Nano GPT logo
NanoGPT

Proteus

proteus
BackTry Model

Proteus

proteus
BackTry Model

Proteus model - high-quality image generation with excellent detail and artistic capabilities.

Approx. Price

$0.003 per image

Model Type

text-to-image

Settings

Generation controls available for this model.

Images Per Run

Up to 20

Output images

Input Images

N/A

No reference/edit image input

Output Sizes

Square
Portrait
Landscape
up to 2,048px

CFG Scale

Default

7.5

Controls how closely the output image aligns with the prompt.

Number of Images

Default

1

Resolution

Default

1024x1024

Options (9)

1024x1024 (Square (1:1)), 1920x1088 (Landscape HD (~16:9)), 1088x1920 (Portrait HD (~9:16)), 768x1024 (Portrait (3:4)) +5 more

Seed

Number

Default

N/A

Random seed to control image generation. Leave empty for random.

Steps

Default

20

Number of inference steps. More steps generally produce better quality.

Benchmarks

No benchmark data is available yet for this model.

Examples

Loading examples…

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

MiniMax H3 Image Edit

wavespeed-ai/minimax-h3/image-edit

Edit images from up to nine references, preserving identity while changing scenes, outfits, or styles. Supports 1K and 2K output.

MiniMax H3 Image

wavespeed-ai/minimax-h3/text-to-image

Generate photorealistic and cinematic images from text at 1K or 2K resolution, with fifteen aspect ratios.

MAI-Image-2.6

microsoft/mai-image-2.6

Microsoft’s image model for detailed photography, product imagery, accurate lettering, and precise edits to an uploaded image.

MAI-Image-2.6 Flash

microsoft/mai-image-2.6-flash

A faster, lower-cost MAI image model for product visuals, creative drafts, and edits to an uploaded image.

Bria FIBO Generate 1.5

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

Bria FIBO Generate 1.5 creates commercially safe images from text prompts, with optional reference-image guidance, photoreal styling, structured prompts, and up to 4MP output.

Muse Image

meta/muse-image/text-to-image

Meta Muse Image generates high-fidelity images with strong instruction following, detailed typography, plots, and QR codes. Upload up to 10 reference images to switch automatically to edit mode.