HiDream-I1 is an open-source, 17B-parameter image generative foundation model that delivers state-of-the-art image quality in seconds. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.012per run·~83 / $1
ExamplesView all
a cat wearing a sunglasses and holding a skateboard which has 'HiDream' written on it in red spray paint
A Ghibli-inspired scene featuring a giant, friendly creature walking through a lush forest and holding a sign saying 'HiDream', with vibrant colors, soft lighting, and whimsical details like floating lights and colorful, magical creatures. The scene captures a peaceful, enchanted atmosphere.
overhead close up view looking down on sweaty kpop star iu lying seductively on floor of dim nightclub with mouth open and tongue sticking out, hair forehead and nose smothered with many streaks of dripping white milk as she looks up at the sky ecstatic
hatsune miku in disney and pixar 3d render in Harry Potter universe
Realistic Paintiing from 18s century fir a kid with brown eyes and dark brown hair, wearing a suit in medieval times
(award-winning cinematic photo of a 6-year-old girl tmtvSophiaDW), ((angelic face of tmtvSophiaDW)), sitting on a rooftop at twilight, black velvet dress with gold embroidery, soft wind blowing her curls, intense blue eyes reflecting city lights, subtle glitter makeup under eyes, glowing skin, melancholic expression, photorealistic, city skyline bokeh in background, shallow depth of field, dark moody color palette, masterpiece, ultra detailed, 85mm lens, cinematic lighting
In a dimly lit, high-end apartment, a confident, dark-skinned young female Interpol agent with her hair tied back in a bun and donning long yellow satin gloves, places a small, silver duct tape wrapped Russian boy onto a worn leather couch. The boy's mouth is taped shut with a wide silver duct tape. The agent grips the boy's cheeks, and he looks surprised. The boy's arms are behind his back. The boy wears a pajama. The agent's smile, a blend of mirth and determination, contrasts with her harsh makeup in an Alpha-inspired style. She wears a yellow floral dress with no sleeves and red thigh high boots. Large windows in the background reveal an ocean view, suggesting a hotel room setting. The director's visual style, reminiscent of Ridley Scott, includes a subtle film grain, cool color grading, and high-contrast lighting with hard shadows and stark highlights, emphasizing the tension in the scene. The lighting setup includes a cool blue key light above and to the left of the agents, a warm white fill light to her right, and a cold white backlight behind the boy. The overall effect is atmosphere of mystery and intrigue.
Dynamic shot of an alternative model with neon green eye makeup that glitches like a corrupted video file, wearing a leather jacket with circuit board patterns that pulse with ransomware animations. Stands in a dystopian hacker market filled with floating crypto wallets and VHS tapes labeled "Classified." Dramatic red/black lighting with green matrix rain and a "FATAL ERROR" tattoo glowing on her neck.
Create a 2D anime-style farm map for a cozy farming game. The map should capture the peaceful and charming atmosphere of rural life in a colorful anime-inspired world. Include the following elements: Lush green farmland with neatly planted crops (e.g., carrots, tomatoes, wheat) Wooden fences separating crop plots and animal pens A small farmhouse with a tiled roof, flower beds, and a chimney Barns and chicken coops in a traditional Japanese countryside style Dirt paths connecting areas, with soft shading and some pebbles or grass Fruit trees (e.g., apple, peach) and wildflowers scattered around the field A pond or small river with a wooden bridge Background with soft hills, trees, or a sunrise sky Optional small animals like cows, chickens, or a dog sleeping in the shade Optional farmer NPCs walking around or working on the land Style: Top-down or isometric 2D view Bright, cell-shaded anime colors, clean lines, and chibi-scale proportions Make it suitable for a mobile farming simulation game with UI space around the edges Do not include any text or interface elements. The map should feel like a warm, quiet, and happy countryside life in an anime world.
A Ghibli-inspired scene featuring a giant, friendly creature walking through a lush forest and holding a sign saying 'HiDream', with vibrant colors, soft lighting, and whimsical details like floating lights and colorful, magical creatures. The scene captures a peaceful, enchanted atmosphere.
A letter based logo for a web app that is used to store your personal knowledge and records of your friends, family etc
Cyberpunk girl with neon pink hair and glowing implants walking through rainy Tokyo streets, reflections, neon signs, 4K hyper-detail, Blade Runner vibes
Related Models
README
HiDream I1 Dev — wavespeed-ai/hidream-i1-dev
HiDream I1 Dev is a fast, cost-efficient text-to-image model for generating high-quality images from prompts. It’s well-suited for concept art, marketing creatives, mascots, and prompt-driven typography-in-image needs (e.g., short words on signs or objects). You can specify exact output dimensions, set a seed for reproducibility, and choose the output format for easy downstream use.
Key capabilities
- Text-to-image generation from a single prompt
- Good for stylized characters, product concepts, and marketing visuals
- Supports prompt-specified text rendering inside the image (best for short phrases)
- Custom output size (set width/height directly)
- Seed control for reproducible generations
- URL output or BASE64 output (API only)
Use cases
- Mascot and character creation (e.g., branded animals, sticker-style art)
- Social creatives and ad variations from one prompt
- Concept exploration (composition, props, outfits, themes)
- Quick brand mockups (logos/words on props, posters, boards)
- Batch generation with consistent framing via fixed seed + size
Pricing
| Output | Price |
|---|---|
| Per image | $0.012 |
Parameters
- prompt (required): what to generate (subject + scene + style + any visible text)
- width / height: output size (e.g., 1024×1024)
- seed: random seed (-1 for random; set for reproducible results)
- output_format: output format (e.g., jpeg)
- enable_base64_output: return BASE64 instead of URL (API only)
Prompting guide
For images that include readable text, keep the on-image text short and unambiguous, and specify where it appears.
Template: Subject + action + setting + style. Include the text “...” on [object] in [color/material], clearly readable.
Example prompts
- A cat wearing sunglasses holding a skateboard. The skateboard has the word “HiDream” written in red spray paint, clearly readable. Street photography style, high detail, strong contrast, 1024×1024.
- A clean product poster: a glossy sneaker on a studio background, with “HiDream” as small text on the shoe tag, minimalist design, soft shadows, crisp lighting.
Hidream I1 Dev API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/hidream-i1-dev with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Hidream I1 Dev below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/hidream-i1-dev" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1024*1024",
"seed": -1,
"output_format": "jpeg",
"enable_base64_output": false
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("wavespeed-ai/hidream-i1-dev", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1024*1024",
"seed": -1,
"output_format": "jpeg",
"enable_base64_output": false
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"wavespeed-ai/hidream-i1-dev",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1024*1024",
"seed": -1,
"output_format": "jpeg",
"enable_base64_output": false
}
)
print(output["outputs"][0]) # → URL of the generated outputHidream I1 Dev API — Frequently asked questions
What is the Hidream I1 Dev API?
Hidream I1 Dev is a WaveSpeedAI model for image generation, exposed as a REST API on WaveSpeedAI. HiDream-I1 is an open-source, 17B-parameter image generative foundation model that delivers state-of-the-art image quality in seconds. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Hidream I1 Dev API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/hidream-i1-dev.
How much does Hidream I1 Dev cost per run?
Hidream I1 Dev starts at $0.012 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Hidream I1 Dev accept?
Key inputs: `prompt`, `size`, `seed`, `enable_base64_output`, `output_format`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/hidream-i1-dev.
How long does Hidream I1 Dev take to generate?
Average end-to-end generation time on WaveSpeedAI is around 14 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Hidream I1 Dev outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.