Stability AI
api.stability.ai
Stability AI provides image generation, editing, and enhancement powered by Stable Diffusion models. Generate images from text prompts, transform existing images, upscale low-resolution images, remove backgrounds, inpaint specific regions, and search-and-replace objects within images.
api_key
free
1.0
https://api.stability.ai
2026-03-01 11:54:47
Health
Capabilities
generate_image
Generate an image from a text prompt using Stable Diffusion 3. Supports multiple aspect ratios, output formats, and negative prompts.
Detail: https://api.stability.ai/capabilities/generate_image
image_to_image
Transform an existing image guided by a text prompt. Control the transformation strength to balance between the original image and the prompt.
Detail: https://api.stability.ai/capabilities/image_to_image
inpaint_image
Edit specific regions of an image by providing a mask and a text prompt describing what to generate in the masked area.
Detail: https://api.stability.ai/capabilities/inpaint_image
remove_background
Automatically remove the background from an image, isolating the foreground subject with transparency.
Detail: https://api.stability.ai/capabilities/remove_background
search_and_replace
Find and replace objects or elements in an image by describing what to search for and what to replace it with.
Detail: https://api.stability.ai/capabilities/search_and_replace
upscale_image
Upscale a low-resolution image to higher resolution while preserving and enhancing details.
Detail: https://api.stability.ai/capabilities/upscale_image
Agent Preview
This is what an AI agent sees when it discovers this service via the Gateway:
Service: Stability AI Description: Stability AI provides image generation, editing, and enhancement powered by Stable Diffusion models. Generate images from text prompts, transform existing images, upscale low-resolution images, remove backgrounds, inpaint specific regions, and search-and-replace objects within images. Auth: api_key Capabilities: - generate_image: Generate an image from a text prompt using Stable Diffusion 3. Supports multiple aspect ratios, output formats, and negative prompts. - image_to_image: Transform an existing image guided by a text prompt. Control the transformation strength to balance between the original image and the prompt. - inpaint_image: Edit specific regions of an image by providing a mask and a text prompt describing what to generate in the masked area. - remove_background: Automatically remove the background from an image, isolating the foreground subject with transparency. - search_and_replace: Find and replace objects or elements in an image by describing what to search for and what to replace it with. - upscale_image: Upscale a low-resolution image to higher resolution while preserving and enhancing details.