Ernie Image Turbo

High-quality text-to-image model by Baidu. Supports English, Chinese, and Japanese prompts with built-in prompt expansion.

Input

Fields marked * are required. Review the price before generating.

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

The size of the generated image.

Number of images to generate.

Additional settings

Negative prompt to guide what should not be in the image.

Number of denoising steps. Turbo model is optimized for 8 steps.

Classifier-free guidance scale.

Random seed for reproducibility.

If True, the prompt will be enhanced using an LLM for more detailed results.

Output image format.

The acceleration level to use for the image generation.

Price$0.02 / megapixel

You sign up first. Your settings are kept.

API code for this input

Complete the required fields and fix input errors to see API code.

How to use Ernie Image Turbo

Getting started

Compare scene ideas or style directions before committing to a detailed composition.

Review your result

Inspect texture, facial features and whether important prompt details survived the shorter sampling.

Inputs and settings

The official Turbo starting point is eight inference steps. Raywake allows 1–20; begin with one image.

Compare enable_prompt_expansion on and off. Use negative_prompt for exclusions and preserve seed when adjusting guidance_scale.