HiDream-O1-Image is a unified native image model for detailed text-to-image output and prompt-based edits with uploaded references, high-resolution 2K+ presets, strong prompt adherence, and flexible aspect ratios.
Added May 11, 2026
Approx. Price
$0.040 per image
Model Type
both
Settings
Generation controls available for this model.
Images Per Run
Up to 4
Output images
Input Images
Up to 3
Reference/edit images accepted • Route max 30 MB
Output Sizes
Number of Images
Default
1
Output Format
Default
jpeg
Options (3)
JPEG, PNG, WebP
Output image format.
Resolution
Default
2048*2048
Options (7)
2048*2048 (Square 2K (1:1)), 2560*1440 (Landscape 2K (16:9)), 1440*2560 (Portrait 2K (9:16)), 2304*1728 (Landscape 2K (4:3)) +3 more
Seed
Default
-1
Control reproducibility (-1 for random).
Benchmarks
Benchmarks
Human preference benchmarks sourced from Artificial Analysis.
Text to Image
#59 / 159
ELO
979.0
Appearances
11,258
95% CI
-8/8
Image Editing
#55 / 76
ELO
951.0
Appearances
4,005
95% CI
-10/10
Release Date 2026-05 · Matched as HiDream-O1-Image
Artificial Analysis APIExamples
Loading examples…
Related image models
Compare HiDream O1 Image with similar models from the same provider or model family.
HiDream O1 Image Dev
hidream-o1-image-devHiDream-O1-Image Dev is the distilled faster variant of HiDream O1 Image, tuned for lower-cost high-resolution 2K+ text-to-image generation, prompt-based edits with uploaded references, and rapid iteration.
Hidream
hidreamHidream I1 Full, the latest and greatest image generation model from Hidream.
HiDream Edit 1.1
hidream-e1-1Advanced image-to-image editing model. Transform images based on editing instructions while preserving key elements of the original image. Supports style transfer, object modification, and scene changes.
HiDream-I1 Fast
hidream-i1-fastFast image generation model. Optimized for speed while maintaining good quality.
Anima
wavespeed-ai/anima/text-to-imageA fast 2B anime image model for tag-driven illustrations, native 1K or 1.5K output, and prompt-guided variations from one uploaded image.
Anima LoRA
wavespeed-ai/anima/text-to-image-loraAnima with faithful support for up to three custom character or style LoRAs, plus native 1K or 1.5K generation and prompt-guided variations from one image.