WaveSpeed.ai
首頁/探索/wavespeed-ai/hidream-i1-dev
text-to-image

text-to-image

HiDream I1 Dev

wavespeed-ai/hidream-i1-dev

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.

Input
width
height
If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.

Idle

a cat wearing a sunglasses and holding a skateboard which has 'HiDream' written on it in red spray paint

您的請求將花費 $0.012 每次運行。

使用 $1 您可以運行此模型大約 83 次。

還有一件事：:

示例查看全部

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

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

OutputPrice
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.