HiDream I1 Full API

hidream/i1-full

Generate high-quality images from a text prompt with strong prompt adherence and detailed, coherent results.

0.05 per megapixel of image

OpenAPI

Input

Prompt

The prompt to generate an image from.

Image Size

Width

Height

The size of the generated image.

Num Images

Min: 1 - Max: 4

The number of images to generate. Each generated image is billed.

Output Format

The format of the generated image.

Additional Settings

Customize your input with more control.

Negative Prompt

Describe what you do NOT want to appear in the image.

Num Inference Steps

Min: 1 - Max: 50

The number of inference steps to perform.

Seed

The same seed and the same prompt given to the same version of the model will output the same image every time.

Guidance Scale

Min: 0 - Max: 20

The CFG scale. Higher values increase adherence to the prompt.

Enable Safety Checker

Safety checker can only be disabled on API call

LoRAs

Optional list of LoRA weights to apply.

You need to be logged in to run this model and view results.

Output

{
  "error": "",
  "inferenceTime": 12232,
  "output": [
    "https://media.modelrunner.ai/i2ZPWoETsiRdXhSp61SIE.jpeg"
  ],
  "input": {
    "loras": [],
    "prompt": "A vintage travel poster for 'KYOTO' featuring a iconic red torii gate at golden hour, bold retro typography, cherry blossom petals drifting in the air, deep indigo sky, art-deco border, flat graphic style",
    "image_size": "portrait_4_3",
    "num_images": 1,
    "output_format": "jpeg",
    "guidance_scale": 5,
    "negative_prompt": "",
    "num_inference_steps": 50,
    "enable_safety_checker": true
  },
  "logs": "Generated 1 output(s)"
}

Generated in 12.232 seconds

Logs (1 lines)

Examples

HiDream I1 Full API

HiDream I1 Full is a text-to-image AI model by hidream. On ModelRunner it runs through a REST API or via MCP from any AI assistant, at $0.05 per megapixel.

POST https://queue.modelrunner.run/hidream/i1-full

cURL

# Submit a request to the queue. Input fields go at the top level of the
# body. The optional reserved "metadata" object holds your own flat string
# tags — stored on the request, never sent to the model; filter later with
# GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>.
curl -X POST https://queue.modelrunner.run/hidream/i1-full \
  -H "Authorization: Key $MRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "loras": [],
    "prompt": "A vintage travel poster for \u0027KYOTO\u0027 featuring a iconic red torii gate at golden hour, bold retro typography, cherry b…",
    "image_size": "portrait_4_3",
    "num_images": 1,
    "output_format": "jpeg",
    "guidance_scale": 5,
    "negative_prompt": "",
    "num_inference_steps": 50,
    "enable_safety_checker": true,
    "metadata": {
      "project": "my-project"
    }
  }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }

# Poll status_url until "COMPLETED", then fetch the result
curl "https://queue.modelrunner.run/hidream/i1-full/requests/$REQUEST_ID/status" \
  -H "Authorization: Key $MRUN_API_KEY"
curl "https://queue.modelrunner.run/hidream/i1-full/requests/$REQUEST_ID" \
  -H "Authorization: Key $MRUN_API_KEY"

JavaScript

import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("hidream/i1-full", {
  input: {
    "loras": [],
    "prompt": "A vintage travel poster for 'KYOTO' featuring a iconic red torii gate at golden hour, bold retro typography, cherry b…",
    "image_size": "portrait_4_3",
    "num_images": 1,
    "output_format": "jpeg",
    "guidance_scale": 5,
    "negative_prompt": "",
    "num_inference_steps": 50,
    "enable_safety_checker": true
  },
});
console.log(result);

Python

import os
import requests

headers = {"Authorization": f"Key {os.environ['MRUN_API_KEY']}"}

submitted = requests.post(
    "https://queue.modelrunner.run/hidream/i1-full",
    headers=headers,
    json={
      "loras": [],
      "prompt": "A vintage travel poster for 'KYOTO' featuring a iconic red torii gate at golden hour, bold retro typography, cherry b…",
      "image_size": "portrait_4_3",
      "num_images": 1,
      "output_format": "jpeg",
      "guidance_scale": 5,
      "negative_prompt": "",
      "num_inference_steps": 50,
      "enable_safety_checker": true
    },
).json()

# Poll submitted["status_url"] until "COMPLETED", then:
result = requests.get(submitted["response_url"], headers=headers).json()

Input parameters

Name	Type	Required	Description
prompt	string	yes	The prompt to generate an image from.
image_size	enum	no	The size of the generated image. Default: "square_hd".
num_images	integer	no	The number of images to generate. Each generated image is billed. Default: 1.
output_format	enum	no	The format of the generated image. Default: "jpeg".
negative_prompt	string	no	Describe what you do NOT want to appear in the image. Default: "".
num_inference_steps	integer	no	The number of inference steps to perform. Default: 50.
seed	integer	no	The same seed and the same prompt given to the same version of the model will output the same image every time.
guidance_scale	number	no	The CFG scale. Higher values increase adherence to the prompt. Default: 5.
enable_safety_checker	boolean	no	If set to true, the safety checker will be enabled. Default: true.
loras	array	no	Optional list of LoRA weights to apply. Default: [].

Machine-readable: OpenAPI schema · llms.txt

Use HiDream I1 Full from Claude & Cursor (MCP)

Point Claude Code, Claude Desktop, Cursor, or any MCP client at the ModelRunner MCP server and HiDream I1 Full becomes a tool your assistant can call directly — it authorizes via OAuth (no API key in config) and runs this model with the run_model tool using the endpoint hidream/i1-full.

MCP client config (Claude Desktop, Cursor)

{
  "mcpServers": {
    "modelrunner": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.modelrunner.run/mcp"]
    }
  }
}

Claude Code

claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcp

Then ask your assistant, for example: “Run hidream/i1-full on ModelRunner to generate image”. MCP setup guide.

Model Details

HiDream I1 Full turns a text prompt into a high-quality image. It is the full-quality variant of HiDream.ai's 17-billion-parameter open image foundation model, tuned for strong prompt adherence and detailed, coherent results, and it runs at the model's maximum step count for the best fidelity. Give it a descriptive prompt, pick a size, and it returns one to four finished images. You can also attach one or more LoRAs to steer style.

## Best for - Generating photorealistic images and detailed illustrations from a text description - Concept art, product renders, and stylized scenes where fidelity matters more than speed - Marketing and social visuals produced from a short written brief - Applying a custom LoRA to push a consistent style across a batch - Producing several variations at once with num_images (1-4)

## Choose another model when - You need to edit or restyle an existing photo rather than generate from scratch - use an image-editing model - You want the fastest, cheapest draft and can trade some quality - use a speed-optimized text-to-image model - You need reliably legible in-image text for logos or signage - use a model tuned for typography - You need video - use a text-to-video or image-to-video model

## Tips - Write specific, descriptive prompts; use negative_prompt to exclude unwanted elements - image_size accepts a preset (square_hd, portrait_16_9, landscape_4_3, ...) or a custom width/height object; billing is per output megapixel, so larger images cost more - Each image in num_images is billed separately

## Advanced Configuration - loras: attach one or more LoRA weights to bias style or subject. Each entry takes a path (a URL or HuggingFace path to the weights) and an optional scale (0-4, default 1); configured via the API.

HiDream I1 Full API

Model Input

Input

Additional Settings

Model Output

Output

Model Example Requests

Examples

HiDream I1 Full API

cURL

JavaScript

Python

Input parameters

Use HiDream I1 Full from Claude & Cursor (MCP)

MCP client config (Claude Desktop, Cursor)

Claude Code

Model Details

Model Details