Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Image
  3. Bria

FIBO 2

Try Model

FIBO 2 by Bria creates images from text and edits up to four ordered source and reference images. Use Inspiration to create a new scene from one visual reference, or a same-size mask to edit one image while preserving pixels outside the mask. Generation and multi-image edits support 21 aspect ratios at about 1MP; single-image edits preserve the source aspect ratio. Supports four photographic styles, reproducible seeds, and reusable structured VGL prompts.

Added Oct 20, 2026

Details

Approx. Price
$0.040 per image
Model type
both

Settings

Generation controls available for this model.

Images Per Run

Fixed 1

Output images

Input Images

Up to 4

Reference/edit images accepted • Route max 30 MB

Output Sizes

Auto

Aspect ratio

Select

Default

auto

Options (22)

Auto, 1:1, 1:2, 1:3 +18 more

Auto uses 1:1 for generation and the first input ratio for editing. Single-image edits require Auto.

Mask URL (optional if drawn below)

Text

Default

N/A

PNG matching one source image. White regenerates; black preserves. Edit mode only.

Mode

Select

Default

auto

Options (4)

Generate / edit, Generate, Edit, Inspiration

Auto edits uploaded images, or generates from text. Inspiration uses one image to create a new scene or close variation.

Number of Images

Default

1

Paint an edit mask

Toggle

Default

No

Enable the mask editor for one source image. White regenerates; black preserves. Leave off for a whole-image edit.

Photographic style

Select

Default

none

Options (5)

None, Kodak Film, Hard Flash, Hazy Dreamy +1 more

Generation with text only. Cannot combine with images or structured VGL.

Resolution

Default

auto

Options (1)

auto (About 1MP; masked edits keep source dimensions)

Seed

Number

Default

5555

Structured VGL (optional JSON)

Text

Default

N/A

Reuse a returned VGL alone, or refine it with text. VGL-only edits need edit_instruction. Cannot combine with Inspiration or a style. Maximum 256 KiB as serialized JSON.

Benchmarks

No public benchmark scores for this model yet.

Examples

Loading examples…

Related image models

Compare FIBO 2 with similar models from the same provider or model family.

Bria FIBO Generate 1.5

bria/fibo-generate-1.5/text-to-image

Bria FIBO 1.5 creates commercially safe images from text and edits uploaded images. Choose Erase for masked object removal, or Expand to extend a canvas while preserving original pixels. Generation supports photoreal styling, structured prompts, and up to 4MP output.

Bria Guided Background Removal

bria/remove-background-guided

Remove a background and optionally describe which objects to keep, drop, or isolate. A blank prompt gives standard background removal. Retained objects use the original pixels with a new alpha channel, preserving the input canvas.

Bria Product Holding

bria/product-holding

Place one to three referenced products naturally into a person's hands while preserving the subject and scene. Built for e-commerce, lifestyle advertising, influencer content, and product campaigns.

Bria Virtual Try-On

bria/virtual-try-on

Dress a person in one to three referenced garments or accessories while preserving their identity and pose. Built for virtual try-on, fashion catalogs, styling, and e-commerce previews.

Bria Fibo

bria-fibo

Bria Fibo is a JSON-native, open-source text-to-image model with structured prompting, negative prompts, and deterministic seed control for consistent compositions.

Bria Fibo Edit

bria-fibo-edit

Bria Fibo Edit applies text-guided edits to an uploaded image, with optional mask targeting, negative prompts, and structured prompts.