Text-to-Image
Prompt
“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
HiDream I1 Full
AI Image Editing Model
Image
$$$
·
5¢
HiDream AI's 17B parameter text-to-image model using sparse diffusion transformer with mixture of experts, achieving state-of-the-art image generation quality with strong prompt following
Details
Model ID
hidream-i1-full
Tags
image-generation
text-to-image
Starting from
$0.050
/image
via fal.ai
Prices shown are in USD · Some prices estimated from per-megapixel or per-token pricing
Full pricing detailsProviders & Pricing (2)
HiDream I1 Full is available from 2 providers, with per-image pricing starting at $0.05 through fal.ai.
fal.ai
Text to Image
fal/hidream-i1-full
Provider Model ID:
fal-ai/hidream-i1-full
$0.050
/megapixel
fal.ai
Image Edit
fal/hidream-i1-full-edit
Provider Model ID:
fal-ai/hidream-i1-full/image-to-image
$0.050
/megapixel
HiDream I1 Full API OpenAI-compatible
Integrate the HiDream I1 Full model into your workflow via Lumenfall’s OpenAI-compatible API to programmatically generate high-fidelity images and perform precise image editing using MiE-based diffusion.
Base URL
https://api.lumenfall.ai/openai/v1
Model
hidream-i1-full
Code Examples
Text to Image
/v1/images/generationscurl -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-full", "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-full', 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-full", prompt="", size="1024x1024")# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }print(response.data[0].url)Image Edit
/v1/images/editscurl -X POST \ https://api.lumenfall.ai/openai/v1/images/edits \ -H "Authorization: Bearer $LUMENFALL_API_KEY" \ -F "model=hidream-i1-full" \ -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-i1-full', 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 OpenAIclient = OpenAI( api_key="YOUR_API_KEY", base_url="https://api.lumenfall.ai/openai/v1")response = client.images.edit( model="hidream-i1-full", 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 |
T2I
Edit
|
negative_prompt
|
string | Negative prompt to guide generation away from undesired content |
T2I
Edit
|
seed
|
integer | Random seed for reproducibility |
T2I
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.
|
T2I
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.
|
T2I
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.
|
T2I
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.
|
T2I
Edit
|
Output & Format
| Parameter | Type | Description | Modes |
|---|---|---|---|
response_format
|
string |
How to return the image
url
b64_json
Default:
"url" |
T2I
Edit
|
output_format
|
string |
Output image format
png
jpeg
gif
webp
avif
Gateway converts to requested format if provider doesn't support it natively.
|
T2I
Edit
|
output_compression
|
integer | Compression level for lossy formats (JPEG, WebP, AVIF) |
T2I
Edit
|
n
|
integer |
Number of images to generate
Default:
1Gateway generates multiple images in parallel even if provider only supports 1.
|
T2I
Edit
|
Additional Parameters
Provider-specific passthrough fields, available only when the request is routed to the listed provider.
| Parameter | Type | Description | Modes |
|---|---|---|---|
|
Universal
|
|||
cfg_scale
|
number | Classifier-free guidance scale — higher values stick more closely to the prompt |
T2I
Edit
|
strength
|
number | How much to transform the input image: 0 keeps it unchanged, 1 fully regenerates from the prompt |
T2I
Edit
|
|
fal
|
|||
enable_safety_checker
|
boolean | If set to true, the safety checker will be enabled. |
T2I
Edit
|
loras
|
array | A list of LoRAs to apply to the model. Each LoRA specifies its path, scale, and optional weight name. |
T2I
Edit
|
num_inference_steps
|
integer | The number of inference steps to perform. |
T2I
Edit
|
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. |
T2I
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.
HiDream I1 Full Benchmarks
HiDream I1 Full is ranked #52 in Text-to-Image with an Elo of 1191 and #26 in Image Editing with an Elo of 1160 on the Lumenfall Arena, where real users pick the better image in blind comparisons. These rankings are based on 6 blind-vote competitions.
Lumenfall Arena
#52
Text-to-Image
1191
Elo
Lumenfall Arena
#26
Image Editing
1160
Elo
Text-to-Image Landscape
Elo vs Cost
1 model without pricing omitted.
Elo vs Speed
38 models waiting for enough speed data.
Image Editing Landscape
Elo vs Cost
1 model without pricing omitted.
Elo vs Speed
16 models waiting for enough speed data.
Competition Results
Text-to-Image
Prompt
“Photorealistic scene inside a yellow New York taxi at night. A capybara is driving, wearing a yellow taxi driver cap and a dark jacket. It has a calm, professional expression and both front paws on the steering wheel. In the back seat sits a human businesswoman in a coat, looking at her phone with a completely normal, bored expression (as if this is just another normal ride). Through the windows you can see the streets of Manhattan at night with blurred lights. Realistic taxi interior, photorealistic, detailed fur and fabric, 35mm lens, night lighting with reflections, shallow depth of field.”
Text-to-Image
Prompt
“Handwritten-style chalkboard menu in a cozy café, all text rendered in the exact same realistic chalk handwriting style with natural variations in letter size, slight slant, and chalk texture — no printed or digital fonts anywhere on the board. Title at the top in elegant cursive chalk handwriting: ‘TODAY’S SPECIALS – APRIL 30, 2026’. Below it, three menu items also in the same handwritten chalk style: ‘Truffle Mushroom Risotto – $24’, ‘Grilled Octopus with Lemon & Herbs – $28’, ‘Brown Butter Chocolate Chip Cookies – $9’. At the very bottom, smaller text in the identical handwritten chalk style (slightly smaller but still clearly legible with the same handwriting characteristics): ‘All items made fresh daily • Ask about our gluten-free options’. Warm ambient café lighting, visible chalk dust and smudges, realistic handwriting imperfections, no clean printed text anywhere.”
Text-to-Image
Prompt
“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.”
Text-to-Image
Prompt
“A candid street photo of an elderly Japanese man repairing a red bicycle in light rain, reflections on wet pavement, shallow depth of field, 50mm lens, natural skin texture, imperfect framing, motion blur from passing cars, cinematic but realistic, no stylization.”
Text-to-Image
Prompt
“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
Text-to-Image
Prompt
“Vintage gothic Halloween party invitation. Dark parchment poster, spooky border with webs and thorns, central glowing jack-o-lantern, bats, twisted trees, moody night sky. Add elegant gothic title text saying "Halloween Party Invitation", a small scroll banner saying "You are invited to a night of frights", and event details at the bottom: Date: 30.10.2026 Time: 7pm Location: The Arches, NYC Spooky but polished, cinematic lighting, square format.”
Text-to-Image
Prompt
“Photorealistic scene inside a yellow New York taxi at night. A capybara is driving, wearing a yellow taxi driver cap and a dark jacket. It has a calm, professional expression and both front paws on the steering wheel. In the back seat sits a human businesswoman in a coat, looking at her phone with a completely normal, bored expression (as if this is just another normal ride). Through the windows you can see the streets of Manhattan at night with blurred lights. Realistic taxi interior, photorealistic, detailed fur and fabric, 35mm lens, night lighting with reflections, shallow depth of field.”
Text-to-Image
Prompt
“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.”
Text-to-Image
Prompt
“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
Text-to-Image
Prompt
“Vintage gothic Halloween party invitation. Dark parchment poster, spooky border with webs and thorns, central glowing jack-o-lantern, bats, twisted trees, moody night sky. Add elegant gothic title text saying "Halloween Party Invitation", a small scroll banner saying "You are invited to a night of frights", and event details at the bottom: Date: 30.10.2026 Time: 7pm Location: The Arches, NYC Spooky but polished, cinematic lighting, square format.”
Text-to-Image
Prompt
“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.”
Text-to-Image
Prompt
“A candid street photo of an elderly Japanese man repairing a red bicycle in light rain, reflections on wet pavement, shallow depth of field, 50mm lens, natural skin texture, imperfect framing, motion blur from passing cars, cinematic but realistic, no stylization.”
Text-to-Image
Prompt
“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
Text-to-Image
Prompt
“Photorealistic scene inside a yellow New York taxi at night. A capybara is driving, wearing a yellow taxi driver cap and a dark jacket. It has a calm, professional expression and both front paws on the steering wheel. In the back seat sits a human businesswoman in a coat, looking at her phone with a completely normal, bored expression (as if this is just another normal ride). Through the windows you can see the streets of Manhattan at night with blurred lights. Realistic taxi interior, photorealistic, detailed fur and fabric, 35mm lens, night lighting with reflections, shallow depth of field.”
Text-to-Image
Prompt
“Handwritten-style chalkboard menu in a cozy café, all text rendered in the exact same realistic chalk handwriting style with natural variations in letter size, slight slant, and chalk texture — no printed or digital fonts anywhere on the board. Title at the top in elegant cursive chalk handwriting: ‘TODAY’S SPECIALS – APRIL 30, 2026’. Below it, three menu items also in the same handwritten chalk style: ‘Truffle Mushroom Risotto – $24’, ‘Grilled Octopus with Lemon & Herbs – $28’, ‘Brown Butter Chocolate Chip Cookies – $9’. At the very bottom, smaller text in the identical handwritten chalk style (slightly smaller but still clearly legible with the same handwriting characteristics): ‘All items made fresh daily • Ask about our gluten-free options’. Warm ambient café lighting, visible chalk dust and smudges, realistic handwriting imperfections, no clean printed text anywhere.”
Text-to-Image
Prompt
“Vintage gothic Halloween party invitation. Dark parchment poster, spooky border with webs and thorns, central glowing jack-o-lantern, bats, twisted trees, moody night sky. Add elegant gothic title text saying "Halloween Party Invitation", a small scroll banner saying "You are invited to a night of frights", and event details at the bottom: Date: 30.10.2026 Time: 7pm Location: The Arches, NYC Spooky but polished, cinematic lighting, square format.”
Text-to-Image
Prompt
“Handwritten-style chalkboard menu in a cozy café, all text rendered in the exact same realistic chalk handwriting style with natural variations in letter size, slight slant, and chalk texture — no printed or digital fonts anywhere on the board. Title at the top in elegant cursive chalk handwriting: ‘TODAY’S SPECIALS – APRIL 30, 2026’. Below it, three menu items also in the same handwritten chalk style: ‘Truffle Mushroom Risotto – $24’, ‘Grilled Octopus with Lemon & Herbs – $28’, ‘Brown Butter Chocolate Chip Cookies – $9’. At the very bottom, smaller text in the identical handwritten chalk style (slightly smaller but still clearly legible with the same handwriting characteristics): ‘All items made fresh daily • Ask about our gluten-free options’. Warm ambient café lighting, visible chalk dust and smudges, realistic handwriting imperfections, no clean printed text anywhere.”
Text-to-Image
Prompt
“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
Text-to-Image
Prompt
“Vintage gothic Halloween party invitation. Dark parchment poster, spooky border with webs and thorns, central glowing jack-o-lantern, bats, twisted trees, moody night sky. Add elegant gothic title text saying "Halloween Party Invitation", a small scroll banner saying "You are invited to a night of frights", and event details at the bottom: Date: 30.10.2026 Time: 7pm Location: The Arches, NYC Spooky but polished, cinematic lighting, square format.”
Text-to-Image
Prompt
“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.”
Text-to-Image
Prompt
“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.”
Text-to-Image
Prompt
“Vintage gothic Halloween party invitation. Dark parchment poster, spooky border with webs and thorns, central glowing jack-o-lantern, bats, twisted trees, moody night sky. Add elegant gothic title text saying "Halloween Party Invitation", a small scroll banner saying "You are invited to a night of frights", and event details at the bottom: Date: 30.10.2026 Time: 7pm Location: The Arches, NYC Spooky but polished, cinematic lighting, square format.”
Text-to-Image
Prompt
“Handwritten-style chalkboard menu in a cozy café, all text rendered in the exact same realistic chalk handwriting style with natural variations in letter size, slight slant, and chalk texture — no printed or digital fonts anywhere on the board. Title at the top in elegant cursive chalk handwriting: ‘TODAY’S SPECIALS – APRIL 30, 2026’. Below it, three menu items also in the same handwritten chalk style: ‘Truffle Mushroom Risotto – $24’, ‘Grilled Octopus with Lemon & Herbs – $28’, ‘Brown Butter Chocolate Chip Cookies – $9’. At the very bottom, smaller text in the identical handwritten chalk style (slightly smaller but still clearly legible with the same handwriting characteristics): ‘All items made fresh daily • Ask about our gluten-free options’. Warm ambient café lighting, visible chalk dust and smudges, realistic handwriting imperfections, no clean printed text anywhere.”
Top Matchups
See how HiDream I1 Full performs head-to-head against other AI models, ranked by community votes in blind comparisons.
Use Cases
See all Use Cases
Gallery
View all 9 imagesHiDream I1 Full FAQ
How much does HiDream I1 Full cost?
HiDream I1 Full starts at $0.05 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.
How do I use HiDream I1 Full via API?
You can use HiDream I1 Full through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "hidream-i1-full". Code examples are available in Python, JavaScript, and cURL.
Which providers offer HiDream I1 Full?
HiDream I1 Full is available through fal.ai on Lumenfall. Lumenfall automatically routes requests to the best available provider.
Overview
HiDream I1 Full is a high-capacity text-to-image and image-to-image model developed by HiDream AI. Utilizing a 17-billion parameter architecture, it is designed to bridge the gap between complex natural language prompts and high-fidelity visual outputs. The model is distinctive for its use of a Sparse Diffusion Transformer (DiT) combined with a Mixture-of-Experts (MoE) framework, allowing it to handle massive parameter counts with localized computational efficiency.
Strengths
- Prompt Adherence: The model demonstrates high fidelity to long, descriptive, and nuanced text prompts, accurately placing specific objects and attributes within a scene as requested.
- Compositional Detail: Due to the large parameter count, it excels at rendering complex textures and lighting conditions that smaller diffusion models often struggle to resolve.
- MoE Efficiency: The Mixture-of-Experts architecture allows the model to activate only a subset of its 17B parameters per request, leading to sophisticated image generation qualities without the prohibitive latency typical of monolithic models of this scale.
- Multimodal Input: It native supports image-to-image workflows, allowing users to provide visual references to guide the style, structure, or content of the final output.
Limitations
- Computational Cost: At $0.05 per generation, the model is targeted towards high-end production use cases and may be less economical for high-volume, low-stakes applications compared to smaller distilled models.
- Specialized Hardware Requirements: Due to the 17B parameter size, local deployment is challenging, making it primarily a cloud-driven model for most enterprise environments.
- Training Cutoff: Like all diffusion models, it may lack specific knowledge of very recent events, niche brand logos, or specialized technical schematics unless explicitly provided in the prompt or through fine-tuning.
Technical Background
HiDream I1 Full is built on a Diffusion Transformer (DiT) backbone, a departure from the traditional U-Net architectures used in earlier generative models. It integrates a Sparse Mixture-of-Experts (MoE) layer, which scales the model’s capacity to 17 billion parameters while maintaining manageable inference speeds. This training approach emphasizes high-dimensional latent space representations to ensure that fine-grained textual details are mapped accurately to pixels.
Best For
- Professional Concept Art: Generating high-resolution environment and character designs where specific lighting and material properties are critical.
- Precision Marketing Assets: Creating brand-aligned imagery that requires strict adherence to complex creative briefs.
- Visual Prototyping: Rapidly iterating on product designs using image-to-image guidance to maintain structural consistency.
HiDream I1 Full is available for immediate testing and deployment through Lumenfall’s unified API and interactive playground.
Try HiDream I1 Full in Playground
Generate images with custom prompts — no API key needed.