WaveSpeed.ai
Home/Explore/Seedream AI Models/bytedance/seedream-v3
text-to-image

text-to-image

Seedream V3 Text-To-Image

bytedance/seedream-v3

ByteDance Seedream V3 is a state-of-the-art text-to-image model that creates photorealistic, high-detail images with artistic flair. 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.
If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API.

Idle

A young write girl with curly hair eating ice cream, colorful city background, realistic lighting, street-style photography look, lifelike details

Your request will cost $0.027 per run.

For $1 you can run this model approximately 37 times.

One more thing::

ExamplesView all

A young write girl with curly hair eating ice cream, colorful city background, realistic lighting, street-style photography look, lifelike details
A smiling young woman in a sunlit field, wearing a flowing yellow dress, realistic lighting, bright colors, ultra-detailed face, high-resolution, photo-realistic
A man in a hooded jacket climbs a rugged mountain path at dawn, breath misting in the cold air. The rising sun casts long shadows over snow-dusted peaks. Wide-angle shot reveals vast alpine scenery, followed by close-up of his determined face. Wind rustles his backpack straps. Sound of crunching snow underfoot and distant eagle cries. Epic orchestral undertone, dynamic movement through drone tracking shots.
A fluffy cartoon bunny exploring a magical forest, oversized mushrooms and glowing plants, smooth camera motion, Pixar-style lighting
A glowing jellyfish floating through an endless galaxy, stars twinkling in the background, camera rotates gently around, ethereal ambiance, surreal beauty
An intense, dynamic close-up of a muscular man in his 30s, his face glistening with sweat and showing intense concentration, performing a heavy deadlift in a gritty gym. The video shows his muscles tensing and the weight lifting off the ground. The lighting is dramatic and high-contrast, with spotlights creating deep shadows. The atmosphere is raw and powerful. Documentary style, super slow-motion, sharp focus on the man's expression, professional video quality.
a realistic and beautiful close-up of a young woman with long, curly brown hair. she is smiling happily, with a look of surprise on her face. she is standing in a lush green garden with flowers in the background. natural lighting, sharp focus on her face, realistic, cinematic, dynamic motion. shot on a Arri Alexa mini LF, 8K.
Inside a classic, well-stocked university library, a group of four or five students are seated around a large wooden table, piled high with books and laptops. They are engaged in an intense academic discussion. One student is quickly jotting down notes, another is flipping through a heavy, hardcover book, and a third is gesticulating to explain complex concepts. Their expressions are focused and full of intellectual curiosity.
A smiling potter is shaping a clay pot on a potter's wheel in her studio. Her hands, covered in clay, gently and skillfully mold the spinning lump of clay, and the pot's form takes shape under her fingertips. The studio is filled with sunlight, and shelves are lined with pottery of various shapes and sizes, creating a peaceful and creative atmosphere.

README

Seedream v3 — bytedance/seedream-v3

Seedream v3 is a high-quality text-to-image model built for fast, photorealistic generation with strong composition and detail. Write a clear prompt describing subject, scene, lighting, and style, and it produces clean, lifelike images suitable for marketing creatives, portraits, lifestyle photography concepts, and general visual production.

Key capabilities

  • Text-to-image generation with strong realism and fine detail
  • Reliable composition across custom sizes (set width/height directly)
  • Good lighting and material rendering for lifelike results
  • Efficient for rapid iteration with controllable randomness via seed

Use cases

  • Lifestyle and street-style photography concepts
  • Portrait generation with realistic skin, hair, and fabric detail
  • Marketing creatives and ad-style key visuals
  • Product and brand imagery with controlled lighting
  • Rapid ideation for concepts, thumbnails, and mood boards

Pricing

OutputPrice
Per image$0.027

Parameters

  • prompt (required): Text description of what to generate
  • width / height: Output size
  • guidance_scale: Prompt adherence strength (higher = stricter; too high may reduce naturalness)
  • seed: Random seed (-1 for random; fixed value for reproducible results)

Prompting guide

A stable prompt structure:

  • Subject: who/what is in frame
  • Action: what they are doing
  • Scene: location + background details
  • Lighting: time of day, key light, contrast
  • Style: photorealistic, street photography, cinematic, etc.

Template: A [subject] [action] in [scene], [lighting], [camera/framing], [style], high detail.

Example prompts

  • A young girl with curly hair eating ice cream, colorful city background, realistic lighting, street-style photography look, lifelike details, shallow depth of field.
  • Close-up portrait of a man in soft window light, natural skin texture, 85mm lens look, subtle film grain, photorealistic.
  • Studio product photo of a minimalist sneaker on a clean backdrop, softbox lighting, crisp shadow, premium advertising style.