Stable Diffusion WebUI
Summary
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.
Available Actions(5)
generate_image
Generate images using Stable Diffusion. Parameters: prompt (required), negative_prompt, steps (default: 4, range: 1-150), width (default: 1024, range: 512-2048), height (default: 1024, range: 512-2048), cfg_scale (default: 1, range: 1-30), sampler_name (default: 'Euler'), scheduler_name (default: 'Simple'), seed (-1 for random), batch_size (default: 1, max: 4), restore_faces, tiling, output_path.
get_sd_models
Get list of available Stable Diffusion models. No parameters required. Returns an array of model names.
set_sd_model
Set the active Stable Diffusion model. Parameters: model_name (required).
get_sd_upscalers
Get list of available upscaler models. No parameters required. Returns an array of upscaler names.
upscale_images
Upscale one or more images using Stable Diffusion. Parameters: images (required), resize_mode (default: from env), upscaling_resize (default: from env), upscaling_resize_w (default: from env), upscaling_resize_h (default: from env), upscaler_1 (default: from env), upscaler_2 (default: from env), output_path.
Recensioni della Community
Nessuna recensione ancora. Sii il primo a recensire!
Accedi per unirti alla conversazione
Highlight AI