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
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
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
Benchmarks
No benchmark data is available yet for this model.
Examples
Loading examples…
Related image models
Compare Proteus with similar models from the same provider or model family.
Muse Image
meta/muse-image/text-to-imageMeta 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.
Recraft V4 Style Pro
recraft-ai/recraft-v4-style-pro/text-to-imageRecraft V4 Style Pro creates premium raster images that consistently follow up to 10 style references or a reusable Recraft Pro style ID.
Recraft V4 Style Pro Vector
recraft-ai/recraft-v4-style-pro/text-to-vectorRecraft V4 Style Pro Vector generates premium vector graphics that consistently follow up to 10 style references or a reusable Recraft Pro style ID.
Recraft V4 Style
recraft-ai/recraft-v4-style/text-to-imageRecraft V4 Style creates consistent raster assets from a prompt plus up to 10 style references or a reusable Recraft style ID.
Recraft V4 Style Vector
recraft-ai/recraft-v4-style/text-to-vectorRecraft V4 Style Vector creates consistent vector assets from a prompt plus up to 10 style references or a reusable Recraft style ID.
Krea 2 Turbo
wavespeed-ai/krea-v2/turboKrea 2 Turbo is a fast 12.9B open-weights image model with native 1K and 2K generation plus optional image-to-image guidance.