Seedream 5.0 Lite
Vendor: ByteDance
Image
Artistic style with excellent Chinese text rendering
- Typical latency
- 5-15s
- Reference inputs
- Up to 10
- toolId
- seedream-5
Input modes
text-to-imageimage-to-image
Parameters
| Parameter | Type | Default | Values | Notes |
|---|---|---|---|---|
| aspect_ratio | select | 1:1 | 1:1 | 4:3 | 3:4 | 16:9 | 9:16 | Choose a fixed frame shape and keep it across a series. |
| resolution | select | 2K | 2K | 3K | Choose 2K for everyday images or 3K for more detail. |
| num_images | select | 1 | 1 | 2 | 3 | 4 | How many variations to generate in one run. More images cost more; re-quote after changing. |
| enable_safety_checker | toggle | true | — | NSFW content filter |
Pricing
Pricing will be published shortly — contact us for early access rates
Prices last updated: —
API example
POST /v1/generations — seedream-5
curl -X POST https://api.mukelabs.com/v1/generations \
-H "Authorization: Bearer $MUKE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"toolId": "seedream-5",
"inputMode": "text-to-image",
"prompt": "your prompt here",
"params": { "aspect_ratio": "1:1" },
"references": [],
"idempotencyKey": "a-unique-key-per-task",
"subjectId": "your-user-id"
}'FAQ
How do I call Seedream 5.0 Lite on Muke Labs?
Submit POST /v1/generations with toolId "seedream-5" and one of its input modes (text-to-image, image-to-image), then poll GET /v1/generations/{jobId} for the result.
What does Seedream 5.0 Lite cost?
Public pricing for this model is being finalized — contact us for early access rates. All tasks are billed from your prepaid USD balance and failed tasks refund automatically.
What happens if a task fails?
The job returns status "failed" with a typed error code, and its charge is returned to your balance automatically.
Where do I get an API key?
Create one in the developer portal (https://portal.muke.name), then send it as a Bearer token on every request.
Related models
Video
Seedance 2.0 Fast
ByteDance
Faster video mode for previewing movement and multi-reference ideas
text-to-videoimage-to-videoomni-reference
Video
Seedance 2.0 Standard
ByteDance
Higher-quality video mode for movement and multi-reference work
text-to-videoimage-to-videoomni-reference
Video
Seedance 2.5
ByteDance
Native 30-second clips with multi-reference control
text-to-videoimage-to-videoomni-reference
Image
Seedream 5.0 Pro
ByteDance
High-fidelity final images with precise composition and subject consistency
text-to-imageimage-to-image