bytedance/seedream-4 ❓🔢📝🖼️ → 🖼️
About
Unified text-to-image generation and precise single-sentence editing at up to 4K resolution

Example Output
Prompt:
"a photo of a store front called "Seedream 4", it sells books, a poster in the window says "Seedream 4 now on Replicate""
Output

Performance Metrics
14.36s
Prediction Time
14.37s
Total Time
All Input Parameters
{ "size": "2K", "width": 2048, "height": 2048, "prompt": "a photo of a store front called \"Seedream 4\", it sells books, a poster in the window says \"Seedream 4 now on Replicate\"", "max_images": 1, "image_input": [], "aspect_ratio": "4:3", "sequential_image_generation": "disabled" }
Input Parameters
- size
- Image resolution: 1K (1024px), 2K (2048px), 4K (4096px), or 'custom' for specific dimensions.
- width
- Custom image width (only used when size='custom'). Range: 1024-4096 pixels.
- height
- Custom image height (only used when size='custom'). Range: 1024-4096 pixels.
- prompt (required)
- Text prompt for image generation
- max_images
- Maximum number of images to generate when sequential_image_generation='auto'. Range: 1-15. Total images (input + generated) cannot exceed 15.
- image_input
- Input image(s) for image-to-image generation. List of 1-10 images for single or multi-reference generation.
- aspect_ratio
- Image aspect ratio. Only used when size is not 'custom'. Use 'match_input_image' to automatically match the input image's aspect ratio.
- sequential_image_generation
- Group image generation mode. 'disabled' generates a single image. 'auto' lets the model decide whether to generate multiple related images (e.g., story scenes, character variations).
Output Schema
Output
Example Execution Logs
Generating 2304x1728 image with aspect ratio 4:3 at 2K resolution Generating... Generated in 14.1sec
Version Details
- Version ID
054cd8c667f535616fd66710ce20c8949bf64ac3d9a3459e338f026424be8bec
- Version Created
- October 1, 2025