F Lite

🚀 F Lite Model Card

F Lite is a 10B parameter diffusion model jointly developed by Freepik and Fal. It is trained solely on copyright - safe and SFW content, offering a reliable solution for text - to - image generation.

🚀 Quick Start

Experience F Lite instantly through our interactive demo on Hugging Face or at fal.ai.

F Lite works with both the diffusers library and ComfyUI. For details, see the F Lite GitHub repository.

✨ Features

F Lite is the first publicly available model of this scale trained exclusively on legally compliant and SFW content. It was trained on Freepik's internal dataset of about 80 million copyright - safe images.

🔧 Technical Details

Read the technical report to learn more about the model details.

📚 Documentation

Limitations and Bias

• The models can generate malformations.
• The text capabilities of the model are limited.
• The model can be subject to biases, although we think we have a good balance given the quality and variety of the Freepik's dataset.

Recommendations

⚠️ Important Note

The models have limitations such as potential malformations, limited text capabilities, and possible biases.

💡 Usage Tip

• Use long prompts to generate better results. Short prompts may result in low - quality images.
• Generate images above the megapixel. Smaller images will result in low - quality images.

📄 License

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.

Acknowledgements

This model uses T5 XXL and Flux Schnell VAE

Citation

If you find our work helpful, please cite it!

@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}
}