Home/Explore/Seedance Video Models/bytedance/seedream-v3.1

text-to-image

bytedance/seedream-v3.1

ByteDance Seedream V3.1 is a text-to-image model that is sourced from the same technology as Seedream, and focuses on upgrading the visual effects of the generated images. This version has made significant improvements in terms of picture aesthetics, style accuracy, and richness of details, while also retaining the ability to respond to text inputs.

Doc
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.
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.

Idle

A smiling young woman in a sunlit field, wearing a flowing yellow dress, realistic lighting, bright colors, ultra-detailed face, high-resolution, photo-realistic

Your request will cost $0.027 per run.

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

One more thing:

ExamplesView all

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 write boy blowing bubbles in the park on a sunny afternoon, vivid colors, cinematic composition, sharp focus, realistic skin textures, shallow depth of field
A group of four women are seated around a wooden picnic table outdoors at a backyard gathering. The woman in the foreground, light-skinned and young adult, has shoulder-length light brown hair and a friendly, smiling expression. She's wearing a white, sleeveless top with small, pearl-like embellishments on the shoulders.  The background shows several people in light-colored clothing, and a long wooden table with wine bottles, glasses, candles, and food on it. The setting is a backyard at twilight, with trees and a string of outdoor lights creating a warm ambiance.  A large white paper lantern hangs above the gathering. The composition is casual, focusing on the smiling woman seated at the table.  The perspective is from slightly above and a bit to the left of the woman's position. The lighting is soft, warm, and ambient, highlighting the faces and creating a welcoming atmosphere.  Colors are muted and natural tones with pops of light from the candles and lights.  The overall style is casual and social, evoking a friendly backyard dinner party.
A classic 1980s-style school portrait of a teenage boy with feathered hair, denim jacket, and a pastel laser background. “Seedream 3.1: Back to the Future of Imaging” is printed in retro-styled Chinese and English text in the bottom right corner. Style: nostalgic realism, retro photography, humor, bilingual poster.
A professional sports photograph, a female boxer in the ring, dynamic action shot, sweat dripping from her face, intense and determined expression, sharp focus on her face and gloves, dramatic ring lighting, motion blur in the background, high contrast, vibrant colors, hyper-realistic, 8k, by Sports Illustrated photographers
A hyper-realistic photograph of a female street artist, paint on her face and clothes, joyfully performing on a vibrant city street, crowd blurred in the background, late afternoon sunlight, sharp focus on her energetic expression and colorful art supplies, bokeh effect, emotional, 4k, by a National Geographic photographer
A fair-skinned European girl with blond hair and a straw hat is looking at the camera. She is in a sunny meadow with a blurred background of flowers and grass. A genuine, bright smile slowly forms on her face. Hyper-realistic, soft, bright, 4K, detailed hair strands under sunlight, freckles and skin texture, warm color tones, shallow depth of field. A frontal close-up shot with a slow dolly zoom out.
A young woman with clear eyes and subtle freckles is looking at the camera. The background is a foggy lakeside at dawn, with soft morning sunlight filtering through the mist, illuminating her hair and shoulders. She squints slightly, enjoying the sun with a peaceful smile. Hyper-realistic, dreamy, soft lighting, 8K, highly detailed, realistic skin texture with subsurface scattering, dynamic hair physics, god rays. A static frontal close-up shot.
A young woman with her eyes closed, her face looking soft in the sunlight. The setting is a warm room, with afternoon sun casting dappled light through a window blind onto her face. Her breathing is gentle and subtle, her eyelashes occasionally twitch, and a hint of a smile plays on her lips. Hyper-realistic, serene, soft lighting, 8K, highly detailed skin texture and facial hair, dynamic sun dappling, depth of field. A static frontal close-up shot.

README

ByteDance Seedream V3.1

ByteDance Seedream V3.1 is a text-to-image model that is sourced from the same technology as Seedream, and focuses on upgrading the visual effects of the generated images. This version has made significant improvements in terms of picture aesthetics, style accuracy, and richness of details, while also retaining the ability to respond to text inputs.

Key Features

  • High-quality image generation
  • Photorealistic output
  • Fast synchronous inference
  • Stable and reliable

Input Requirements

  • Text prompt describing the desired image
  • Maximum prompt length: 100 characters
  • Supports both Chinese and English prompts

Output

  • High-quality images with flexible resolution (512~2048)
  • URL format for easy access
  • Usage statistics included

Use Cases

  • Digital art creation
  • Content generation
  • Visual design
  • Creative inspiration

Limitations

  • Supported image sizes: 512~2048 pixels
  • Single image generation per request
  • Text-to-image only (no image-to-image or inpainting)

Out-of-Scope Use

This model should not be used for:

  • Generating harmful or misleading content
  • Creating copyrighted material without permission
  • Any illegal or unethical purposes