generate_image_variants
Create diverse image variations from a single prompt by adjusting aspect ratio, output format, and quality. Customize with optional prompt modifiers for unique results.
Instructions
Generate multiple variants of the same image from a single prompt
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| aspect_ratio | No | Aspect ratio for the generated image | 1:1 |
| disable_safety_checker | No | Disable safety checker for generated images. | |
| go_fast | No | Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16 | |
| megapixels | No | Approximate number of megapixels for generated image | 1 |
| num_inference_steps | No | Number of denoising steps. 4 is recommended, and lower number of steps produce lower quality outputs, faster. | |
| num_variants | No | Number of image variants to generate (2-10) | |
| output_format | No | Format of the output images | webp |
| output_quality | No | Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs | |
| prompt | Yes | Text description for the image to generate variants of | |
| prompt_variations | No | Optional list of prompt modifiers to apply to variants (e.g., ['in watercolor style', 'in oil painting style']). If provided, these will be used instead of random seeds. | |
| seed | No | Base random seed. Each variant will use seed+variant_index for reproducibility | |
| support_image_mcp_response_type | No | Support image MCP response type on client side | |
| variation_mode | No | How to apply prompt variations: 'append' adds to the base prompt, 'replace' uses variations as standalone prompts | append |
Input Schema (JSON Schema)
{
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"aspect_ratio": {
"default": "1:1",
"description": "Aspect ratio for the generated image",
"enum": [
"1:1",
"16:9",
"21:9",
"3:2",
"2:3",
"4:5",
"5:4",
"3:4",
"4:3",
"9:16",
"9:21"
],
"type": "string"
},
"disable_safety_checker": {
"default": false,
"description": "Disable safety checker for generated images.",
"type": "boolean"
},
"go_fast": {
"default": true,
"description": "Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16",
"type": "boolean"
},
"megapixels": {
"default": "1",
"description": "Approximate number of megapixels for generated image",
"enum": [
"1",
"0.25"
],
"type": "string"
},
"num_inference_steps": {
"default": 4,
"description": "Number of denoising steps. 4 is recommended, and lower number of steps produce lower quality outputs, faster.",
"maximum": 4,
"minimum": 1,
"type": "integer"
},
"num_variants": {
"default": 4,
"description": "Number of image variants to generate (2-10)",
"maximum": 10,
"minimum": 2,
"type": "integer"
},
"output_format": {
"default": "webp",
"description": "Format of the output images",
"enum": [
"webp",
"jpg",
"png"
],
"type": "string"
},
"output_quality": {
"default": 80,
"description": "Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs",
"maximum": 100,
"minimum": 0,
"type": "integer"
},
"prompt": {
"description": "Text description for the image to generate variants of",
"minLength": 1,
"type": "string"
},
"prompt_variations": {
"description": "Optional list of prompt modifiers to apply to variants (e.g., ['in watercolor style', 'in oil painting style']). If provided, these will be used instead of random seeds.",
"items": {
"type": "string"
},
"type": "array"
},
"seed": {
"description": "Base random seed. Each variant will use seed+variant_index for reproducibility",
"type": "integer"
},
"support_image_mcp_response_type": {
"default": true,
"description": "Support image MCP response type on client side",
"type": "boolean"
},
"variation_mode": {
"default": "append",
"description": "How to apply prompt variations: 'append' adds to the base prompt, 'replace' uses variations as standalone prompts",
"enum": [
"append",
"replace"
],
"type": "string"
}
},
"required": [
"prompt"
],
"type": "object"
}