WaveSpeed.ai
DashboardExploreInspiration
Home/Explore/Dreamina AI Models/bytedance/dreamina-v3.0/text-to-image

text-to-image

bytedance/dreamina-v3.0/text-to-image

ByteDance Dreamina V3.0 Text-to-Image is a text-to-image model that is sourced from the same technology as Dreamina, 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 little boy playing with a red toy airplane in a sunny backyard, wearing a striped T-shirt and denim shorts, laughter frozen in the moment, golden-hour lighting with warm tones.

Your request will cost $0.027 per run.

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

One more thing:

ExamplesView all

A little boy playing with a red toy airplane in a sunny backyard, wearing a striped T-shirt and denim shorts, laughter frozen in the moment, golden-hour lighting with warm tones.
An Art Deco poster illustration of a fantastical skyscraper at night, reaching into the clouds. The building features strong geometric shapes and a symmetrical, stepped-back structure. The sky is a deep indigo blue, adorned with stylized stars. Bold golden lines define the building's contours and the light from its windows, creating a sense of luxury, futurism, and the Jazz Age.
Candid street photograph. A young woman in a stylish trench coat glances back over her shoulder while waiting at the busy Shibuya Crossing in Tokyo. Her expression is calm. The background is a motion blur of the crowd on the crosswalk and vibrant billboards. Documentary style with noticeable film grain.
An elderly couple sitting on a wooden bench facing the sea, holding hands, both wearing light sweaters, the horizon glowing with the colors of sunset, peaceful and heartwarming atmosphere.
A young man lifting weights in a modern gym, sweat dripping down his forehead, wearing a black tank top and gloves, sunlight shining through the large glass windows, realistic sports photography style..
A teenage girl practicing ballet in a rehearsal studio, wearing a white leotard and soft pink ballet shoes, standing in front of a mirror with graceful posture, wooden floor reflecting warm light.
A young man cooking dinner in a small apartment kitchen, steam rising from the pan, warm light from overhead lamps, casual and intimate atmosphere.
A family of four having breakfast together, parents reading newspapers, kids laughing while eating cereal, warm morning sunlight filling the dining room.
Two coworkers chatting casually in the office break room, holding coffee mugs, bulletin board with colorful notes behind them.
A group of friends sitting around a campfire at night, roasting marshmallows, laughter and storytelling under a starry sky.

README

ByteDance Dreamina V3.0 Text-to-Image

ByteDance Dreamina V3.0 Text-to-Image is a text-to-image model that is sourced from the same technology as Dreamina, 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