← Back to Models

prunaai/z-image-turbo

Turbo image generation model with configurable dimensions and quality settings.

image text-to-image

Pricing

Base: 1 credits per image

Adjustments:

Example Pricing:

Base request: 2 credits
Range: 1 - 4 credits

Input Parameters

Prompt string

Text prompt for image generation

Default: Young Chinese woman in red Hanfu, intricate embroidery. Impeccable makeup, red floral forehead pattern. Elaborate high bun, golden phoenix headdress, red flowers, beads. Holds round folding fan with lady, trees, bird. Neon lightning-bolt lamp (⚡️), bright yellow glow, above extended left palm. Soft-lit outdoor night background, silhouetted tiered pagoda (西安大雁塔), blurred colorful distant lights.

Height integer

Height of the generated image

Default: 1024

Width integer

Width of the generated image

Default: 1024

Num Inference Steps integer

Number of inference steps. This actually results in (num_inference_steps - 1) DiT forwards

Default: 8

Guidance Scale number

Guidance scale. Should be 0 for Turbo models

Default: 0

Seed integer

Random seed. Set for reproducible generation

output_format string

Format of the output images

Default: jpg

Options: png, jpg, webp

Output Quality integer

Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs

Default: 80

Directives

Advanced Keys:
seed guidance_scale num_inference_steps output_format output_quality
Hidden Keys:
Raw JSON
{
    "identifier": "prunaai/z-image-turbo",
    "replicate_version": "prunaai/z-image-turbo:7ea16386290ff5977c7812e66e462d7ec3954d8e007a8cd18ded3e7d41f5d7cf",
    "type": "image",
    "category": "text-to-image",
    "description": "Turbo image generation model with configurable dimensions and quality settings.",
    "pricing": {
        "version": 1,
        "base": {
            "unit": "image",
            "credits": 1
        },
        "adjustments": [
            {
                "type": "resolution_multiplier",
                "base_resolution": 1048576
            }
        ],
        "display": {
            "min_credits": 1,
            "max_credits": 4
        }
    },
    "directives": {
        "advancedKeys": [
            "seed",
            "guidance_scale",
            "num_inference_steps",
            "output_format",
            "output_quality"
        ],
        "hiddenKeys": [],
        "inputTransforms": [],
        "imageArrayKeys": []
    },
    "inputSchema": {
        "type": "object",
        "title": "Input",
        "properties": {
            "prompt": {
                "type": "string",
                "title": "Prompt",
                "default": "Young Chinese woman in red Hanfu, intricate embroidery. Impeccable makeup, red floral forehead pattern. Elaborate high bun, golden phoenix headdress, red flowers, beads. Holds round folding fan with lady, trees, bird. Neon lightning-bolt lamp (\u26a1\ufe0f), bright yellow glow, above extended left palm. Soft-lit outdoor night background, silhouetted tiered pagoda (\u897f\u5b89\u5927\u96c1\u5854), blurred colorful distant lights.",
                "x-order": 0,
                "description": "Text prompt for image generation"
            },
            "height": {
                "type": "integer",
                "title": "Height",
                "default": 1024,
                "maximum": 2048,
                "minimum": 64,
                "x-order": 1,
                "description": "Height of the generated image"
            },
            "width": {
                "type": "integer",
                "title": "Width",
                "default": 1024,
                "maximum": 2048,
                "minimum": 64,
                "x-order": 2,
                "description": "Width of the generated image"
            },
            "num_inference_steps": {
                "type": "integer",
                "title": "Num Inference Steps",
                "default": 8,
                "maximum": 50,
                "minimum": 1,
                "x-order": 3,
                "description": "Number of inference steps. This actually results in (num_inference_steps - 1) DiT forwards"
            },
            "guidance_scale": {
                "type": "number",
                "title": "Guidance Scale",
                "default": 0,
                "maximum": 20,
                "minimum": 0,
                "x-order": 4,
                "description": "Guidance scale. Should be 0 for Turbo models"
            },
            "seed": {
                "type": "integer",
                "title": "Seed",
                "x-order": 5,
                "nullable": true,
                "description": "Random seed. Set for reproducible generation"
            },
            "output_format": {
                "enum": [
                    "png",
                    "jpg",
                    "webp"
                ],
                "type": "string",
                "title": "output_format",
                "description": "Format of the output images",
                "default": "jpg",
                "x-order": 6
            },
            "output_quality": {
                "type": "integer",
                "title": "Output Quality",
                "default": 80,
                "maximum": 100,
                "minimum": 0,
                "x-order": 7,
                "description": "Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs"
            }
        }
    },
    "outputSchema": {
        "type": "string",
        "title": "Output",
        "format": "uri"
    }
}