WaveSpeed.ai
首页/探索/Seedream AI Models/bytedance/seedream-v5.0-lite/edit-sequential
image-to-image

image-to-image

Seedream 4.5 Edit Sequential

bytedance/seedream-v5.0-lite/edit-sequential

Seedream 5.0 Lite Edit Sequential performs multi-image editing while locking character and object identity across shots. It detects main subjects, preserves continuity, and applies controlled edits with up to 4K output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Input

Hint: You can drag and drop a file or click to upload

preview
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, change to a Japanese manga style, bold black ink lines, speed lines behind the motorcycle, a dynamic action panel, and a comic book aesthetic. Second, change into cyberpunk neon style, glowing neon orange and blue lights on the bike and suit, dark futuristic background, rain and reflections, cyberpunk 2077 aesthetic
2 images. First, change to a Japanese manga style, bold black ink lines, speed lines behind the motorcycle, a dynamic action panel, and a comic book aesthetic. Second, change into cyberpunk neon style, glowing neon orange and blue lights on the bike and suit, dark futuristic background, rain and reflections, cyberpunk 2077 aesthetic

您的请求将花费 $0.035 每次运行。

使用 $1 您可以运行此模型大约 28 次。

还有一件事：

示例查看全部

2 images. First, change to a Japanese manga style, bold black ink lines, speed lines behind the motorcycle, a dynamic action panel, and a comic book aesthetic. Second, change into cyberpunk neon style, glowing neon orange and blue lights on the bike and suit, dark futuristic background, rain and reflections, cyberpunk 2077 aesthetic
2 images. First, The same young man sitting at the desk, but the books behind him start glowing with golden magical light, ancient runes floating out of the open book, his eyes wide with surprise, Harry Potter aesthetic, cinematic. Second, The young man back in the library, book closed, looking shaken at a tiny dragon sleeping on the stack of books beside him, warm cozy lighting, magical realism

README

Seedream V5.0 Lite Edit Sequential

Seedream V5.0 Lite Edit Sequential is ByteDance's multi-image editing model designed to apply the same edit across a whole set of images or generate multiple style variations from a single image. It automatically tracks the main subject, keeps identity stable, and generates clean, high-resolution results — ideal for campaigns, product sets, and character line-ups.

Why Choose This?

  • Multi-image subject tracking Detects the main subject across all input images and treats them as the same person or object.

  • Character consistency lock Preserves facial structure, proportions, and overall identity across every edited output.

  • High reference fidelity Maintains lighting, color balance, and key visual details while applying the requested changes.

  • Controlled, repeatable edits One prompt drives a consistent transformation across the entire batch.

  • Multiple variations Generate multiple style variations from a single source image.

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

Parameters

ParameterRequiredDescription
promptYesDescribe the edit and specify how many images to generate
imagesYesSource images to edit (max: 10 images)
sizeNoOutput size (click + to expand options)
max_imagesNoNumber of images to generate (max: 15, default: 2)
enable_base64_outputNoReturn base64 instead of URL (API only)
enable_sync_modeNoWait for result in response (API only)

How to Use

  1. Upload source images — add up to 10 images containing the same main subject or product.
  2. Set max_images first — specify how many edited outputs you want to generate.
  3. Write the edit prompt — describe the shared change and include the number of images in your prompt.
  4. Choose size (optional) — select the target resolution.
  5. Run — submit the job and review the edited series.

Important: Set max_images first, then specify the same number in your prompt!

Example prompt format:

  • max_images = 4
  • Prompt: "I want to generate 4 images. First, transform into Japanese manga style... Second, transform into cyberpunk neon style..."

Pricing

max_imagesTotal Price
1$0.035
2$0.07
4$0.14
8$0.28
15$0.525

Billing Rules

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

Best Use Cases

  • Batch Portrait Editing — Apply a fixed style or look across multiple portraits.
  • Product Series — Create coherent product images that feel like one set.
  • Brand Campaigns — Iterate on the same model or hero product with different styles.
  • Character Design — Generate variations in outfits, moods, or lighting.
  • E-commerce Catalogs — Refresh seasonal updates with consistent styling.
  • Social Media Series — Create visual series where continuity matters.

Pro Tips

  • Use clear, global instructions in the prompt ("add winter outfit and snow ambience") rather than per-image directions.
  • Keep input images reasonably consistent in framing and lighting so the model can lock onto the same subject.
  • Put your cleanest, clearest reference image first — the model relies on it most strongly for identity.
  • Don't generate too many images at once — larger batches may cause instability. Start with 2–4 images.
  • For campaign work, generate at the highest resolution you need once, then downscale for web or social formats.

Notes

  • Both prompt and images are required fields.
  • Maximum reference images: 10
  • Maximum output images per run: 15 (recommended: 2–4 for stability)
  • Always match max_images setting with the number specified in your prompt.
  • Ensure uploaded image URLs are publicly accessible.

Related Models