Advanced 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.
Approx. Price
$0.060 per image
Model Type
image-to-image
Settings
Generation controls available for this model.
Images Per Run
Up to 4
Output images
Input Images
Supported
Reference/edit images accepted • Route max 30 MB
Output Sizes
Enable Safety Checker
Default
No
Guidance Scale
Default
3.5
How closely to follow the prompt (0-20)
Image Guidance Scale
Default
2
How closely to stick to the original image (0-20)
Inference Steps
Default
50
Number of inference steps (1-50)
Negative Prompt
Default
low resolution, blur
Describe what you don't want in the image
Number of Images
Default
1
Resolution
Options (1)
auto (Original size)
Supported output resolutions.
Target Image Description
Default
N/A
Optional: Describe the desired result. Leave blank for the model to use its imagination.
Benchmarks
Benchmarks
Human preference benchmarks sourced from Artificial Analysis.
Image Editing
#73 / 79
ELO
808.0
Appearances
3,441
95% CI
-11/11
Release Date 2025-07 · Matched as HiDream-E1.1
Artificial Analysis APIExamples
Loading examples…
Related image models
Compare HiDream Edit 1.1 with similar models from the same provider or model family.
HiDream O1 Image
hidream-o1-imageHiDream-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.
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-I1 Fast
hidream-i1-fastFast image generation model. Optimized for speed while maintaining good quality.
Qwen Image 2.1 Edit
wavespeed-ai/qwen-image-2.1/editEdit from up to ten reference images with natural-language instructions, strong subject preservation, flexible framing, and native output up to 2K.
Qwen Image 2.1 Edit LoRA
wavespeed-ai/qwen-image-2.1/edit-loraEdit from up to ten references while applying up to three custom LoRAs for precise identity, product, or style control at up to 2K.