WaveSpeed.ai
DashboardExploreInspiration
Home/Explore/wavespeed-ai/hunyuan-image-3

text-to-image

wavespeed-ai/hunyuan-image-3

HunyuanImage-3.0 is a groundbreaking native multimodal model that unifies multimodal understanding and generation within an autoregressive framework. Our text-to-image module achieves performance comparable to or surpassing leading closed-source models.

width
height
If set to true, the function will wait for the image to be generated and uploaded before returning the response. It allows you to get the image directly in the response. This property is only available through the API.
If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.

Idle

Sticker sheet of a cute and expressive orange chibi cat. A set of 12 stickers, each showing a different emotion or action like crying, cheering, angry, sorry, and confident. Each sticker has a corresponding text label (e.g., "Sorry!", "Love you!", "Leave it to me!"). The style is clean, minimalist vector illustration with a thick white border, perfect for printing.

Your request will cost $0.05 per run.

For $1 you can run this model approximately 20 times.

One more thing:

ExamplesView all

Sticker sheet of a cute and expressive orange chibi cat. A set of 12 stickers, each showing a different emotion or action like crying, cheering, angry, sorry, and confident. Each sticker has a corresponding text label (e.g., "Sorry!", "Love you!", "Leave it to me!"). The style is clean, minimalist vector illustration with a thick white border, perfect for printing.
清明上河图风格，平面面展现江南立体图景，集合东方明珠、城隍庙、上海迪士尼、黄浦江等特色，图上有"上海"及"CHINA"标识，构图灵动，有小人儿在搞中秋节活动，配色浓郁热烈，充满市井烟火气。表面处理为亚麻效果，侧光烘托层次，背景采用颜色丰富，超高清画质，纤毫毕现，史诗级视角，精品，图片上方有“中秋节”真实。
A 3x3 grid collage of Elon Musk memes in 16-bit pixel art style. Each panel has a different theme: 1. Elon Musk as an astronaut. 2. Elon Musk with a punk rock mohawk. 3. Elon Musk holding a Dogecoin. 4. Elon Musk laughing with "LOL". 5. Elon Musk wearing "deal with it" sunglasses. 6. Elon Musk as a wizard holding a wand. 7. Elon Musk crying with the word "WHY". 8. A portrait of Elon Musk with "TO THE MOON". 9. A thoughtful portrait of Elon Musk with a colorful abstract background.
A digital artwork of cat composed entirely of wind, set against a black background.
A character sheet of a cute chibi girl with short black hair and a white t-shirt. A set of 4 illustrations on a plain white background. The poses are: 1. Relaxing on a deck chair wearing sunglasses. 2. Jumping with joy. 3. Eating an ice cream cone. 4. Yawning sleepily with "Z Z" symbols. The style is minimalist, clean lines, and adorable.
A 3x3 comic grid featuring a cute cartoon penguin expressing different daily moods. Each panel has a simple pastel background and a text caption. The panels include: "WOKE UP IT'S MONDAY", "I GOT THE SNACK", "SMOOTH", "JUST VIBING", "NEED MORE COFFEE". The art style is simple, cute, and expressive with bold outlines.
一位身着花色戏曲服装的中国美人，具有国潮花旦的戏曲妆扮，半身眼部特写，焦点在勾魂摄魄的双眼上。画面采用微距摄影风格，高清、富有想象力的真人写真，强调细节和真实感。构图采用近距离特写视角，美人位于画面中心，眼部占据主导位置，背景虚化以突出眼睛的深邃魅力。神秘冷光从上方斜照，营造出蓝色调的冷峻氛围，光线柔和且集中，增强眼睛的魅力和神秘感。f/2.8光圈，100mm微距镜头，浅景深，8K分辨率。
清明上河图风格，平面面展现江南立体图景，集合东方明珠、城隍庙、上海迪士尼、黄浦江等特色，图上有"上海"及"CHINA"标识，构图灵动，有小人儿在搞中秋节活动，配色浓郁热烈，充满市井烟火气。表面处理为亚麻效果，侧光烘托层次，背景采用颜色丰富，超高清画质，纤毫毕现，史诗级视角，精品，图片上方有“中秋节”真实。
一只可爱的宠物猫 在干净明亮的米白色纯色背景上，以九宫格（3x3）形式展示九种中秋节主题造型： 1.戴着小枫叶发夹，吐舌舔鼻子上沾着的月饼碎屑，表情顽皮。 2.穿焦糖色小毛衣（带有精致玉兔刺绣），坐直，前爪抱着一个迷你中式灯笼。 3.戴着小围巾（有桂花暗纹），蹭着一个圆形月饼毛绒玩具。 4.叼着一枝仿真桂花枝，奔跑跳跃的动态瞬间。 5.穿一件迷你浅红橙色"嫦娥"款式小外套（金边），歪着头，很好奇。 6.戴着缀有玉兔和月亮挂饰的项圈，打哈欠，显得困倦可爱。 7.趴在焦糖色软垫上（有月亮云纹图案），抬头看向前方。 8.戴着一个点缀着金色银杏和桂花的小发带，低头。 9.兴奋地咬着一个迷你毛绒月饼玩具，耳朵竖起，眼睛闪亮。 整体风格：温馨中秋节氛围，柔和光线，电影感，照片级真实，表情可爱，统一的暖色调（焦糖色、米色、棕色、月白色）。所有道具对宠物安全且大小合适。 风格：真实摄影。
狸花猫。瞬间抓拍，独特的拍摄角度，非对称，动态模糊，低光环境，光影美学，自然色彩，丰富层次感，细腻画质，真实，虚化柔和过渡，情绪氛围感，电影质感，获奖作品。
A confident professional woman is sitting in a minimalist office. She is wearing a white silk blouse and high-waisted wide-leg pants. The background shows a floor-to-ceiling window with a view of the city skyline. The indoor lighting is bright and even, creating a realistic portrait.
A handsome man in a well-tailored dark grey suit is leaning against the wall of a modern building in New York. He is wearing sunglasses and has a confident expression. The scene is lit with dramatic hard lighting, creating strong shadows and an urban chic feel, in the style of a Vogue editorial.
Close-up portrait of a model with sculptural facial features, against a solid color background (e.g., premium grey or Morandi color), dramatic side lighting creating a strong three-dimensional effect, ethereal gaze, minimalist composition, fashion magazine cover quality.
A lady in a midnight-blue off-the-shoulder silk evening gown, wearing a sparkling diamond necklace, standing in a magnificent ballroom, holding a glass of champagne, crystal chandeliers and blurred crowd in the background, noble and elegant atmosphere, cinematic lighting, ultra-realistic.
A graceful woman walking on a Parisian street, wearing a beige trench coat and black heels, holding an exquisite leather bag, smiling, soft afternoon sunlight, blurred historical buildings in the background, street style photography, full-body shot, photorealistic.
Inks of various colors spread gracefully in water, mimicking the flowing form of a silk skirt. The colors blend into each other, creating complex, organic patterns. Light from below the water makes the entire image look like a vivid abstract painting, full of movement and poetry.
A woman in a flowing, beige linen maxi dress walks barefoot on a beach at dusk. The sea breeze gently lifts her skirt and hair. The setting sun paints the sky in shades of orange and purple. The scene is tranquil, beautiful, and filled with a sense of nature.
A professional young woman walks down a street in New York, wearing a well-tailored grey wool blazer over a white silk camisole with matching wide-leg trousers. She is wearing delicate gold earrings and carrying a black leather tote bag. Her expression is confident, with a blurred city scene in the background.
a massive steampunk airship with intricate brass gears and pipes, flying slowly over Victorian London at sunset, warm light illuminating the clouds, extremely detailed, matte painting, imaginative, warm color palette
concept art of a magnificent, forgotten underwater city, Atlantis style, giant glowing crystals powering the city, schools of fish and massive sea creatures swimming among the ruins, digital painting, style of Greg Rutkowski, cool color palette, epic, strong lighting and shadows.
professional portrait of a confident female architect in her 30s, sharp short hair, determined and confident gaze, studio setting with a dark gray background, Rembrandt lighting with soft shadows defining her features, hyper-detailed, visible skin pores and texture, catchlight in eyes, shot on Hasselblad X2D 100C

README

Hunyuan Image 3.0

Harness the cutting-edge technology of Hunyuan Image 3.0 to transform your written ideas into compelling visual content. This advanced model ensures visuals that not only align with your narrative but also enhance its emotional and conceptual appeal.

What is Hunyuan Image 3.0?

Hunyuan Image 3.0 is a state-of-the-art text-to-image generation model. By simply providing a written prompt, you can create high-quality images that capture the essence of your story, resonate emotionally, and elevate your creative output.

Why it looks great

  • Prompt-driven generation: translates text descriptions into rich, detailed visuals.
  • Emotional resonance: enhances narrative impact by aligning visuals with tone and mood.
  • Flexible sizing: supports custom width and height up to large resolutions.
  • Style diversity: accommodates multiple visual aesthetics, from realism to artistic styles.
  • Reproducibility: use the seed parameter for consistent, repeatable results.
  • Format choice: export in JPEG and PNG for easy integration.

Limits and Performance

  • Max resolution per job: up to 2048 × 2048 pixels
  • Processing speed: ~5–10 seconds per image (varies by complexity and queue load)
  • Input prompt: supports detailed, multi-line descriptions

Pricing

Every image just $0.03!!!

How to Use

  1. Write a prompt describing the image you want.
  2. Adjust size (width & height).
  3. Set a seed for reproducibility.
  4. Choose output_format.
  5. Submit the job and download the generated image.

Pro tips for best quality

  • Be descriptive in your prompt — include mood, lighting, and style.
  • Portraits with clear attributes (face, pose, background) yield sharper results.
  • Fix the seed if you want consistent outputs across runs.
  • Use custom sizes for tailored content (e.g., vertical posters or wide banners).