A server that provides text-to-image generation capabilities by integrating with Stable Diffusion WebUI (ForgeUI/AUTOMATIC-1111). It exposes a single tool for generating images with extensive parameter control including prompts, negative prompts, sampling steps, dimensions, and more. The implementation handles authentication, manages output directories, and embeds generation parameters as image metadata. Built for users who want to generate AI art through natural language requests while maintaining fine-grained control over the generation process.
No reviews yet. Be the first to review!
Sign in to join the conversation
Highlight AIGenerate images using Stable Diffusion. Parameters: prompt (required string), negative_prompt (optional string), steps (optional integer), width (optional integer), height (optional integer), cfg_scale (optional integer), sampler_name (optional string), scheduler_name (optional string), seed (optional integer), batch_size (optional integer), restore_faces (optional boolean), tiling (optional boolean), output_path (optional string)
Get list of available Stable Diffusion models. No parameters required. Returns an array of model names.
Set the active Stable Diffusion model. Parameters: model_name (required string)
Get list of available upscaler models. No parameters required. Returns an array of upscaler names.
Upscale one or more images using Stable Diffusion. Parameters: images (required array of strings), resize_mode (optional integer), upscaling_resize (optional integer), upscaling_resize_w (optional integer), upscaling_resize_h (optional integer), upscaler_1 (optional string), upscaler_2 (optional string), output_path (optional string)
