Accurate typography
Lettering inside the picture is rendered accurately.
Create a picture from a description
Fibo
SOTA open-source text-to-image model delivering high-fidelity outputs with accurate typography. JSON-structured prompts provide production-ready controllability for enterprise and agentic workflows. Trained exclusively on licensed data.
Made by Bria400 creditsper run Pro
Opens the image studio with Fibo ready to use. You can look around as a guest. Running it takes the Pro plan or higher.
What Fibo makes, what it needs and what you get
What it makes
Create a picture from a description
Turns a written description into a picture.
What you need
- A description of the picture
Optional: a picture to start from.
What you get
A new picture
- 9 aspect ratios
About Fibo
Fibo is an open-source text-to-image model from Bria AI. You describe a picture and it returns a high-fidelity image with accurate typography, meaning the lettering in the picture. Fibo was trained only on licensed data.
Fibo takes a Prompt and one reference image. It also takes a Structured Prompt, a prompt written in a fixed JSON layout. Aspect Ratio has nine choices: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16 and 16:9. It starts at 1:1. Resolution offers 1MP or 4MP (megapixels) and starts at 1MP.
Fibo costs 400 credits. Fibo Lite costs 360 credits and has no Resolution option. Fibo Bbq Preview also costs 400 credits, but it has a Guidance Scale option in place of Resolution.
Other models for this job
Same job: create a picture from a description. Compare before you choose.
Image Free Open
SDXL LightningCreate a picture from a description
A speed-tuned variant of Stable Diffusion XL that generates high-quality images in a handful of steps, trading a little fine detail for near-instant results - ideal for rapid concept exploration and draft iteration.
ByteDance10 creditsper run
Image Free Open
Qwen Image LightningCreate a picture from a description
Alibaba's fast-inference Qwen Image variant, tuned for near-instant text-to-image generation without sacrificing prompt accuracy - built for rapid drafts and high-volume workflows.
Alibaba10 creditsper run
Image Free Open
Qwen ImageCreate a picture from a description
Alibaba's Qwen Image model generates accurate, detailed visuals from text prompts with strong prompt comprehension, including legible in-image text and complex compositions.
Alibaba10 creditsper run
Image Free Open
Flux KreaCreate a picture from a description
A FLUX variant tuned by Krea for stylized, painterly image generation - strong for concept art and creative visuals that want more artistic flair than strict photorealism.
Black Forest Labs85 creditsper run
What it does well
Structured Prompt input
Give a Structured Prompt, a prompt written in a fixed JSON layout.
One reference image
Add one reference image to your run.
How to use Fibo
How It Works
How It Works
01
Open Fibo
Pick Fibo from the text-to-image models.
02
Add your prompt
Write a Prompt that describes the picture. You can also add a Structured Prompt or one reference image.
03
Set shape and size, then generate
Choose an Aspect Ratio and a Resolution if you want, then start the run. Fibo costs 400 credits.
Tip Aspect Ratio starts at 1:1 and Resolution at 1MP. Change them if you need another shape or a 4MP image.
Good for
Posters and signs with text
Make pictures that contain lettering, since Fibo renders typography accurately.
Scenes and objects from a description
Describe a scene or an object in the Prompt and get an image back.
Questions
Quick answers to help you get the most out of Fibo in FunAI Studio.
1. What can I give Fibo?
2. What can I change?
3. What do I get back, and what does it cost?