F-Lite -> F Lite
Browse files
README.md
CHANGED
|
@@ -5,17 +5,17 @@ language:
|
|
| 5 |
pipeline_tag: text-to-image
|
| 6 |
---
|
| 7 |
|
| 8 |
-
# F
|
| 9 |
|
| 10 |
-
and [Flux Sch
|
|
| 36 |
|
| 37 |
## License
|
| 38 |
|
| 39 |
-
The F
|
| 40 |
|
| 41 |
## Citation
|
| 42 |
|
|
@@ -44,7 +44,7 @@ If you find our work helpful, please cite it!
|
|
| 44 |
|
| 45 |
```
|
| 46 |
@article{ryu2025flite,
|
| 47 |
-
title={F
|
| 48 |
author={Ryu, Simo and Pengqi, Lu and Mart\'in Juan, Javier and de Prado Alonso, Iv\'an},
|
| 49 |
year={2025}
|
| 50 |
}
|
|
|
|
| 5 |
pipeline_tag: text-to-image
|
| 6 |
---
|
| 7 |
|
| 8 |
+
# F Lite Model Card
|
| 9 |
|
| 10 |
+

|
| 11 |
|
| 12 |
+
F Lite is a 10B parameter diffusion model created by [Freepik](https://www.freepik.com) and [Fal](https://fal.ai), trained exclusively on copyright-safe and SFW content. The model was trained on Freepik's internal dataset comprising approximately 80 million copyright-safe images, making it the first publicly available model of this scale trained exclusively on legally compliant and SFW content.
|
| 13 |
|
| 14 |
## Usage
|
| 15 |
|
| 16 |
+
Experience F Lite instantly through our [interactive demo](https://huggingface.co/spaces/Freepik/F-Lite) on Hugging Face.
|
| 17 |
|
| 18 |
+
F Lite works with both the `diffusers` library and [ComfyUI](https://www.comfy.org/). For details, see the [F Lite GitHub repository](https://github.com/Freepik/F-Lite).
|
| 19 |
|
| 20 |
# Technical Report
|
| 21 |
|
|
|
|
| 36 |
|
| 37 |
## License
|
| 38 |
|
| 39 |
+
The F Lite weights are licensed under the permissive CreativeML Open RAIL-M license. The T5 XXL and Flux Schnell VAE are licensed under Apache 2.0.
|
| 40 |
|
| 41 |
## Citation
|
| 42 |
|
|
|
|
| 44 |
|
| 45 |
```
|
| 46 |
@article{ryu2025flite,
|
| 47 |
+
title={F Lite Technical Report},
|
| 48 |
author={Ryu, Simo and Pengqi, Lu and Mart\'in Juan, Javier and de Prado Alonso, Iv\'an},
|
| 49 |
year={2025}
|
| 50 |
}
|