Auto-Photoshop-StableDiffusion-Plugin

Manages end-to-end image generation workflows by maintaining a central Generation Session object that coordinates parameters (prompts, dimensions, sampling steps), selection context from Photoshop, and communication with pluggable backends (Automatic1111, ComfyUI, Stable Horde). The session persists generation state and history across multiple requests, enabling iterative refinement without re-specifying parameters. Implements a backend abstraction layer that normalizes API differences across implementations, allowing users to switch backends without UI changes.

Extracts active selection boundaries and layer information from Photoshop documents using the UXP API, converts selected regions to base64-encoded image data, and sends them to the backend as inpainting masks or reference images. Supports both inpainting (regenerating masked regions) and outpainting (extending canvas beyond original boundaries) by reading selection geometry and layer pixel data. After generation, automatically places results back into Photoshop as new layers, preserving layer hierarchy and blend modes.

Queries the configured backend to dynamically discover available models and samplers, populating UI dropdowns with live options from the backend. Allows users to select which Stable Diffusion model to use (e.g., sd-v1-5, sd-xl, custom fine-tuned models) and which sampler/scheduler to apply (e.g., DPM++, Euler, Heun). Caches discovered models and samplers to avoid repeated API calls, with manual refresh option. Supports model switching without restarting the plugin, and automatically validates that selected model is available on the backend before generation.

Manages random seed values for generation, allowing users to specify fixed seeds for reproducible results or use random seeds for variation. Tracks generation history including seed, prompt, parameters, and output image, enabling users to reproduce previous generations by selecting from history. Implements seed validation (ensuring seeds are within valid range) and provides UI controls for seed increment (generating variations with sequential seeds). Stores generation history in memory during session with optional export to JSON for external analysis.

Integrates ControlNet conditioning by accepting control images (edge maps, depth maps, pose skeletons, etc.) and control strength parameters, forwarding them to backends that support ControlNet (Automatic1111 with ControlNet extension, ComfyUI with ControlNet nodes). Includes a preset system (stored in controlnet_preset.js) that defines common ControlNet configurations (Canny edges, depth estimation, OpenPose, etc.), allowing users to select presets from the UI rather than manually configuring control types. Automatically extracts control images from Photoshop selections or accepts external image uploads.

Integrates SAM (Segment Anything Model) to automatically generate inpainting masks from user clicks or bounding boxes on the Photoshop canvas. When enabled, SAM processes the current image and generates precise segmentation masks for selected objects, which are then used as inpainting masks for subsequent generation. The plugin communicates with a backend SAM service (typically running as a separate Python service) to perform segmentation, then converts SAM output masks to Photoshop selections or inpainting masks.

Accepts uploaded or Photoshop-sourced images as input and performs image-to-image (img2img) transformations using a denoising strength parameter (0.0-1.0) that controls how much the output diverges from the input. Lower strength values preserve input image structure while applying style changes; higher values allow more creative variation. Supports style transfer (applying artistic styles while maintaining composition), variation generation (creating similar images with different details), and guided image editing (regenerating specific aspects while preserving others). Communicates with backend img2img endpoints that support denoising strength parameter.

Analyzes the current Photoshop image or selection and automatically generates descriptive text prompts using a vision model or heuristic analysis. This enables users to generate variations or transformations without manually writing detailed prompts. The feature extracts visual features (colors, objects, composition) from the image and constructs prompts that preserve these characteristics while allowing style or content modifications. Integrates with external vision APIs (e.g., CLIP interrogation, image captioning services) or uses local heuristics to generate prompts.

Provides a settings management system that allows users to configure multiple Stable Diffusion backends (Automatic1111, ComfyUI, Stable Horde) with their respective API endpoints, authentication tokens, and model preferences. Settings are persisted across plugin sessions (stored in browser local storage or plugin-specific storage). Users can switch between backends from the UI without reconfiguring generation parameters, and the plugin automatically adapts API calls to each backend's specific format (Automatic1111 REST API vs ComfyUI WebSocket API vs Stable Horde HTTP API).

Automatically creates new Photoshop layers for generated images and places them into the active document with configurable layer naming, blending modes, and opacity. Preserves generation metadata (prompt, seed, parameters) as layer notes or custom properties, enabling traceability of generated content. Supports layer grouping (organizing generated images into folders) and automatic layer naming based on generation parameters or timestamps. Uses Photoshop UXP API to manipulate layer hierarchy and properties without requiring external scripts.

Continuously monitors connectivity to the configured Stable Diffusion backend by periodically sending health-check requests (e.g., /api/sd-models endpoint for Automatic1111). Displays connection status in the UI (connected/disconnected/error) and provides detailed error messages when generation fails due to backend issues (network timeout, API error, model not loaded, etc.). Implements exponential backoff retry logic for transient failures and graceful degradation when backend is unavailable (disables generation UI, shows helpful error messages).

Enables generation of multiple images in a single request by varying generation parameters (prompts, seeds, sampling steps, guidance scales) across a batch. Supports grid-based parameter exploration (e.g., generate 4x4 grid with different prompts and seeds) and automatically organizes results into Photoshop layer groups. Implements queue-based batch processing that sends multiple generation requests to the backend sequentially, displaying progress and allowing cancellation. Results are automatically composited into a grid image or placed as separate layers for comparison.