Private AI
Baidu's ERNIE Image model for high-quality multilingual text-to-image generation with built-in prompt expansion.
Added Apr 10, 2026
Approx. Price
$0.009 per image
Model Type
text-to-image
Generation controls available for this model.
Images Per Run
Up to 4
Output images
Input Images
N/A
No reference/edit image input
Output Sizes
Enable Safety Checker
Default
No
Guidance Scale
Default
5
How strongly to follow the prompt (1-20).
Inference Steps
Default
50
Number of denoising steps (1-100).
Negative Prompt
Default
N/A
Describe what to avoid in the image.
Number of Images
Default
1
Output Format
Human preference benchmarks sourced from Artificial Analysis.
Text to Image
#32 / 147
ELO
1166.0
Appearances
4,813
95% CI
-8/8
Release Date 2026-04 · Matched as ERNIE Image
Artificial Analysis APILoading examples…
Default
jpeg
Options (2)
JPEG, PNG
Image output format.
Prompt Expansion
Default
Yes
Enhance the prompt automatically for richer outputs.
Resolution
Default
1024x1024
Options (11)
512x512 (Square), 1024x1024 (Square HD), 768x1024 (Portrait (3:4)), 576x1024 (Portrait (9:16)) +7 more
Seed
Default
N/A
Random seed for reproducible outputs.