What Is HiDream I1 Full?
HiDream I1 Full is the 17-billion-parameter quality tier of the open HiDream family. It provides a broad visual range plus negative prompt, sampling-step, guidance and seed controls for reproducible experiments.
HiDream Model Versions
HiDream I1 Full
Full quality · 2K
From 4 Credits
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
HiDream I1 Fast
The 16-step HiDream I1 checkpoint for fast open-model concepts without losing the family’s visual range.
- Resolutions: 1K / 2K
- Reference images: not supported
- Modes: Text to Image
- Speed: Fast
What Is HiDream I1 Full Best For?
- Open-model evaluation
- Detailed illustration
- Broad style exploration
- Reproducible parameter studies
How to Use HiDream I1 Full
- Start at 1K and 50 steps.
- Use a concrete negative prompt.
- Fix a seed before comparing guidance.
- Move the chosen composition to 2K.
HiDream I1 Full Settings Explained
Steps
Fifty is the full-model default; reduce it for drafts before increasing resolution.
Guidance
Five is the documented starting point for prompt adherence.
The panel above shows only the parameters HiDream I1 Full actually supports. Switch versions and unsupported controls disappear rather than sitting there doing nothing.
HiDream I1 Full Prompt Examples
Fantasy environment
Terraced city carved into red canyon walls, wind bridges, early morning haze, intricate architectural illustration
Photographic scene
Small independent bookstore at dusk, rain on the pavement, warm window light, documentary photograph, 35mm lens
HiDream I1 Full 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 I1 Full, so this page shows no scores. We do not publish numbers we have not measured.
HiDream I1 Full Limitations
- Slower than distilled models
- Text-to-image only on this page
- 2K output costs four times the pixels of 1K
HiDream I1 Full Pricing and Credits
Credits scale with resolution and image count. The Generate button always shows what this run costs.
1K
4 credits / image
2K
15 credits / image
Failed generations cost 0 credits.
Commercial Use and Image Rights
HiDream I1 is released under the MIT License; hosted inference also follows the selected service terms.
- Model used: HiDream I1 Full
- 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
Is HiDream I1 open source?+
The model is released under the MIT License; this page uses hosted inference.
Why use the Full variant?+
It prioritises quality and control. The smaller variants are faster but are not silently substituted here.
Release History and Sources
April 7, 2025 · Open weights released
This date applies to the event shown. Later API access, weights and availability on All Image AI may have different dates.
Explore this event on the image model timeline →
Related Models and Tools
AI Image Generator
Create an image, try a new look or transform a photo. Start with the result you want.
Poster Generator
Posters with headlines that come out right the first time.
Stable Diffusion 3.5 Large
Stability AI
The full 8B SD 3.5 model with negative prompts, CFG and sampling-step control.
Stable Diffusion 3.5 Large Turbo
Stability AI
The four-step distilled SD 3.5 Large for fast, controllable open-model drafts.
Stable Diffusion 3.5 Medium
Stability AI
The resource-efficient SD3.5 tier with classic CFG, steps and negative-prompt controls.
Stable Diffusion 3 Medium
Stability AI
Stability AI’s two-billion-parameter SD3 checkpoint with typography, negative prompts and familiar diffusion controls.