Baidu ERNIE Image Turbo Text-to-image

Use Baidu ERNIE Image Turbo Text-to-image for image; see supported inputs and option-based pricing on this page.

modellane/baidu-ernie-image-turbo-text-to-image-09586bc0 · Text to image · Baidu

Baidu ERNIE Image Turbo Text-to-image supports text to image. Its documented input fields are listed below; the request price is calculated from the selected options.

Vendor
Baidu
Task
Text to image
Output
Image
Price
$0 · per run

Input parameters

  • Prompt prompt — required Describe what you want produced as concretely as you can.
  • Size size — optional, options: 1024x1024, 1376x768, 1264x848, 1200x896, 896x1200, 848x1264, 768x1376
  • Number of images n — optional, default: 1, range: 1–10
  • Seed seed — optional, default: -1 The same seed and the same settings produce a similar result; leave it empty and one is picked at random.
  • Prompt enhancement use_pe — optional, default: true
  • Steps num_inference_steps — optional, default: 8, range: 1–100 More steps usually give a cleaner result and take longer.
  • Prompt adherence guidance_scale — optional, default: 1, range: 1–20 A high value stays close to the prompt, a low value leaves the model more room.

Recommended use cases

    Where it is strong

      Limits

        Example prompt

        A red bicycle against a stone wall at sunset, in natural light.

        Example request

        POST /v1/queue/modellane/baidu-ernie-image-turbo-text-to-image-09586bc0

        Playground

        The identifier, price, parameters, and example requests on this page can be read without signing in. Running the model from the panel sends a real generation request and charges the project balance; the playground therefore requires an account.