Text-to-Image Generator

Generates images from text descriptions using the FLUX ai image generator. This actor takes a text prompt and optional parameters to generate customized images, returning them as base64-encoded data.

Features

• Generate images from text descriptions
• Customize image dimensions (64x64 to 2048x2048 pixels)
• Optional AI prompt enhancement
• Returns base64-encoded images
• Stores results in Apify dataset

Input Parameters

The actor accepts the following input parameters via the input schema:

1{
2    "prompt": "A beautiful sunset over mountains",
3    "width": 1024,
4    "height": 768,
5    "enhance": true
6}

Parameter	Type	Description	Default
prompt	string	The text description of the image you want to generate	(Required)
width	integer	Width of the generated image in pixels (64-2048)	1024
height	integer	Height of the generated image in pixels (64-2048)	1024
enhance	boolean	Whether to enhance the prompt using AI	true

Output

The actor stores its results in the default dataset. Each result contains:

1{
2    "prompt": "Original text prompt",
3    "image": "data:image/jpeg;base64,..."
4}

The image is returned as a base64-encoded data URL that can be directly used in HTML <img> tags or decoded back to binary data.