HiDream AI

llms.txt

HiDream E1

Name: HiDream E1
Brand: HiDream AI
Price: 0.06 USD
Availability: InStock

AI Image Editing Model

Image

HiDream AI's image-to-image editing model for instruction-based image modifications and transformations

Example outputs coming soon

Try Model

Supported Modes

Image Edit

Active

Details

Model ID

hidream-e1-1

Creator

HiDream AI

Family

hidream

Ready to integrate?

Access hidream-e1-1 via our unified API.

Create Account

Available at 1 provider

Starting from

$0.060 /image via fal.ai

Prices shown are in USD

Full pricing details

Providers & Pricing (1)

HiDream E1 is available exclusively through fal.ai, starting at $0.06/image.

fal.ai

fal/hidream-e1-1

Provider Model ID: fal-ai/hidream-e1-1

$0.060 /image

View pricing details

HiDream E1 API OpenAI-compatible

Developers can integrate HiDream E1 via the Lumenfall OpenAI-compatible API to perform instruction-based image modifications and text-to-image generation.

Base URL

https://api.lumenfall.ai/openai/v1

Model

hidream-e1-1

Code Examples

Image Edit

/v1/images/edits

curl -X POST \

  https://api.lumenfall.ai/openai/v1/images/edits \

  -H "Authorization: Bearer $LUMENFALL_API_KEY" \

  -F "model=hidream-e1-1" \

  -F "[email protected]" \

  -F "prompt=Add a starry night sky to this image" \

  -F "size=1024x1024"

# Response:

# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

import OpenAI from 'openai';

import fs from 'fs';

const client = new OpenAI({

  apiKey: 'YOUR_API_KEY',

  baseURL: 'https://api.lumenfall.ai/openai/v1'

});

const response = await client.images.edit({

  model: 'hidream-e1-1',

  image: fs.createReadStream('source.png'),

  prompt: 'Add a starry night sky to this image',

  size: '1024x1024'

});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }

console.log(response.data[0].url);

from openai import OpenAI

client = OpenAI(

    api_key="YOUR_API_KEY",

    base_url="https://api.lumenfall.ai/openai/v1"

response = client.images.edit(

    model="hidream-e1-1",

    image=open("source.png", "rb"),

    prompt="Add a starry night sky to this image",

    size="1024x1024"

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }

print(response.data[0].url)

Parameter Reference

Required Supported Not available

Core Parameters

Parameter	Type	Description	Modes
`prompt`	string	Required. Edit instruction for the image	Edit
`negative_prompt`	string	Negative prompt to guide generation away from undesired content	Edit
`seed`	integer	Random seed for reproducibility	Edit

Size & Layout

Parameter	Type	Description	Modes
`size`	string	Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9") WxH determines both shape and scale (aspect_ratio and resolution are ignored when size is provided). W:H format is equivalent to aspect_ratio.	Edit
`aspect_ratio`	string	Aspect ratio of the output image (e.g. "16:9", "1:1") Controls shape independently of scale. Use with resolution to control both. If size is also provided, size takes precedence. Any ratio is accepted and mapped to the nearest supported value.	Edit
`resolution`	string	Output resolution tier (e.g. "1K", "4K") Controls scale independently of shape. Higher tiers produce larger images and cost more. If size is also provided, size takes precedence for scale. Any tier is accepted and mapped to the nearest supported value.	Edit

size

Exact pixel dimensions

"1920x1080"

aspect_ratio

Shape only, default scale

"16:9"

resolution

Scale tier, preserves shape

"1K"

Priority when combined

size › aspect_ratio + resolution › aspect_ratio › resolution

size is most specific and always wins. aspect_ratio and resolution control shape and scale independently.

How matching works

Shape matching – we pick the closest supported ratio. Ask for 7:1 on a model with 4:1 and 8:1, you get 8:1.

Scale matching – providers use different tier formats: K tiers (0.5K 1K 2K 4K) or megapixel tiers (0.25 1). If the exact tier isn't available, you get the nearest one.

Dimension clamping – if a model has pixel limits, we clamp dimensions to fit and keep the aspect ratio intact.

Media Inputs

Parameter	Type	Description	Modes
`image`	file	Required. Input image(s) to edit Supports PNG, JPEG, WebP.	Edit

Output & Format

Parameter	Type	Description	Modes
`response_format`	string	How to return the image `url` `b64_json` Default: `"url"`	Edit
`output_format`	string	Output image format `png` `jpeg` `gif` `webp` `avif` Gateway converts to requested format if provider doesn't support it natively.	Edit
`output_compression`	integer	Compression level for lossy formats (JPEG, WebP, AVIF)	Edit
`n`	integer	Number of images to generate Default: `1` Gateway generates multiple images in parallel even if provider only supports 1.	Edit

Additional Parameters

Parameter	Type	Description	Modes
`cfg_scale`	number	Classifier-free guidance scale — higher values stick more closely to the prompt	Edit
`enable_safety_checker` fal	boolean	If set to true, the safety checker will be enabled.	Edit
`image_guidance_scale` fal	number	The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your initial image when looking for a related image to show you.	Edit
`num_inference_steps` fal	integer	The number of inference steps to perform.	Edit
`sync_mode` fal	boolean	If `True`, the media will be returned as a data URI and the output data won't be available in the request history.	Edit
`target_image_description` fal	string	The description of the target image after your edits have been made. Leave this blank to allow the model to use its own imagination.	Edit

Parameter Normalization

How we handle parameters across different providers

Not every provider speaks the same language. When you send a parameter, we handle it in one of four ways depending on what the model supports:

Behavior	What happens	Example
`passthrough`	Sent as-is to the provider	style, quality
`renamed`	Same value, mapped to the field name the provider expects	prompt
`converted`	Transformed to the provider's native format	size
`emulated`	Works even if the provider has no concept of it	n, response_format

Parameters we don't recognize pass straight through to the upstream API, so provider-specific options still work.

Full API Reference Authentication, endpoints, and more

Gallery

View all 1 images

HiDream E1 FAQ

How much does HiDream E1 cost?

HiDream E1 starts at $0.06 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

How do I use HiDream E1 via API?

You can use HiDream E1 through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "hidream-e1-1". Code examples are available in Python, JavaScript, and cURL.

Which providers offer HiDream E1?

HiDream E1 is available through fal.ai on Lumenfall. Lumenfall automatically routes requests to the best available provider.

Overview

HiDream E1 is an instruction-based image-to-image editing model developed by HiDream AI. It is designed to perform precise modifications and transformations on existing images based on natural language prompts. Unlike standard text-to-image models that generate visuals from scratch, E1 specializes in altering specific elements of a source image while maintaining the original context and structure.

Strengths

Instructional Precision: Excels at following specific, action-oriented directives (e.g., “change the color of the shirt” or “add a sunset to the background”) without redrawing the entire scene.
Context Retention: Demonstrates high fidelity in preserving the identity and spatial arrangement of unchanged elements within the source image.
Stylistic Flexibility: Capable of executing both photorealistic edits and more dramatic artistic transformations, such as converting a photograph into a specific painting style.
Efficient Processing: Optimized for rapid iterations, making it suitable for workflows that require multiple sequential edits to reach a final result.

Limitations

Complex Spatial Reconfiguration: May struggle with edits that require moving objects to entirely new positions or changing camera angles significantly while maintaining consistency.
Granular Detail Control: While effective for broad modifications, it may occasionally overlook very fine-grained textural details or subtle lighting nuances during complex background swaps.
Textual Rendering: Like many image-based models, its ability to edit or generate coherent text within an image remains a secondary capability compared to its visual manipulation strengths.

Technical Background

HiDream E1 is built on a diffusion-based architecture specifically tuned for image-to-image tasks. It utilizes a conditioning mechanism that balances the visual information from the input image with the semantic requirements of the text prompt. This approach allows the model to treat the original image as a structural guide rather than a mere suggestion, ensuring that edits feel integrated rather than overlaid.

Best For

HiDream E1 is ideal for professional design workflows, social media content creation, and e-commerce product visualization where users need to iterate on existing assets. It is particularly effective for background replacement, wardrobe adjustments, and applying global style transfers to specific photographs.

HiDream E1 is available through Lumenfall’s unified API and playground, allowing developers to integrate these advanced editing capabilities into their applications with a single standardized interface.

Try HiDream E1 in Playground

Generate images with custom prompts — no API key needed.

Open Playground