# HiDream I1 Fast

> Distilled version of HiDream AI's 17B parameter text-to-image model

## Quick Reference

- Model ID: hidream-i1-fast
- Creator: HiDream AI
- Status: active
- Family: hidream
- Base URL: https://api.lumenfall.ai/openai/v1

## Specifications

- Input Modalities: text
- Output Modalities: image
- Supported Modes: Text to Image

## API Parameters

The compiled parameter schema for this model is available via the API: `GET /v1/models/hidream-i1-fast?schema=true`.

### Core Parameters

- `prompt` (string) — REQUIRED: Text prompt for image generation
- `negative_prompt` (string): Negative prompt to guide generation away from undesired content
- `seed` (integer): Random seed for reproducibility

### Size & Layout

- `size` (string): Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9")
- `aspect_ratio` (string): Aspect ratio of the output image (e.g. "16:9", "1:1")
- `resolution` (string): Output resolution tier (e.g. "1K", "4K")

### Output & Format

- `response_format` (string): How to return the image. Default: url. Values: url, b64_json
- `output_format` (string): Output image format. Values: png, jpeg, gif, webp, avif
- `output_compression` (integer): Compression level for lossy formats (JPEG, WebP, AVIF)
- `n` (integer): Number of images to generate. Default: 1

### Additional Parameters

- `enable_safety_checker` (boolean): If set to true, the safety checker will be enabled.. Only available via fal
- `model_type` (string): Model type. Values: fast. Only available via replicate
- `num_inference_steps` (integer): The number of inference steps to perform.. Only available via fal
- `output_quality` (integer): Output quality (for jpg and webp). Only available via replicate
- `speed_mode` (string): Speed optimization level. Values: Extra Juiced 🚀 (even more speed), Juiced 🔥 (more speed), Lightly Juiced 🍊 (more consistent), Unsqueezed 🍋 (highest quality). Only available via replicate
- `sync_mode` (boolean): If `True`, the media will be returned as a data URI and the output data won't be available in the request history.. Only available via fal


## Model Identifiers

- Primary Slug: hidream-i1-fast


## Tags

image-generation, text-to-image

## Available Providers

### fal.ai

- Config Key: fal/hidream-i1-fast
- Provider Model ID: fal-ai/hidream-i1-fast
- Pricing: $0.010/megapixel
  - Source: https://fal.ai/models/fal-ai/hidream-i1-fast

### Replicate

- Config Key: replicate/hidream-i1-fast
- Provider Model ID: prunaai/hidream-l1-fast
- Pricing: $0.0050/image
  - Note: PrunaAI optimized version of HiDream L1
  - Note: ~$0.014 per image (71 runs per $1)
  - Source: https://replicate.com/prunaai/hidream-l1-fast


## Arena Benchmarks

### Fantasy Warrior

- Elo: 1174
- Record: 9W / 31L / 2T (42 battles)
- Rank: #13 of 21

### Fantasy Warrior

- Elo: 1049
- Record: 1W / 5L / 0T (6 battles)
- Rank: #12 of 14

### Heroic Super Hero Portrait

- Elo: 1000
- Record: 0W / 8L / 0T (8 battles)
- Rank: #21 of 21


## Use Cases & Category Performance

### Portrait (Text-to-Image)

- Rank: #18 of 21
- Elo: 1131
- Record: 9W / 31L / 2T (42 battles)
- Win Rate: 21.4%


## Image Gallery

5 images available for this model. Browse all at https://lumenfall.ai/models/hidream-ai/hidream-i1-fast/gallery

### Curated Examples

- [A cinematic, wide-angle shot of a luxury boutique storefront at dusk. The shop’s large glass wind...](https://assets.lumenfall.ai/d5xeQ0sTegkSwSW7lwK039huBRmjPrkRu3stpE0SZzs/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/kkouwhj2ful7dvxtslxy0jvgcoy5@jpeg)
- [A cozy street corner bakery with a large chalkboard sign that says "FRESH SOURDOUGH" in elegant h...](https://assets.lumenfall.ai/5UhtCJlZL8tTqv1N_yPXiwWu1I80kJhO58h91Qh-cbU/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/lqbkzw6yrewue298m07w5kjbh5md@jpeg)

### Arena Competition Results

- [Fantasy Warrior](https://assets.lumenfall.ai/r-1iHE3lkSGBafj9d-74XQXcLjb3me2-I7qLamuW0RM/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/tubawpdaywbcppaqruurgnfeb3ha@jpeg): #13 of 21 (Elo 1174)
- [Fantasy Warrior](https://assets.lumenfall.ai/nJZiuw4sePsrkKuHpCh59tTG-B-uC00znCsTMEJAiOE/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/52m6021xtw5oxbv7fslrghzbi28i@jpeg): #12 of 14 (Elo 1049)
- [Heroic Super Hero Portrait](https://assets.lumenfall.ai/W68EAZ3x1IPO4SFPbU5DycIvnRosgIIff9vdJ-jWgrc/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/kvx1ntj0equaf966e0y5ote5gdoy@jpeg): #21 of 21 (Elo 1000)

## Example Prompt

The following prompt was used to generate an example image in our playground:

A cozy street corner bakery with a large chalkboard sign that says "FRESH SOURDOUGH" in elegant hand-lettered cursive. Golden afternoon sun hits the storefront. In the background, a capybara calmly waits in line behind a woman in a floral dress.

## Code Examples

### Text to Image (/v1/images/generations)

#### cURL

curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/generations \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hidream-i1-fast",
    "prompt": "",
    "size": "1024x1024"
  }'

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

#### JavaScript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.lumenfall.ai/openai/v1'
});

const response = await client.images.generate({
  model: 'hidream-i1-fast',
  prompt: '',
  size: '1024x1024'
});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
console.log(response.data[0].url);

#### Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.lumenfall.ai/openai/v1"
)

response = client.images.generate(
    model="hidream-i1-fast",
    prompt="",
    size="1024x1024"
)

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
print(response.data[0].url)


## About

## Overview
HiDream I1 Fast is a distilled text-to-image model developed by HiDream AI, optimized for low-latency image generation. It is a high-speed variant of the company's flagship 17-billion parameter model, designed to retain the compositional intelligence of a large-scale architecture while significantly reducing inference costs and generation time.

## Strengths
*   **Low Latency Generation:** The distillation process allows the model to produce high-resolution images in a fraction of the time required by standard diffusion models.
*   **Multi-Subject Composition:** Leveraging its 17B-parameter lineage, the model excels at managing spatial relationships and interactions between multiple distinct objects within a single frame.
*   **Prompt Adherence:** It demonstrates high fidelity to descriptive text inputs, particularly when handling complex attributes such as lighting conditions, material textures, and specific artistic styles.
*   **Resource Efficiency:** Provides a high quality-to-cost ratio, making it suitable for applications that require massive batches of image generation at a starting price of $0.005 per output.

## Limitations
*   **Detail Nuance:** As a distilled model, it may lack some of the fine-grained textural detail and edge sharpness found in the full 17B parameter non-distilled version.
*   **Text Rendering:** Like many diffusion-based architectures, it may struggle with generating lengthy or highly specific typographic strings within the image.
*   **Photorealism Extremes:** While it handles stylized and general photographic content well, it may produce occasional artifacts in anatomy or complex environmental reflections compared to slower, specialized photorealistic models.

## Technical Background
HiDream I1 Fast is based on a transformer-heavy diffusion architecture, utilizing a massive 17-billion parameter backbone. The model employs knowledge distillation techniques to compress the computational requirements of the teacher model into a faster student model, prioritizing inference speed without sacrificing the fundamental semantic understanding acquired during large-scale pre-training.

## Best For
HiDream I1 Fast is an ideal choice for real-time creative tools, social media asset generation, and rapid prototyping where speed is as critical as aesthetic quality. It is also well-suited for high-volume workflows like generating game assets or marketing variations. You can access HiDream I1 Fast through Lumenfall’s unified API and interactive playground, allowing for easy integration into existing production pipelines.

## Frequently Asked Questions

### How much does HiDream I1 Fast cost?

HiDream I1 Fast starts at $0.005 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

### How do I use HiDream I1 Fast via API?

You can use HiDream I1 Fast through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "hidream-i1-fast". Code examples are available in Python, JavaScript, and cURL.

### Which providers offer HiDream I1 Fast?

HiDream I1 Fast is available through fal.ai and Replicate on Lumenfall. Lumenfall automatically routes requests to the best available provider.

## Links

- Model Page: https://lumenfall.ai/models/hidream-ai/hidream-i1-fast
- About: https://lumenfall.ai/models/hidream-ai/hidream-i1-fast/about
- Providers, Pricing & Performance: https://lumenfall.ai/models/hidream-ai/hidream-i1-fast/providers
- API Reference: https://lumenfall.ai/models/hidream-ai/hidream-i1-fast/api
- Benchmarks: https://lumenfall.ai/models/hidream-ai/hidream-i1-fast/benchmarks
- Use Cases: https://lumenfall.ai/models/hidream-ai/hidream-i1-fast/use-cases
- Gallery: https://lumenfall.ai/models/hidream-ai/hidream-i1-fast/gallery
- Playground: https://lumenfall.ai/playground?model=hidream-i1-fast
- API Documentation: https://docs.lumenfall.ai