Hidream E1 Full

HiDream-E1 is an image editing model built on HiDream-I1.

Features

HiDream-E1-Full is a state-of-the-art image-to-image editing model, developed on top of HiDream-I1. Designed for high-fidelity visual transformation, it enables nuanced and prompt-controlled edits while preserving the key structure and style of the original image.

Key Features

• Text-Guided Image Editing: Edit images by providing natural language prompts, enabling seamless content, style, or object-level changes.
• High Visual Fidelity: Maintains original image structure, identity, and lighting while reflecting prompt-driven changes.
• Detail-Preserving Architecture: Built on the HiDream-I1 backbone, E1 enhances control and consistency with minimal content distortion.
• Open Source, API-Ready: Available for real-time experimentation and scalable deployment via the WaveSpeedAI platform.

ComfyUI

HiDream-E1-Full is also available on ComfyUI, providing local inference capabilities through a node-based workflow, ensuring flexible and efficient image generation on your system.

Use Cases

• Product/Character Variants: Instantly generate new designs or looks for a character or product by modifying accessories, colors, or styles using simple prompts.
• Concept Art & Creative Iteration: Explore multiple creative directions without redrawing the base image. Great for artists, storyboarders, and content creators.
• Precise Marketing Asset Revision: Change backgrounds, lighting, or brand elements in promotional visuals while keeping layout and subject intact.
• Photorealistic Object Modification: Add or remove items (e.g., hats, glasses, logos) in real-world scenes with photorealistic quality.
• Style Transfer with Control: Apply stylization (e.g., anime, oil painting, cyberpunk) to input photos while retaining core composition.

Accelerated Inference

Our accelerated inference approach leverages advanced optimization technology from WavespeedAI. This innovative fusion technique significantly reduces computational overhead and latency, enabling rapid image generation without compromising quality. The entire system is designed to efficiently handle large-scale inference tasks while ensuring that real-time applications achieve an optimal balance between speed and accuracy. For further details, please refer to the blog post.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/hidream-e1-full" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "prompt": "for a light gray sweater and gold thin-rimmed glasses.",
    "image": "https://d2g64w682n9w0w.cloudfront.net/media/dd703f8dc97646268d372cdd689fdccc/images/1747376730398194676_K2jByuqm.jpeg",
    "seed": -1,
    "enable_base64_output": false,
    "enable_safety_checker": true
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Query Parameters

Result Request Parameters

Result Response Parameters