Skip to main content
Glama

transform_image

Transform existing images using text prompts to modify visual content through AI-powered image-to-image generation.

Instructions

Transform an existing image using a text prompt (img2img). Either image_path or image_base64 must be provided.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
promptYesText description of the desired transformation
image_pathNoPath to the source image file to transform
image_base64NoBase64-encoded source image (alternative to image_path)
negative_promptNoElements to exclude from the transformed image
denoising_strengthNoStrength of the transformation (0.0-1.0, default: 0.75). Lower values keep more of the original image.
stepsNoNumber of inference steps (default: 20)
cfg_scaleNoClassifier-free guidance scale (default: 7.5)
seedNoRandom seed for reproducibility (-1 for random)
output_pathNoCustom file path to save the transformed image

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/james-see/mcp-drawthings'

If you have feedback or need assistance with the MCP directory API, please join our Discord server