An excellent image model with state of the art inpainting, prompt comprehension and especially text rendering.
Approx. Price
$0.136 per image
Model Type
image
Preview Examples
4
Generation controls available for this model.
Images Per Run
Up to 1
Resolution Options
7
1024x1024 (Square (1:1)), 768x1024 (Portrait (3:4)), 1024x768 (Landscape (4:3)) +4 more
Tunable Settings
5
Magic Prompt
Default
On
Options (2)
On, Off
Optimizes your prompt to maximize variety and quality. Supports multiple languages.
Negative Prompt
Default
N/A
Details you don't want in the image (e.g. blurry, low quality, etc)
Resolution
Default
1024x1024
Options (7)
1024x1024 (Square (1:1)), 768x1024 (Portrait (3:4)), 1024x768 (Landscape (4:3)), 640x1344 (Portrait (5:11)) +3 more
Steps
Default
25
Style
Default
Auto
Options (6)
Auto, General, Realistic, Design +2 more
Define the specific aesthetic of the image you want to generate
Human preference benchmarks sourced from Artificial Analysis.
Text to Image
#74 / 129
ELO
1067.0
Appearances
8,728
95% CI
-8/8
Release Date 2024-08 · Matched as Ideogram v2
Artificial Analysis API
Girl with freckles and curly red hair lying in a field of wildflowers, soft natural light, macro-level skin details, gentle breeze captured in motion
Korean girl in a hanbok standing under cherry blossoms, soft pastel tones, shallow depth of field, cinematic film look, photorealistic
Japanese high school boy leaning on a balcony, sunset in the background, uniform details, warm atmosphere, delicate lighting, hyperreal face textures
Woman in a red dress walking through foggy street at night, streetlamp glow behind her, mysterious atmosphere, soft focus background, high fidelity textures
