Ernie Image Text To Image

Playground

Baidu ERNIE Image generates high-quality images from text prompts in English, Chinese, and Japanese, with flexible sizing and LLM-enhanced prompt expansion. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

ERNIE Image Text-to-Image

ERNIE Image Text-to-Image is Baidu’s text-to-image model, generating high-quality images from natural language prompts. It supports prompts in English, Chinese, and Japanese — making it a strong choice for multilingual creative and production workflows.

Why Choose This?

Multilingual prompt support Write prompts in English, Chinese, or Japanese — the model understands all three natively for accurate, culturally relevant image generation.
Fast generation Generates images quickly — ideal for rapid iteration, high-volume workflows, and real-time applications.
Custom size output Specify any output dimensions to match your target format — social media, banners, portraits, or custom layouts.

Parameters

Parameter	Required	Description
prompt	Yes	Text description of the image. Supports English, Chinese, and Japanese.
size	No	Output dimensions in width×height pixels. Default: 1024×1024. Range: 256–1536 per side.

How to Use

Write your prompt — describe the subject, scene, style, and mood in English, Chinese, or Japanese.
Set size (optional) — specify output dimensions to match your target format.
Submit — generate and download your image.

Pricing

Just $0.03 per image.

Best Use Cases

Multilingual content creation — Generate images from Chinese, Japanese, or English prompts for localized creative workflows.
Rapid prototyping — Quickly iterate on visual concepts with fast turbo-speed generation.
Social media & marketing — Produce on-brand visuals at custom sizes for any platform or format.
E-commerce — Generate product lifestyle and scene imagery at scale.
Developer integrations — Embed fast, multilingual image generation into apps and pipelines.

Pro Tips

Be specific in your prompt — include subject, style, lighting, and composition details for the most accurate results.
Chinese and Japanese prompts can be especially effective for culturally specific aesthetics and artistic styles.
Use custom size to match your exact delivery format rather than cropping after generation.

Notes

Only prompt is required; size is optional and defaults to 1024×1024.
Supported size range: 256–1536 pixels per dimension.
Please ensure your content complies with Baidu’s usage policies.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/ernie-image/text-to-image" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "size": "1024*1024"
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

Parameter	Type	Required	Default	Range	Description
prompt	string	Yes		-	Text prompt describing the image. Supports English, Chinese, and Japanese.
size	string	No	1024*1024	256 ~ 1536 per dimension	The size of the generated image in pixels (width*height).

Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data.id	string	Unique identifier for the prediction, Task Id
data.model	string	Model ID used for the prediction
data.outputs	array	Array of URLs to the generated content (empty when status is not `completed`)
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.has_nsfw_contents	array	Array of boolean values indicating NSFW detection for each output
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Result Request Parameters

Parameter	Type	Required	Default	Description
id	string	Yes	-	Task ID

Result Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data	object	The prediction data object containing all details
data.id	string	Unique identifier for the prediction, the ID of the prediction to get
data.model	string	Model ID used for the prediction
data.outputs	string	Array of URLs to the generated content (empty when status is not completed).
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Emu 3.5 Image Text To Image Internal Ernie Image Text To Image Turbo