Nano Banana 2 & Pro Sale — 15% OFF | Apr 1–15 Only
Sign In
Home/Explore/wavespeed-ai/ernie-image/text-to-image-turbo

ERNIE Image Turbo

wavespeed-ai /

Baidu ERNIE Image Turbo is a distilled, 8-step version of ERNIE Image for fast, low-cost generation. Supports English, Chinese, and Japanese prompts with flexible sizing. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

text-to-image
Input
width
height
864 × 1152 px
Range: 256 - 1536

Idle

A weathered desert nomad hunter crouching on a sand dune at golden hour, face wrapped in deep crimson cloth revealing only sharp dark eyes, a compound bow slung over one shoulder, fingers tracing ancient markings in the sand, enormous shadow stretching behind him, heat haze distorting the horizon, National Geographic photography style, raw and visceral

Your request will cost $0.03 per run.

For $1 you can run this model approximately 33 times.

One more thing:

ExamplesView all

A weathered desert nomad hunter crouching on a sand dune at golden hour, face wrapped in deep crimson cloth revealing only sharp dark eyes, a compound bow slung over one shoulder, fingers tracing ancient markings in the sand, enormous shadow stretching behind him, heat haze distorting the horizon, National Geographic photography style, raw and visceral
A celestial messenger descending from a crescent moon, gender-ambiguous figure draped in flowing white robes that dissolve into moonlight at the edges, long silver hair floating weightlessly, bare feet hovering above a sleeping city, holding a luminous orb containing a tiny storm, calm expression with closed eyes, painterly style blending Alphonse Mucha Art Nouveau with contemporary digital art
A lone assassin pausing mid-rooftop sprint, rain hammering down, body frozen as a distant neon sign flickers revealing their own wanted poster — they stare at their own face, fractured memory, gloved hand pressed against wet glass, black tactical outfit, expression unreadable, cinematic noir, anamorphic lens, shallow depth of field

README

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

ParameterRequiredDescription
promptYesText description of the image. Supports English, Chinese, and Japanese.
sizeNoOutput dimensions in width×height pixels. Default: 1024×1024. Range: 256–1536 per side.

How to Use

  1. Write your prompt — describe the subject, scene, style, and mood in English, Chinese, or Japanese.
  2. Set size (optional) — specify output dimensions to match your target format.
  3. 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.

Related Models