Baidu modelsimage generation api

baidu/ernie-image/turbo

Name: Ernie Image
Author: Baidu

Ernie Image Turbo is Baidu's advanced text-to-image AI model. Create photorealistic images, illustrations, and concept art from natural language descriptions with exceptional detail and prompt adherence.

Input

Prompt(string)

Text prompt for image generation. Supports English, Chinese, and Japanese.

Aspect Ratio(string)

The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.

Guidance Scale(number)

120

Classifier-free guidance scale. Range: 1 to 20.

Num Inference Steps(integer)

120

Number of denoising steps. Turbo model is optimized for 8 steps. Range: 1 to 20.

Output Format(string)

Output image format. Allowed values: jpeg, png.

Seed(integer)

Random seed for reproducibility.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDbaidu/ernie-image/turbo

Input Schema

6 parameters · 1 required · 5 optional

Parameter	Type	Required	Description
`prompt`	string	Required	Text prompt for image generation. Supports English, Chinese, and Japanese.
`seed`	integer	Optional	Random seed for reproducibility.
`aspect_ratio`	string	Optional	The aspect ratio of the generated image. · Options: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 21:916:93:24:35:41:14:53:42:39:16
`output_format`	string	Optional	Output image format. · Options: jpeg, png · Default: "jpeg" jpegpng
`guidance_scale`	number	Optional	Classifier-free guidance scale. · Min: 1 · Max: 20 · Default: 1
`num_inference_steps`	integer	Optional	Number of denoising steps. Turbo model is optimized for 8 steps. · Min: 1 · Max: 20 · Default: 8

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "baidu/ernie-image/turbo",
  "prompt": "A serene mountain landscape at sunset with golden light",
  "output_format": "jpeg",
  "guidance_scale": 1,
  "num_inference_steps": 8
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to Ernie Image

API README

Ernie Image

Ernie Image is the faster ERNIE image-generation model, retaining Baidu’s prompt-led scene construction while reducing turnaround for repeated creative exploration. It is useful when teams need many coherent candidates and cannot reserve a slower render cycle for every layout, mood, or style decision.

Use concise, ordered prompts for rapid iteration: subject and action first, followed by composition, environment, lighting, palette, and finish. The Turbo model fits social content, thumbnails, early campaign studies, and high-volume variants; reserve slower finishing work for only the concepts that survive review.

Highlights

Accelerated prompt-to-image synthesis. Reduces generation time for interactive and high-volume creative workflows.
Coherent rapid composition. Maintains readable subject hierarchy and scene organization despite the speed focus.
Broad visual ideation. Produces photographic, illustrated, and concept-art directions for quick comparison.
Production-scale variation. Supports many prompt, layout, and style alternatives within a short review cycle.

Pricing

Billing unit	Price
Per request	$0.01

When to Use

✅ Good fit	❌ Consider alternatives
The model's named workflow matches the source material and intended output	A different input modality or model route is required
A managed asynchronous result is suitable for the production pipeline	A synchronous, interactive editor is essential
The documented controls cover the required duration, framing, or format	The project needs controls outside this endpoint's schema
Creative iteration benefits from a repeatable request structure	Exact deterministic pixels, frames, geometry, or samples are mandatory
A finished downloadable media asset is the desired deliverable	Editable source layers or a native project file are required

Prompt Guide

For generation, state the intended result first, then add the subject or source treatment, progression, style, and delivery constraints. Keep one creative variable per phrase, use the documented field names for controls, and change one setting at a time when comparing results.

{
  "aspect_ratio": "21:9",
  "output_format": "jpeg",
  "prompt": "A serene mountain landscape at sunset with golden light"
}

Technical Specs

Spec	Value
Model ID	`baidu/ernie-image/turbo`
Inputs	aspect_ratio, guidance_scale, num_inference_steps, output_format, prompt, seed
Required inputs	prompt
Output fields	content_type, url
Execution	Async (submit, then poll for result)
Aspect Ratio	21:9 / 16:9 / 3:2 / 4:3 / 5:4 / 1:1 / 4:5 / 3:4 / 2:3 / 9:16
Output Format	jpeg / png

Related Models

baidu/ernie-image — Compare this concrete local family route.
baidu/ernie-image-trainer — Compare this concrete local family route.