WaveSpeed.ai
Home/Explore/Dreamina AI Models/bytedance/dreamina-v3.1/text-to-image
text-to-image

text-to-image

ByteDance Dreamina 3.1 Text-To-Image

bytedance/dreamina-v3.1/text-to-image

ByteDance Dreamina V3.1 is a text-to-image model with enhanced aesthetics and style accuracy, producing richer, more polished images. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

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 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 painter working in a sunlit studio, large canvas filled with abstract colors, brushes and paint tubes scattered on the floor, creative atmosphere.

Your request will cost $0.027 per run.

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

One more thing::

ExamplesView all

A painter working in a sunlit studio, large canvas filled with abstract colors, brushes and paint tubes scattered on the floor, creative atmosphere.
An action shot of a male trail runner ascending a mountain ridge path at sunset. He is covered in dirt and sweat, his expression is determined, and his breath is visible in the cool air. The golden sunset light comes from behind, creating a strong rim light on his muscular silhouette. The background is rolling mountains and a spectacular sky.
Wide-angle view of a bustling night market, colorful lanterns hanging above, smoke rising from food stalls, people moving in blurred motion.
A candid portrait of an elderly woman sitting by a window, soft daylight on her face, hands gently holding a teacup, timeless and emotional feel.
A rainy evening in New York, yellow taxis reflecting on wet asphalt, a woman crossing the street with an umbrella, cinematic street photography style.
A young backpacker standing on top of a cliff in Santorini, overlooking whitewashed houses with blue domes, bright Mediterranean sunlight and deep blue sea.
A train passing through snowy mountains, smoke rising from the engine, pine trees covered in snow, cinematic winter travel scene.
A ferris wheel glowing at a seaside carnival, long exposure shot capturing colorful light trails against the dark sky.
A couple sitting on a rooftop under the night sky, city lights glowing below, Milky Way faintly visible above, romantic cinematic mood.

README

ByteDance Dreamina v3.1 Text-to-Image

Generate beautiful, detailed images from text descriptions with ByteDance's latest Dreamina v3.1 model. Featuring flexible custom dimensions, enhanced prompt understanding, and high-fidelity output — perfect for creating professional visuals at an affordable price.

Why It Looks Great

  • Advanced generation: ByteDance's latest v3.1 model delivers improved detail, coherence, and artistic quality.
  • Custom dimensions: Precise control over width and height for any aspect ratio or resolution.
  • High resolution support: Generate images up to 1328×1328 and beyond.
  • Prompt Enhancer: Built-in tool to automatically refine and expand your descriptions.
  • Prompt expansion option: Enable automatic prompt enhancement for richer, more detailed outputs.
  • Reproducible results: Use the seed parameter to recreate exact outputs or explore variations.

Parameters

ParameterRequiredDescription
promptYesText description of the image you want to generate.
sizeNoCustom dimensions with separate width and height controls.
widthNoOutput width in pixels (e.g., 1328).
heightNoOutput height in pixels (e.g., 1328).
seedNoRandom seed for reproducibility. Use -1 for random.
enable_prompt_expansionNoAPI only: Waits for image generation and returns it directly in the response.

How to Use

  1. Write your prompt — describe your image with details about subject, style, lighting, and atmosphere.
  2. Use Prompt Enhancer (optional) — click to automatically enrich your description.
  3. Set dimensions — adjust width and height sliders to your desired resolution and aspect ratio.
  4. Set seed (optional) — use -1 for random, or a specific number to reproduce results.
  5. Run — click the button to generate.
  6. Download — preview and save your image.

Pricing

Flat rate per image generation.

OutputCost
Per image$0.027

Best Use Cases

  • Artistic Scenes — Create atmospheric environments, studios, and creative spaces.
  • Marketing Visuals — Generate custom imagery for campaigns and brand content.
  • Concept Art — Visualize ideas for games, films, and creative projects.
  • Social Media Content — Produce eye-catching visuals optimized for any platform format.
  • Stock Image Alternative — Create unique, royalty-free imagery on demand.

Example Prompts

  • "A painter working in a sunlit studio, large canvas filled with abstract colors, brushes and paint tubes scattered on the floor, creative atmosphere"
  • "Cozy coffee shop corner with vintage furniture, morning light streaming through large windows, steam rising from a ceramic cup"
  • "Futuristic city rooftop garden at golden hour, glass skyscrapers in background, lush green plants contrasting with urban architecture"
  • "Portrait of a jazz musician mid-performance, dramatic stage lighting, saxophone gleaming, smoky club atmosphere"
  • "Serene Japanese zen garden with raked sand patterns, moss-covered stones, soft morning mist, minimalist aesthetic"

Pro Tips for Best Results

  • Include atmosphere and mood — "creative atmosphere", "warm lighting", "dramatic shadows".
  • Describe environmental details — objects, textures, and spatial relationships.
  • Use the Prompt Enhancer to add professional details to simple ideas.
  • Square dimensions (1328×1328) work well for balanced compositions.
  • Adjust dimensions to match your platform: tall for Stories, wide for headers, square for feeds.
  • Keep the seed constant when testing prompt variations to isolate changes.

Notes

  • The enable_prompt_expansion option is only available through the API.
  • Generation time may vary based on resolution and current queue load.
  • Higher resolutions produce more detailed results but may take slightly longer.