AllImageAI

HiDream O1 Image Generator and Editor

One native model for generation, natural-language editing and subject-driven reference composition.

Developed by HiDream.aiActiveVerified August 25, 2026

Model Version

Mode

Reference Images0/3

Preview mode: placeholder output, no credits charged

Output

HiDream O1 Image

One native model for generation, natural-language editing and subject-driven reference composition.

SlowUp to 2KRefs ×31:116:99:164:3

Try one of these prompts

Developer
HiDream.ai
Model
HiDream O1 Image
Status
Active
Max Output
2K
Input
Text + Images
Released
May 9, 2026
Last Verified
August 25, 2026

What Is HiDream O1 Image?

HiDream O1 Image is a unified image model: the same operation can start from text, revise one image or combine several subject references. It supports custom dimensions up to roughly 2K without switching to a separate editing model.

HiDream Model Versions

HiDream O1 Image

Multi-reference · 2K

From 1 Credits

HiDream I1 Full

Full quality · 2K

From 3 Credits

Open this version →

HiDream O1 Image

One native model for generation, natural-language editing and subject-driven reference composition.

  • Resolutions: 1K / 2K
  • Reference images: up to 3
  • Modes: Text to Image, Image to Image, Edit Image, Multi-reference
  • Speed: Slow

HiDream I1 Full

A large open image foundation model with classic diffusion controls and broad style range.

  • Resolutions: 1K / 2K
  • Reference images: not supported
  • Modes: Text to Image
  • Speed: Slow

What Is HiDream O1 Image Best For?

  • Natural-language image editing
  • Subject-driven generation
  • Multi-reference compositions
  • High-resolution product concepts

How to Use HiDream O1 Image

  1. Generate from text or upload references.
  2. Identify each reference by number.
  3. State what must remain unchanged.
  4. Use 2K only for the selected result.

HiDream O1 Image Settings Explained

Reference Images

Use one for editing or up to three for subject-driven composition.

Guidance

The documented full-model default is 5; raise it cautiously for strict instructions.

The panel above shows only the parameters HiDream O1 Image actually supports. Switch versions and unsupported controls disappear rather than sitting there doing nothing.

HiDream O1 Image Prompt Examples

Subject composition

Place the person from image 1 in the studio from image 2, holding the product from image 3; preserve identity and label details

Local edit

Keep the room and camera angle unchanged; replace only the chair with a low walnut lounge chair

HiDream O1 Image Test Results

Testing in progress

Every model runs the same eight-category prompt set — portrait, product, poster text, anime character, interior, multi-reference, image editing and character consistency — recording generation time, success rate, text accuracy and identity retention. That run has not finished for HiDream O1 Image, so this page shows no scores. We do not publish numbers we have not measured.

HiDream O1 Image Limitations

  • The interface caps references at three for predictable prompts
  • The full 50-step model is slower than its distilled variants
  • Dense copy still needs proofreading

HiDream O1 Image Pricing and Credits

Credits scale with resolution and image count. The Generate button always shows what this run costs.

1K

1 credits / image

2K

2 credits / image

Failed generations cost 0 credits.

Commercial Use and Image Rights

Commercial use is subject to the HiDream O1 model licence and the selected service terms.

  • Model used: HiDream O1 Image
  • Model developer: HiDream.ai
  • The inference route is managed internally and may change without changing the selected model
  • Uploads are sent only to the configured inference service needed to complete the generation
  • You can delete any generation from your history at any time

Frequently Asked Questions

Does editing call a different model?+

No. This integration uses the unified HiDream O1 Image operation and passes references directly.

Why only three references?+

The upstream schema allows multiple images without publishing a numeric limit, so the interface uses a conservative cap.

Model Updates and Changelog

  • 2026-08-25 —— Added unified generation and conservative three-reference editing support.