Fast, low-latency text-to-image model with high-quality output and full JSON-structured controllability. Open-source, trained on licensed data, and optimized for production-scale generation.

bria/fibo-lite/generate

Fast, low-latency text-to-image model with high-quality output and full JSON-structured controllability. Open-source, trained on licensed data, and optimized for production-scale generation.

Inference

Commercial use

Partner

Schema

Playground API Examples

SandboxOpen in Sandbox

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

bria/fibo-lite/generate

Schema

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

{ "image": { "url": "https://v3b.fal.media/files/b/0a8739b1/5PkOKEpdQu16ZkS3ovA92_e0d9e8ab6833478aa854cba5ca1c88ad.png", "width": 1024, "height": 1024, "file_name": "e0d9e8ab6833478aa854cba5ca1c88ad.png", "file_size": 1393039, "content_type": "image/png" }, "images": [ { "url": "https://v3b.fal.media/files/b/0a8739b1/5PkOKEpdQu16ZkS3ovA92_e0d9e8ab6833478aa854cba5ca1c88ad.png" } ], "structured_prompt": { "context": "This image is an artistic, abstract photograph, likely intended for use in advertising related to coffee, or as a fine art print for interior decoration.", "objects": [ { "texture": "slightly rough, matte surface with a subtle sheen", "location": "center foreground and midground", "description": "A cluster of roasted coffee beans, appearing vibrant red due to the color filter.", "orientation": "varied, some upright, some tilted", "relationship": "The beans are suspended in the air, appearing to float.", "relative_size": "medium to large within frame", "shape_and_color": "Oval, bean-shaped. Dominant color is a vivid red, with hints of darker red and black.", "number_of_objects": 5, "appearance_details": "Each bean has a distinct central groove. Some beans show slight imperfections or variations in roast level." }, { "texture": "slightly rough, matte surface with a subtle sheen", "location": "bottom-left foreground", "description": "A single roasted coffee bean, prominently featured in the foreground.", "orientation": "tilted slightly", "relationship": "It is part of the floating cluster, closest to the viewer.", "relative_size": "large within frame", "shape_and_color": "Oval, bean-shaped. Vivid red color with darker red and black undertones.", "number_of_objects": 1, "appearance_details": "Clearly defined central groove, sharp edges." }, { "texture": "slightly rough, matte surface with a subtle sheen", "location": "top-center midground", "description": "A roasted coffee bean, positioned in the upper-center of the frame.", "orientation": "upright", "relationship": "It is part of the floating cluster, positioned above and behind the central bean.", "relative_size": "medium", "shape_and_color": "Oval, bean-shaped. Vivid red color.", "number_of_objects": 1, "appearance_details": "Distinct central groove, well-defined." } ], "lighting": { "shadows": "soft, elongated shadows cast by the beans onto the implied space, adding depth", "direction": "side-lit from the right, with some fill light from the left", "conditions": "dramatic, moody lighting" }, "aesthetics": { "composition": "extreme close-up, centered with floating elements", "color_scheme": "monochromatic red with black background", "aesthetic_score": "very high", "mood_atmosphere": "intense, dramatic, moody, artistic", "preference_score": "very high" }, "style_medium": "photograph", "artistic_style": "abstract, dramatic, monochromatic", "short_description": "An extreme close-up, artistic photograph of several red coffee beans floating in mid-air against a stark black background. The image is characterized by a dramatic red color filter that casts an intense, moody atmosphere. The shallow depth of field keeps the foreground beans in sharp focus, while the background elements blur into an abstract, dark expanse. The composition emphasizes the texture and form of the beans, creating a visually striking and abstract representation of coffee.", "background_setting": "A completely dark, black background that is devoid of any discernible features, creating a stark contrast with the red coffee beans.", "photographic_characteristics": { "focus": "sharp focus on the foreground beans, with a soft bokeh effect on background beans", "camera_angle": "slightly low angle", "depth_of_field": "shallow", "lens_focal_length": "macro lens" } } }

Overview

Fibo Lite, the new addition to the Fibo model family, allows generating high-quality images with the same controllability of the JSON structured prompt, while using significantly fewer inference steps, resulting in significantly improved latency.

This is a two-stage distilled model for the FIBO text-to-image model, combining:

CFG Distillation: First, we distill classifier-free guidance into the model, enabling inference with Guidance Scale = 1.0 (skipping the negative prompt pass).
SCFM (Shortcutting Flow Matching): On top of the CFG-distilled merged model, we apply velocity field self-distillation to enable efficient few-step sampling.

🔑 Key Benefits

Two-Stage Distillation: Combines CFG distillation with SCFM for maximum efficiency—the SCFM was trained on top of the already CFG-distilled merged model.
Few-Step Generation: SCFM enables efficient sampling in significantly fewer inference steps.
No CFG Overhead: Running at guidance_scale=1 means calculating the noise prediction only once per step instead of twice.
Quality Tradeoff: As a distillation approach, there is a slight quality degradation compared to the full model at CFG=5, but the speed gains make it ideal for rapid iteration and production workflows.
Drop-in Replacement: Works seamlessly with existing FIBO workflows—just set guidance_scale=1.0.
Memory Efficient: Minimal additional GPU memory overhead.