README.md

---
license: creativeml-openrail-m
language:
- en
pipeline_tag: text-to-image
---

# F Lite 7B Model Card

![F Lite 7B mosaic](f_lite_7b_gallery.jpg)

F Lite 7B is a **7 B parameter** diffusion model developed by [Freepik](https://www.freepik.com) and [Fal](https://fal.ai).

It has been built through knowledge distillation from [F Lite](https://huggingface.co/Freepik/F-Lite) and, as such, it delivers image quality comparable to its larger sibling while being faster and more memory-efficient. It also preserves the same copyright-safe, SFW generation characteristics as F Lite.

## Usage

Try F Lite 7B instantly through our [interactive demo](https://huggingface.co/spaces/Freepik/F-Lite-7B) on Hugging Face.

F Lite 7B works with both the `diffusers` library and [ComfyUI](https://www.comfy.org/). For details, see the [F Lite GitHub repository](https://github.com/fal-ai/f-lite).

## Technical Report

Read the [technical report](https://github.com/fal-ai/f-micro/blob/main/assets/F%20Micro%20Technical%20Report.pdf) to learn more about the model architecture, training recipe and evaluation.

## Limitations and Bias

* Like its teacher, the model can generate malformations.
* Text rendering capabilities remain limited.
* Despite careful curation, societal and aesthetic biases can still emerge.

## Recommendations

* Longer, descriptive prompts improve quality; very short prompts may yield sub-optimal images.
* Generate images above the megapixel mark; low resolutions reduce fidelity.

## Acknowledgements

This model relies on high-quality components including [T5 XXL](https://huggingface.co/google/t5-v1_1-xxl) for prompt encoding and the [Flux Schnell VAE](https://huggingface.co/black-forest-labs/FLUX.1-schnell) for efficient latent-space compression.

## License

The F Lite 7B weights are released under the permissive **CreativeML Open RAIL-M** license. Dependencies inherit their respective licenses (Apache 2.0 for T5 XXL and Flux Schnell VAE).

## Citation

```bibtex
@article{ryu2025flite,
  title={F Lite Technical Report},
  author={Ryu, Simo and Pengqi, Lu and Mart\'in Juan, Javier and de Prado Alonso, Iv\'an},
  year={2025}
}
```