|  | --- | 
					
						
						|  | license: creativeml-openrail-m | 
					
						
						|  | language: | 
					
						
						|  | - en | 
					
						
						|  | pipeline_tag: text-to-image | 
					
						
						|  | --- | 
					
						
						|  |  | 
					
						
						|  | # F Lite Model Card | 
					
						
						|  |  | 
					
						
						|  |  | 
					
						
						|  |  | 
					
						
						|  | 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. | 
					
						
						|  |  | 
					
						
						|  | ## Usage | 
					
						
						|  |  | 
					
						
						|  | Experience F Lite instantly through our [interactive demo](https://huggingface.co/spaces/Freepik/F-Lite) on Hugging Face or at [fal.ai](https://fal.ai/models/fal-ai/f-lite/standard). | 
					
						
						|  |  | 
					
						
						|  | 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/fal-ai/f-lite). | 
					
						
						|  |  | 
					
						
						|  | # Technical Report | 
					
						
						|  |  | 
					
						
						|  | Read the [technical report](https://github.com/fal-ai/f-lite/blob/main/assets/F%20Lite%20Technical%20Report.pdf) to learn more about the model details. | 
					
						
						|  |  | 
					
						
						|  | # 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 | 
					
						
						|  | * 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. | 
					
						
						|  |  | 
					
						
						|  | ## Acknowledgements | 
					
						
						|  |  | 
					
						
						|  | This model uses [T5 XXL](https://huggingface.co/google/t5-v1_1-xxl)and [Flux Schnell VAE](https://huggingface.co/black-forest-labs/FLUX.1-schnell) | 
					
						
						|  |  | 
					
						
						|  | ## 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. | 
					
						
						|  |  | 
					
						
						|  | ## 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} | 
					
						
						|  | } | 
					
						
						|  | ``` |