← Back to Models

bytedance/seedream-4.5

Seedream 4.5 text-to-image generation model. A new-generation image creation model by ByteDance that integrates image generation capabilities.

image text-to-image

Pricing

Base: 3 credits per image

Adjustments:

image_size multiplier:
auto_2K: 1x
auto_4K: 2x
square_hd: 0.75x
square: 0.75x
portrait_4_3: 1x
portrait_16_9: 1x
landscape_4_3: 1x
landscape_16_9: 1x
custom: 1.5x

Example Pricing:

Base request: 4 credits
Range: 5 - 9 credits

Input Parameters

Prompt required string

The text prompt used to generate the image

Image Size string

The size of the generated image. Use predefined aspect ratios or 'custom' for specific dimensions. Width and height must be between 1920 and 4096, or total pixels between 2560*1440 and 4096*4096.

Default: auto_2K

Options: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, auto_2K, auto_4K, custom

Width integer

Custom image width (only used when image_size='custom'). Range: 1920-4096 pixels.

Default: 2048

Height integer

Custom image height (only used when image_size='custom'). Range: 1920-4096 pixels.

Default: 2048

Number of Images integer

Number of separate model generations to be run with the prompt.

Default: 1

Max Images integer

If set to a number greater than one, enables multi-image generation. The model will potentially return up to max_images images every generation, and in total, num_images generations will be carried out.

Default: 1

Seed integer

Random seed to control the stochasticity of image generation.

Sync Mode boolean

If true, the media will be returned as a data URI and the output data won't be available in the request history.

Default:

Enable Safety Checker boolean

If set to true, the safety checker will be enabled.

Default: 1

Directives

Advanced Keys:
num_images max_images seed sync_mode enable_safety_checker width height
Hidden Keys:
Raw JSON
{
    "identifier": "bytedance/seedream-4.5",
    "fal_endpoint": "fal-ai/bytedance/seedream/v4.5/text-to-image",
    "type": "image",
    "updated_at": "2025-10-08T00:00:00Z",
    "category": "text-to-image",
    "description": "Seedream 4.5 text-to-image generation model. A new-generation image creation model by ByteDance that integrates image generation capabilities.",
    "pricing": {
        "version": 1,
        "base": {
            "unit": "image",
            "credits": 3
        },
        "adjustments": [
            {
                "type": "multiplier_map",
                "key": "image_size",
                "map": {
                    "auto_2K": 1,
                    "auto_4K": 2,
                    "square_hd": 0.75,
                    "square": 0.75,
                    "portrait_4_3": 1,
                    "portrait_16_9": 1,
                    "landscape_4_3": 1,
                    "landscape_16_9": 1,
                    "custom": 1.5
                },
                "default": 1
            }
        ],
        "display": {
            "min_credits": 5,
            "max_credits": 9
        }
    },
    "directives": {
        "advancedKeys": [
            "num_images",
            "max_images",
            "seed",
            "sync_mode",
            "enable_safety_checker",
            "width",
            "height"
        ],
        "hiddenKeys": [],
        "inputTransforms": [],
        "imageArrayKeys": []
    },
    "fal": {
        "input_transforms": [
            {
                "type": "image_size_custom_object",
                "key": "image_size",
                "width_key": "width",
                "height_key": "height",
                "drop_width_height": true
            }
        ]
    },
    "inputSchema": {
        "type": "object",
        "title": "Input",
        "required": [
            "prompt"
        ],
        "properties": {
            "prompt": {
                "type": "string",
                "title": "Prompt",
                "x-order": 0,
                "description": "The text prompt used to generate the image"
            },
            "image_size": {
                "enum": [
                    "square_hd",
                    "square",
                    "portrait_4_3",
                    "portrait_16_9",
                    "landscape_4_3",
                    "landscape_16_9",
                    "auto_2K",
                    "auto_4K",
                    "custom"
                ],
                "type": "string",
                "title": "Image Size",
                "description": "The size of the generated image. Use predefined aspect ratios or 'custom' for specific dimensions. Width and height must be between 1920 and 4096, or total pixels between 2560*1440 and 4096*4096.",
                "default": "auto_2K",
                "x-order": 1
            },
            "width": {
                "type": "integer",
                "title": "Width",
                "default": 2048,
                "maximum": 4096,
                "minimum": 1920,
                "x-order": 2,
                "description": "Custom image width (only used when image_size='custom'). Range: 1920-4096 pixels."
            },
            "height": {
                "type": "integer",
                "title": "Height",
                "default": 2048,
                "maximum": 4096,
                "minimum": 1920,
                "x-order": 3,
                "description": "Custom image height (only used when image_size='custom'). Range: 1920-4096 pixels."
            },
            "num_images": {
                "type": "integer",
                "title": "Number of Images",
                "default": 1,
                "minimum": 1,
                "x-order": 4,
                "description": "Number of separate model generations to be run with the prompt."
            },
            "max_images": {
                "type": "integer",
                "title": "Max Images",
                "default": 1,
                "minimum": 1,
                "x-order": 5,
                "description": "If set to a number greater than one, enables multi-image generation. The model will potentially return up to max_images images every generation, and in total, num_images generations will be carried out."
            },
            "seed": {
                "type": "integer",
                "title": "Seed",
                "x-order": 6,
                "description": "Random seed to control the stochasticity of image generation."
            },
            "sync_mode": {
                "type": "boolean",
                "title": "Sync Mode",
                "default": false,
                "x-order": 7,
                "description": "If true, the media will be returned as a data URI and the output data won't be available in the request history."
            },
            "enable_safety_checker": {
                "type": "boolean",
                "title": "Enable Safety Checker",
                "default": true,
                "x-order": 8,
                "description": "If set to true, the safety checker will be enabled."
            }
        }
    },
    "outputSchema": {
        "type": "object",
        "title": "Output",
        "properties": {
            "images": {
                "type": "array",
                "items": {
                    "type": "object",
                    "properties": {
                        "url": {
                            "type": "string",
                            "format": "uri"
                        },
                        "content_type": {
                            "type": "string"
                        },
                        "file_name": {
                            "type": "string"
                        },
                        "file_size": {
                            "type": "integer"
                        },
                        "width": {
                            "type": "integer"
                        },
                        "height": {
                            "type": "integer"
                        }
                    }
                }
            },
            "seed": {
                "type": "integer"
            }
        }
    }
}