Instructions to use microsoft/Lens-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use microsoft/Lens-Base with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("microsoft/Lens-Base", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -11,29 +11,30 @@ pipeline_tag: text-to-image
|
|
| 11 |
<img src="assets/teaser.webp" alt="Lens Teaser" width="100%" />
|
| 12 |
|
| 13 |
<p>
|
| 14 |
-
<
|
| 15 |
-
<strong>
|
| 16 |
-
<strong>
|
| 17 |
-
<strong>Zhiyang Liang</strong>*,
|
| 18 |
-
<strong>Yang Yue</strong>*,
|
| 19 |
-
<strong>Jiawei Zhang</strong>*,
|
| 20 |
-
<strong>Fangyun Wei</strong>†,
|
| 21 |
<strong>Dong Chen</strong>†,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
<strong>Qinhong Yang</strong>,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
<strong>Yanchen Dong</strong>,
|
|
|
|
| 24 |
<strong>Yitong Wang</strong>,
|
| 25 |
<strong>Yunuo Chen</strong>,
|
| 26 |
-
<strong>
|
| 27 |
-
<strong>Ziyu Wan</strong>
|
| 28 |
-
<strong>Lei Shi</strong>,
|
| 29 |
-
<strong>Ji Li</strong>,
|
| 30 |
-
<strong>Dongdong Chen</strong>,
|
| 31 |
-
<strong>Chong Luo</strong>,
|
| 32 |
-
<strong>Yan Lu</strong>,
|
| 33 |
-
<strong>Baining Guo</strong>
|
| 34 |
-
</sub>
|
| 35 |
<br />
|
| 36 |
-
|
| 37 |
</p>
|
| 38 |
|
| 39 |
<p>
|
|
@@ -399,7 +400,7 @@ python inference.py \
|
|
| 399 |
```bibtex
|
| 400 |
@article{zhao2026lens,
|
| 401 |
title = {Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models},
|
| 402 |
-
author = {
|
| 403 |
journal = {arXiv preprint arXiv:PLACEHOLDER},
|
| 404 |
year = {2026}
|
| 405 |
}
|
|
|
|
| 11 |
<img src="assets/teaser.webp" alt="Lens Teaser" width="100%" />
|
| 12 |
|
| 13 |
<p>
|
| 14 |
+
<b>Contributors (Alphabetical Order):</b><br />
|
| 15 |
+
<strong>Baining Guo</strong>,
|
| 16 |
+
<strong>Chong Luo</strong>,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
<strong>Dong Chen</strong>†,
|
| 18 |
+
<strong>Dongdong Chen</strong>,
|
| 19 |
+
<strong>Fangyun Wei</strong>†,
|
| 20 |
+
<strong>Ji Li</strong>,
|
| 21 |
+
<strong>Jianmin Bao</strong>,
|
| 22 |
+
<strong>Jiawei Zhang</strong>*,
|
| 23 |
+
<strong>Jinjing Zhao</strong>*,
|
| 24 |
+
<strong>Lei Shi</strong>,
|
| 25 |
<strong>Qinhong Yang</strong>,
|
| 26 |
+
<strong>Sirui Zhang</strong>*,
|
| 27 |
+
<strong>Xiuyu Wu</strong>,
|
| 28 |
+
<strong>Xuelu Feng</strong>,
|
| 29 |
+
<strong>Yan Lu</strong>,
|
| 30 |
<strong>Yanchen Dong</strong>,
|
| 31 |
+
<strong>Yang Yue</strong>*,
|
| 32 |
<strong>Yitong Wang</strong>,
|
| 33 |
<strong>Yunuo Chen</strong>,
|
| 34 |
+
<strong>Zhiyang Liang</strong>*,
|
| 35 |
+
<strong>Ziyu Wan</strong>†
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
<br />
|
| 37 |
+
Microsoft | *Core Contributors | †Project Lead
|
| 38 |
</p>
|
| 39 |
|
| 40 |
<p>
|
|
|
|
| 400 |
```bibtex
|
| 401 |
@article{zhao2026lens,
|
| 402 |
title = {Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models},
|
| 403 |
+
author = {Guo, Baining and Luo, Chong and Chen, Dong and Chen, Dongdong and Wei, Fangyun and Li, Ji and Bao, Jianmin and Zhang, Jiawei and Zhao, Jinjing and Shi, Lei and Yang, Qinhong and Zhang, Sirui and Wu, Xiuyu and Feng, Xuelu and Lu, Yan and Dong, Yanchen and Yue, Yang and Wang, Yitong and Chen, Yunuo and Liang, Zhiyang and Wan, Ziyu},
|
| 404 |
journal = {arXiv preprint arXiv:PLACEHOLDER},
|
| 405 |
year = {2026}
|
| 406 |
}
|