was fine-tuned with SAD on latents from one generator. The encoder, the latent space and the
|
|
@@ -72,7 +72,7 @@ To train a decoder for your own generator, see the [training guide](https://gith
|
|
| 72 |
@article{lei2026sad,
|
| 73 |
title = {Sample-Aligned Decoders for Latent Generative Models},
|
| 74 |
author = {Lei, Yu and Li, Yi and Gao, Hongcheng and Wei, Yipeng and Li, Liang and Su, Li and Huang, Qingming},
|
| 75 |
-
journal = {arXiv preprint},
|
| 76 |
year = {2026}
|
| 77 |
}
|
| 78 |
```
|
|
|
|
| 14 |
<sup>1</sup>Institute of Computing Technology, Chinese Academy of Sciences<br>
|
| 15 |
<sup>2</sup>University of Chinese Academy of Sciences <sup>3</sup>Tsinghua University
|
| 16 |
|
| 17 |
+
[Paper](https://arxiv.org/abs/2611.22458) 路 [Project page](https://torpedo2003.github.io/SAD/) 路 [Code](https://github.com/torpedo2003/SAD)
|
| 18 |
|
| 19 |
These are drop-in decoders for latent generative models. Each file holds only the decoder (`decoder.*`, `post_quant_conv.*`) of
|
| 20 |
the original autoencoder. It was fine-tuned with SAD on latents from one generator. The encoder, the latent space and the
|
|
|
|
| 72 |
@article{lei2026sad,
|
| 73 |
title = {Sample-Aligned Decoders for Latent Generative Models},
|
| 74 |
author = {Lei, Yu and Li, Yi and Gao, Hongcheng and Wei, Yipeng and Li, Liang and Su, Li and Huang, Qingming},
|
| 75 |
+
journal = {arXiv preprint arXiv:2611.22458},
|
| 76 |
year = {2026}
|
| 77 |
}
|
| 78 |
```
|