jigsawstack / image-generation

Generate an image based on the given text by employing AI models like Flux, Stable Diffusion, and other top models.

  • Public
  • 20 runs
Iterate in playground

Input

string
Shift + Return to add a new line

The text prompt to generate the image from. Must be between 1-5000 characters.

Default: ""

string

The aspect ratio of the generated image

Default: "1:1"

integer

The width of the image. Must be between 256-1920 pixels.

integer

The height of the image. Must be between 256-1920 pixels.

integer
(minimum: 1, maximum: 90)

The number of denoising steps. Must be between 1-90. Higher values produce better quality images but take more time to generate.

Default: 4

string

The output format of the generated image

Default: "png"

string
Shift + Return to add a new line

A valid URL where the generated image will be sent

string
Shift + Return to add a new line

Key to store the generated image in file storage

string
Shift + Return to add a new line

Text describing what you don't want in the image

number
(minimum: 1, maximum: 28)

Higher guidance forces the model to better follow the prompt, but may result in lower quality output. Must be between 1-28.

integer

Makes generation deterministic. Using the same seed and set of parameters will produce identical image each time.

string
Shift + Return to add a new line

🔐 Your JigsawStack API Key (required)

Output

output
Generated in

Run time and cost

This model runs on CPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

🖼️ JigsawStack Image Generation

This model wraps the JigsawStack Image Generation API and allows you to generate high-quality images from text prompts using Replicate.

📦 It supports advanced controls like custom dimensions, guidance scale, negative prompts, and deterministic seeding.


🚀 What It Does

You provide a text prompt (and optionally, aspect ratio, resolution, etc.), and the model returns a generated image using JigsawStack’s hosted API.


🔑 Inputs

Name Type Required Description
prompt string ✅ Yes Text to guide image generation
api_key string ✅ Yes Your JigsawStack API key
aspect_ratio string ❌ No Aspect ratio (default: 1:1)
width int ❌ No Image width (256–1920)
height int ❌ No Image height (256–1920)
steps int ❌ No Generation steps (default: 4)
output_format string ❌ No Output format (png, svg)
negative_prompt string ❌ No What not to include
guidance float ❌ No Prompt adherence (1–28)
seed int ❌ No Deterministic seed
url string ❌ No Optional webhook for generated image
file_store_key string ❌ No Key to save output on your file storage

📤 Output

  • A single image (.png or .svg) generated by the model, shown directly in Replicate preview.