Available now

HiDream O1 Image Dev: text to image

HiDream O1 Image Dev turns a written description into detailed images, one to four per run, at sizes up to about 2048x2048 pixels.

Model ID

Input

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

Text prompt for image generation, editing, or subject-driven personalization.

Example prompt. Edit it or write your own.

Requested output image size. Dimensions are rounded down to a multiple of 32, up to about 2048x2048 pixels.

Additional settings

Number of denoising steps. The dev model is distilled for 28 steps.

Classifier-free guidance scale. The dev model uses 0.0 by default.

Random seed for reproducible generation.

Price$0.01 / megapixel

You sign up first. Your settings are kept.

About this model

Overview

HiDream O1 Image Dev is the dev version of HiDream's O1 image model. It renders in square, portrait or landscape sizes, as JPEG, PNG or WebP, with 28 steps by default and guidance off, the setting it is tuned for.

What you can build

  • Detailed illustrations with many small elements
  • Large square artwork for covers and prints
  • Concept scenes for games and stories
  • Portrait and landscape images for web pages

Prompting tips

  • Keep the default steps and guidance; the dev model is set up for them.
  • List the small details you want to see, such as textures, materials and patterns.
  • Fix the seed while you adjust wording, so you can see what each change does.

What to check

Inspect edges, anatomy and texture rather than comparing appearance alone.

Inputs

  • Prompt (required): Text prompt for image generation, editing, or subject-driven personalization.
  • Image Size (optional): Requested output image size. Dimensions are rounded down to a multiple of 32, up to about 2048x2048 pixels. Options: 1024 × 1024, Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9.
  • Number of Inference Steps (optional): Number of denoising steps. The dev model is distilled for 28 steps.
  • Guidance Scale (optional): Classifier-free guidance scale. The dev model uses 0.0 by default. From 0 to 20.
  • Seed (optional): Random seed for reproducible generation.
  • Number of Images (optional): Number of images to generate. From 1 to 4.
  • Output Format (optional): The format of the generated image. Options: jpeg, png, webp.

Output and limits

  • Image sizes: 1024 × 1024, Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9.
  • File formats: JPEG, PNG, WEBP.
  • Up to 4 images per run.
  • Small or dense text in the image can come out misspelled.
  • Hands, crowds and complex poses can show artifacts; generate a few variations and pick the best.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • 1 megapixel: $0.01 / megapixel