Bytedance Seedream V4.5
Playground
Try it on WavespeedAI!Seedream 4.5 by ByteDance is a state-of-the-art text-to-image model with all-round improvements through model scaling. Features enhanced typography, clear text rendering for posters and brand visuals, superior prompt adherence, and up to 4K resolution. Ready-to-use REST API with best performance and no coldstarts.
Features
bytedance/seedream-v4.5 (Text-to-Image)
Seedream 4.5 is ByteDance’s latest image generation model, achieving all-round improvements through comprehensive model scaling. It excels at typography, poster design, and brand visual creation with superior prompt adherence and aesthetic quality.
Model Highlights
- Enhanced Typography: Clear and readable text rendering, ideal for posters, logos, and brand visuals
- Designer-Level Composition: Advanced poster layout capabilities with professional typographic hierarchy
- Superior Prompt Adherence: Improved alignment between input descriptions and generated outputs
- High Resolution: Supports up to 4K (4096×4096) resolution output
- Aesthetic Excellence: Significant improvements in visual quality benchmarked on MagicBench
Use Cases
- Poster and banner design with embedded text
- Brand visual and logo creation
- E-commerce product imagery
- Social media content with typography
- Marketing campaign visuals
Price
Only $0.04 per image!
How to Use
- Enter your prompt: Describe the subject, layout, text placement (title/subtitle), and style
- Set size: Choose width/height up to 4096×4096
- Run: Click Run to generate your image
Recommended Resolutions
| Aspect Ratio | Resolution (W×H) |
|---|---|
| 1:1 | 1024 × 1024 |
| 3:2 | 1216 × 832 |
| 4:3 | 1152 × 896 |
| 16:9 | 1344 × 768 |
| 2K (1:1) | 1448 × 1448 |
| 4K (1:1) | 4096 × 4096 |
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/bytedance/seedream-v4.5" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"size": "2048*2048",
"enable_base64_output": false,
"enable_sync_mode": false
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | The positive prompt for the generation. | |
| size | string | No | 2048*2048 | 1440 ~ 4096 per dimension | Specify the width and height pixel values of the generated image.Total pixel value range: [2560*1440, 4096*4096] |
| enable_base64_output | boolean | No | false | - | If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API. |
| enable_sync_mode | boolean | No | false | - | 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. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |