WaveSpeed.ai
Accueil/Explorer/Seedream AI Models/bytedance/seedream-v5.0-lite/sequential
text-to-image

text-to-image

Seedream 4.5 Sequential

bytedance/seedream-v5.0-lite/sequential

Seedream 5.0 Lite Sequential generates multi-image sets with consistent characters and objects, unifying palette, lighting, and style across all outputs. Supports up to 4K results for campaigns, storyboards, and product lines. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Input
width
height
2048 × 2048 px
Range: 1440 - 4096
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

2 images. First, a young princess in a torn royal dress sneaking through a dark castle corridor at night, holding a stolen map, torchlight flickering on stone walls, fear in her eyes, fantasy art, cinematic. Second, the princess and the cloaked figure riding together on horseback at dawn, the castle burning, she looks one last time with tears in her eyes, epic wide shot, golden hour, fantasy art, cinematic
2 images. First, a young princess in a torn royal dress sneaking through a dark castle corridor at night, holding a stolen map, torchlight flickering on stone walls, fear in her eyes, fantasy art, cinematic. Second, the princess and the cloaked figure riding together on horseback at dawn, the castle burning, she looks one last time with tears in her eyes, epic wide shot, golden hour, fantasy art, cinematic

Votre requête coûtera $0.035 par exécution.

Pour $1 vous pouvez exécuter ce modèle environ 28 fois.

Encore une chose :

ExemplesTout voir

2 images. First, a young princess in a torn royal dress sneaking through a dark castle corridor at night, holding a stolen map, torchlight flickering on stone walls, fear in her eyes, fantasy art, cinematic. Second, the princess and the cloaked figure riding together on horseback at dawn, the castle burning, she looks one last time with tears in her eyes, epic wide shot, golden hour, fantasy art, cinematic
2 images. First, A woman alone in a cozy apartment at night, reading a book on the couch, warm lamp light, rain on the window, peaceful and quiet atmosphere, thriller movie still, photorealistic. Second, The same woman freezing mid-page, eyes wide, staring at the front door where a shadow of a person is visible through the frosted glass, tension building, thriller movie still, photorealistic

README

Seedream V5.0 Lite Sequential

Seedream V5.0 Lite Sequential is ByteDance's multi-image text-to-image model designed to generate a series of coherent images from a single prompt. Describe multiple scenes in one prompt — the model generates a consistent visual sequence with stable character identity and style continuity, perfect for storytelling, storyboards, and visual narratives.

Why Choose This?

  • Multi-image generation Generate multiple related images in a single run with consistent style and characters.

  • Character consistency Maintains character identity, proportions, and visual style across the entire sequence.

  • Narrative storytelling Create visual stories by describing multiple scenes in one prompt.

  • High resolution support Custom width and height from 1440 to 4096 pixels.

  • Flexible aspect ratios Multiple presets including 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, and 2:3.

  • Prompt Enhancer Built-in tool to automatically improve your descriptions.

Parameters

ParameterRequiredDescription
promptYesDescribe the images to generate (include count in prompt)
sizeNoAspect ratio preset: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3
widthNoCustom width in pixels (range: 1440–4096)
heightNoCustom height in pixels (range: 1440–4096)
max_imagesNoNumber of images to generate (default: 2)

How to Use

  1. Set max_images first — specify how many images you want to generate.
  2. Write your prompt — describe each image in sequence, starting with the count.
  3. Choose size — select a preset or customize width/height.
  4. Use Prompt Enhancer (optional) — click to automatically refine your description.
  5. Run — submit and download your image sequence.

Important: Specify the number of images in your prompt to match max_images!

Example prompt format:

  • max_images = 2
  • Prompt: "2 images. First, a young princess in a torn royal dress sneaking through a dark castle corridor... Second, the princess and the cloaked figure riding together on horseback at dawn..."

Pricing

max_imagesTotal Price
1$0.035
2$0.07
4$0.14
8$0.28

Billing Rules

  • Base price: $0.035 per output image
  • Total cost = $0.035 × max_images

Best Use Cases

  • Visual Storytelling — Create sequential narratives with consistent characters.
  • Storyboards — Generate scene-by-scene illustrations for projects.
  • Comic & Manga — Produce multi-panel visual sequences.
  • Character Series — Generate variations of the same character in different scenarios.
  • Marketing Campaigns — Create cohesive visual series for brand storytelling.
  • Social Media Content — Produce carousel posts with narrative continuity.

Pro Tips

  • Always specify the number of images at the start of your prompt (e.g., "2 images. First... Second...").
  • Use "First," "Second," "Third," etc. to clearly separate each image description.
  • Include consistent character descriptions across scenes for better identity preservation.
  • Keep style references consistent throughout the prompt (e.g., "fantasy art, cinematic" for all scenes).
  • Start with fewer images (2–4) to test consistency before generating larger sequences.

Notes

  • Prompt is the only required field.
  • Always match max_images setting with the number specified in your prompt.
  • Resolution range: 1440–4096 pixels for both width and height.
  • Ensure your prompts comply with content guidelines.

Related Models