KovAPIKovAPI
AnnouncementsAll updates →
NewNew: Seedream 5.5 (Beta), ByteDance's newest image model, from 4 credits an image NoticeSeedance 2.5 Special: choose 11 or 13 seconds instead of 12 NoticeSeedance 2.5 Special accepts reference video again
简体中文English ✓Español한국어日本語Русский
Log in Get API Key
Image ● Operational Service status →

Seedream 5.0 Pro

⧉
seedream-5.0-pro

Seedream 5.0 Pro is the flagship image model of ByteDance's Seedream 5.0 series. One model handles text-to-image and editing: an edit keeps the original composition and changes only what the prompt asks for, and up to 8 reference images can be fused into one picture (people, products, scenes). In-image text, Chinese included, comes out legible. 1K / 2K and 8 aspect ratios (21:9 included); you get the original JPEG with its C2PA content credential, never cropped or resized. OpenAI-compatible images API, billed per image, failures refunded in full.

Text-to-imageImage editingMulti-image fusion1K/2KOriginal output
Get API Key → API Docs

Live Test · Playground

Try out Seedream 5.0 Pro right here (available after login).

Model Type

Input

Image

Output

image
Results will appear here after running.
🕑 Generated images and videos are kept for 7 days and then deleted automatically. Download anything you want to keep.

About Seedream 5.0 Pro

Seedream 5.0 Pro is the flagship image model of ByteDance's Seedream 5.0 series, one model for text-to-image and editing. An edit keeps the original composition and changes only what you ask for; up to 8 reference images can be fused into one picture. In-image text, Chinese included, comes out legible. 1K / 2K in 8 ratios; you get the original JPEG with its C2PA content credential, never cropped or resized. Billed per image, failures refunded in full.

Use cases

Posters and text layouts

Headlines, price tags and menus come out legible, Chinese included; 21:9 suits site banners.

Edits and product shots

Swap the background, recolour, rewrite a sign: the composition and subject stay put. Good for many versions of one product shot.

Multi-image fusion

Put people, products and places (up to 8 references) into one picture; say in the prompt what each image is for, in order.

How to choose

Pick it for photographic texture, clean in-image text, or edits that leave the composition alone; for 4K, transparent backgrounds or GIF use Nano Banana or GPT Image 2.6.

FAQ

Which ratios and resolutions?
1K and 2K, in 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3 and 21:9. You get that ratio's native size (2K 16:9 is 2560×1440), never cropped or resized; any other ratio returns 400 at submit and nothing is charged.
How many reference images?
Up to 8: one in image, several in images, as an image URL, a data: URI or base64. With several, say in the prompt what each one is for, in order.
What format comes back?
The original JPEG with its C2PA content credential. PNG, transparent backgrounds and layer splitting are not offered yet, and each request makes one image.
How long, and what if it fails?
Usually 40–90 seconds; 2K and several references take a little longer. A failed render or a content-check rejection costs nothing: the hold is released in full and you can resubmit as is.

Related Models

Explore other models you can integrate.

View all →
Seedream 5.5 Image

Seedream 5.5

seedream-5.5

ByteDance's newest Seedream image model · text-to-image and multi-image editing

$0.020/img and up View →
Nano Banana 2.1 Image

Nano Banana 2.1

nano-banana-2.1

The upgraded Nano Banana 2, with better images and text

$0.015/img and up View →
GPT Image 2.6 Flare Image

GPT Image 2.6 Flare

gpt-image-2.6-flare

OpenAI's November 2026 image model · clean and smooth

$0.015/img and up View →
Nano Banana Pro Image

Nano Banana Pro

nano-banana-pro

Flagship text-to-image / image-to-image model

$0.020/img and up View →
Grok Imagine Image Image

Grok Imagine Image

grok-imagine-image

xAI's image model · renders in seconds

$0.005/img and up View →