bytedance/seedream-4.5 ❓🔢📝🖼️ → 🖼️
About
Seedream 4.5: Upgraded Bytedance image model with stronger spatial understanding and world knowledge
Example Output
Prompt:
"A warm, nostalgic film-style interior of a cozy café, shot on 35mm-inspired digital photography with soft afternoon sunlight filtering through the front windows. Wooden shelves display neatly arranged ceramics, pastries, and coffee beans. Hand-painted signage on the main interior window reads ‘Seedream 4.5’ in clean, classic lettering, similar to boutique branding. A vintage bicycle with a wicker basket is visible outside the entrance, casting soft shadows on the floor. Rich textures, natural light, warm tones, subtle grain, and calm neighborhood-café ambiance."
Output
Performance Metrics
15.19s
Prediction Time
15.20s
Total Time
All Input Parameters
{
"size": "4K",
"width": 2048,
"height": 2048,
"prompt": "A warm, nostalgic film-style interior of a cozy café, shot on 35mm-inspired digital photography with soft afternoon sunlight filtering through the front windows. Wooden shelves display neatly arranged ceramics, pastries, and coffee beans. Hand-painted signage on the main interior window reads ‘Seedream 4.5’ in clean, classic lettering, similar to boutique branding. A vintage bicycle with a wicker basket is visible outside the entrance, casting soft shadows on the floor. Rich textures, natural light, warm tones, subtle grain, and calm neighborhood-café ambiance.",
"max_images": 1,
"image_input": [],
"aspect_ratio": "16:9",
"sequential_image_generation": "disabled"
}
Input Parameters
- size
- Image resolution: 2K (2048px), 4K (4096px), or 'custom' for specific dimensions. Note: 1K resolution is not supported in Seedream 4.5.
- 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 1-14 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 4096x2304 image with aspect ratio 16:9 at 4K resolution Generating... Generated in 14.0sec
Version Details
- Version ID
8356ab00a2acd0f79338ecf1ffa0e32493c6f7cdfc7178b5cfbdb1461202fdc2- Version Created
- December 4, 2025