Hidream I1 Dev

HiDream-I1 is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds.

Features

HiDream-I1-Dev is a distilled version of the 17-billion-parameter HiDream-I1 text-to-image generation model developed by HiDream.ai. It offers high-quality image generation with reduced computational requirements, making it suitable for developers and researchers seeking efficient performance.

Key Features

• High-Quality Image Generation: Produces exceptional results across multiple styles, including photorealistic, cartoon, and artistic.
• Efficient Performance: Distilled model offers faster inference with lower computational overhead.
• Open Source: Released under the MIT license, encouraging scientific advancement and creative innovation.
• Commercial-Friendly: Generated images can be freely used for personal projects, scientific research, and commercial applications.

ComfyUI

hidream-i1-dev is also available on ComfyUI, providing local inference capabilities through a node-based workflow, ensuring flexible and efficient image generation on your system.

Limitations

• Reduced Model Size: As a distilled version, it may not capture all the nuances of the full model.
• Prompt Sensitivity: The quality of generated images can vary based on the specificity and clarity of input prompts.
• Potential Biases: Outputs may reflect biases present in the training data.
• Content Responsibility: Users are responsible for ensuring that generated content complies with legal and ethical standards.

Out-of-Scope Use

The model and its derivatives may not be used in any way that violates applicable national, federal, state, local, or international law or regulation, including but not limited to:

• Exploiting, harming, or attempting to exploit or harm minors, including solicitation, creation, acquisition, or dissemination of child exploitative content.
• Generating or disseminating verifiably false information with the intent to harm others.
• Creating or distributing personal identifiable information that could be used to harm an individual.
• Harassing, abusing, threatening, stalking, or bullying individuals or groups.
• Producing non-consensual nudity or illegal pornographic content.
• Making fully automated decisions that adversely affect an individual’s legal rights or create binding obligations.
• Facilitating large-scale disinformation campaigns.

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/v2/wavespeed-ai/hidream-i1-dev" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "prompt": "A Ghibli-inspired scene featuring a giant, friendly creature walking through a lush forest and holding a sign saying \"HiDream on wavespeed.ai\", with vibrant colors, soft lighting, and whimsical details like floating lights and colorful, magical creatures. The scene captures a peaceful, enchanted atmosphere",
    "size": "1024*1024",
    "seed": -1,
    "enable_base64_output": true,
    "enable_safety_checker": true
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v2/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