Image
Ernie Image
Generate images from text with Baidu’s Ernie Image and optional prompt expansion.
- Text to image
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Ernie Image. Review your own result before publishing.
A starting point.
Draft scenes in English, Chinese or Japanese, with a negative prompt for unwanted details.
Before you publish.
Check whether expansion changed the intended subject, and review any generated lettering.
Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.
Settings and model questionsCheck the available settings and guidance when preparing your input.
Inputs and settings
Start with one image. Adjust num_inference_steps within 1–100 and guidance_scale within 1–20 only after reviewing composition.
Toggle enable_prompt_expansion to compare interpretation. Keep seed for comparisons and choose JPEG or PNG output.
Inputs, all modes and APIModel IDs, current input limits and the API generation workflow.
Supported inputs
These fields come from the current studio form for ernie-image. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | — |
acceleration | Text | Optional | — |
enable_prompt_expansion | On/off | Optional | — |
enable_safety_checker | On/off | Optional | — |
guidance_scale | Number | Optional | ≥ 1 · ≤ 20 |
negative_prompt | Text | Optional | — |
num_images | Whole number | Optional | ≥ 1 · ≤ 4 |
num_inference_steps | Whole number | Optional | ≥ 1 · ≤ 100 |
output_format | Text | Optional | jpeg, png |
seed | Whole number | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Ernie Image through the API.
Start with this model ID for the endpoint featured on this page:
ernie-image
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
Check the current model schema for supported inputs and options. Other tasks may use different model IDs.
From quote to result.
Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.
Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.