Distilled version of HiDream AI's 17B parameter text-to-image model
hidream-i1-fast
Starting from
Prices shown are in USD · Some prices estimated from per-megapixel or per-token pricing
See all providersHiDream I1 Fast is available from 2 providers, with per-image pricing starting at $0.005 through Replicate.
replicate/hidream-i1-fast
fal/hidream-i1-fast
Access HiDream I1 Fast through Lumenfall's OpenAI-compatible API to integrate fast, high-quality text-to-image generation into any application with a single endpoint.
https://api.lumenfall.ai/openai/v1
hidream-i1-fast
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": "..." }] }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);from openai import OpenAIclient = 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)| Parameter | Type | Description | Modes |
|---|---|---|---|
prompt
|
string | Required. Text prompt for image generation |
T2I
|
negative_prompt
|
string | Negative prompt to guide generation away from undesired content |
T2I
|
seed
|
integer | Random seed for reproducibility |
T2I
|
| 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.
|
T2I
|
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.
|
T2I
|
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.
|
T2I
|
size
Exact pixel dimensions
"1920x1080"
aspect_ratio
Shape only, default scale
"16:9"
resolution
Scale tier, preserves shape
"1K"
size is most specific and always wins. aspect_ratio and resolution control shape and scale independently.
7:1 on a model with
4:1 and 8:1,
you get 8:1.
0.5K 1K 2K 4K)
or megapixel tiers (0.25 1).
If the exact tier isn't available, you get the nearest one.
| Parameter | Type | Description | Modes |
|---|---|---|---|
response_format
|
string |
How to return the image
url
b64_json
Default:
"url" |
T2I
|
output_format
|
string |
Output image format
png
jpeg
gif
webp
avif
Gateway converts to requested format if provider doesn't support it natively.
|
T2I
|
output_compression
|
integer | Compression level for lossy formats (JPEG, WebP, AVIF) |
T2I
|
n
|
integer |
Number of images to generate
Default:
1Gateway generates multiple images in parallel even if provider only supports 1.
|
T2I
|
| Parameter | Type | Description | Modes |
|---|---|---|---|
enable_safety_checker
fal
|
boolean | If set to true, the safety checker will be enabled. |
T2I
|
model_type
replicate
|
string |
Model type
fast
|
T2I
|
num_inference_steps
fal
|
integer | The number of inference steps to perform. |
T2I
|
output_quality
replicate
|
integer | Output quality (for jpg and webp) |
T2I
|
speed_mode
replicate
|
string |
Speed optimization level
Extra Juiced 🚀 (even more speed)
Juiced 🔥 (more speed)
Lightly Juiced 🍊 (more consistent)
Unsqueezed 🍋 (highest quality)
|
T2I
|
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. |
T2I
|
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.
HiDream I1 Fast holds the 26th position in the text-to-image arena with an Elo rating of 1155. This distilled version of HiDream AI's 17B parameter architecture competes against major models in the prompt-to-image generation category.
“Close portrait of a battle-worn paladin in ornate engraved plate armor, hair braided with small beads, faint scars and dirt on the skin, warm torchlight reflecting off metal, shallow depth of field, bokeh sparks, lifelike eyes, highly detailed texture on leather straps and cloth underlayer.”
“Hyper-photorealistic full-body portrait of a female superhero standing triumphantly on a New York skyscraper rooftop at golden sunset, wearing a classic modest superhero costume with flowing cape, chest emblem, gloves, and boots in red and blue colors, practical design, short hair, strong determined heroic expression looking into the distance, powerful confident stance with hands on hips and cape billowing dramatically in the wind, detailed urban cityscape background, warm natural sunlight with sharp shadows and fabric highlights, ultra-sharp textures on suit, hair, and concrete, 8K masterpiece, empowering family-friendly style.”
“Close portrait of a battle-worn paladin in ornate engraved plate armor, hair braided with small beads, faint scars and dirt on the skin, warm torchlight reflecting off metal, shallow depth of field, bokeh sparks, lifelike eyes, highly detailed texture on leather straps and cloth underlayer.”
See how HiDream I1 Fast performs head-to-head against other AI models, ranked by community votes in blind comparisons.
HiDream I1 Fast ranks 16th out of 19 models for portrait generation, achieving a 20.6% win rate in human-preference testing. It excels at high-speed generation of human subjects while maintaining competitive performance across diverse text-to-image prompt categories.
HiDream I1 Fast starts at $0.005 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.
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.
HiDream I1 Fast is available through fal.ai and Replicate on Lumenfall. Lumenfall automatically routes requests to the best available provider.
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.
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.
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.
Generate images with custom prompts — no API key needed.
