{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"github-abdullahalfaraj--auto-photoshop-stablediffusion-plugin","slug":"abdullahalfaraj--auto-photoshop-stablediffusion-plugin","name":"Auto-Photoshop-StableDiffusion-Plugin","type":"extension","url":"https://github.com/AbdullahAlfaraj/Auto-Photoshop-StableDiffusion-Plugin","page_url":"https://unfragile.ai/abdullahalfaraj--auto-photoshop-stablediffusion-plugin","categories":["image-generation"],"tags":["ai","ai-art","art","automatic1111","comfy","comfyui","comfyui-manager","photoshop","plugin","stable-diffusion"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"github-abdullahalfaraj--auto-photoshop-stablediffusion-plugin__cap_0","uri":"capability://image.visual.multi.backend.stable.diffusion.image.generation.with.session.orchestration","name":"multi-backend stable diffusion image generation with session orchestration","description":"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.","intents":["Generate AI images from text prompts directly within Photoshop without leaving the application","Switch between different Stable Diffusion backends (Automatic1111, ComfyUI) without reconfiguring the plugin","Maintain generation history and parameters across multiple image generation attempts","Coordinate generation parameters with Photoshop selection context for targeted operations"],"best_for":["Digital artists and designers using Photoshop as primary creative tool","Teams running self-hosted Stable Diffusion backends (Automatic1111 or ComfyUI)","Users wanting to avoid context-switching between Photoshop and separate AI generation tools"],"limitations":["Requires external Stable Diffusion backend running locally or remotely — no built-in model inference","Session state is ephemeral and lost on plugin reload — no persistent generation history across sessions","Backend communication is synchronous, blocking UI during generation (no streaming progress updates)","Limited to single-image generation per request — batch generation not supported"],"requires":["Adobe Photoshop 2022 or later with UXP support","Running instance of Automatic1111 WebUI, ComfyUI, or Stable Horde account","Network connectivity to backend (local or remote)","TypeScript/JavaScript runtime for plugin execution"],"input_types":["text prompts (positive and negative)","numeric parameters (steps, guidance scale, seed)","image selections from Photoshop canvas","backend configuration (URL, API key)"],"output_types":["PNG/JPEG images","base64-encoded image data","generation metadata (seed, parameters used)"],"categories":["image-visual","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-abdullahalfaraj--auto-photoshop-stablediffusion-plugin__cap_1","uri":"capability://image.visual.photoshop.layer.and.selection.aware.image.inpainting.and.outpainting","name":"photoshop layer and selection-aware image inpainting and outpainting","description":"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.","intents":["Regenerate specific regions of an image by selecting them in Photoshop and using AI inpainting","Extend image boundaries (outpainting) by selecting the area to fill and specifying expansion direction","Maintain non-destructive workflows by placing generated content on separate layers","Use Photoshop's native selection tools (rectangular, lasso, magic wand) to define inpainting regions"],"best_for":["Photoshop power users comfortable with selection tools and layer workflows","Designers needing non-destructive AI-assisted editing within their existing Photoshop projects","Artists using inpainting for content removal, extension, or region-specific style transfer"],"limitations":["Selection extraction is limited to rectangular or simple polygonal regions — complex feathered selections may lose precision","Layer placement always creates new layers rather than modifying existing ones — requires manual layer merging","Inpainting quality depends entirely on backend model and mask quality — no built-in mask refinement tools","Large selections (>2048x2048) may cause memory pressure in plugin due to base64 encoding overhead"],"requires":["Active Photoshop document with at least one layer","Active selection in Photoshop (rectangular or polygonal)","Backend support for inpainting mode (img2img with mask parameter)","Sufficient VRAM on backend for selected image dimensions"],"input_types":["Photoshop selection geometry (bounds, coordinates)","Layer pixel data (extracted via UXP)","Inpainting prompt and negative prompt","Mask strength and other inpainting parameters"],"output_types":["New Photoshop layer containing inpainted/outpainted result","Layer metadata (name, blend mode, opacity)"],"categories":["image-visual","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-abdullahalfaraj--auto-photoshop-stablediffusion-plugin__cap_10","uri":"capability://tool.use.integration.stable.diffusion.model.and.sampler.selection.with.dynamic.backend.discovery","name":"stable diffusion model and sampler selection with dynamic backend discovery","description":"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.","intents":["Select different Stable Diffusion models (v1.5, XL, custom fine-tunes) without manual configuration","Choose sampling methods that affect generation quality and speed (DPM++ vs Euler vs Heun)","Discover newly added models on the backend without plugin restart","Validate model availability before generation to avoid errors"],"best_for":["Users with multiple models installed on their backend and wanting to switch between them","Teams experimenting with different model architectures (v1.5 vs XL vs custom fine-tunes)","Developers testing model-specific features or comparing output quality across models"],"limitations":["Model discovery requires backend API call — adds latency on plugin startup (1-2 seconds)","Model caching may become stale if models are added/removed on backend without plugin refresh","Model selection is global — cannot use different models for different layers or regions","Sampler availability varies by backend and model — some samplers may not work with all models"],"requires":["Backend API endpoint that exposes available models and samplers (e.g., /api/sd-models for Automatic1111)","At least one model installed on the backend"],"input_types":["Backend configuration (URL, type)","Model name (string)","Sampler name (string)"],"output_types":["List of available models (array of strings)","List of available samplers (array of strings)","Selected model and sampler (strings)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-abdullahalfaraj--auto-photoshop-stablediffusion-plugin__cap_11","uri":"capability://memory.knowledge.seed.management.and.reproducible.generation.with.history.tracking","name":"seed management and reproducible generation with history tracking","description":"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.","intents":["Reproduce previous generations by selecting from history and re-running with same seed and parameters","Generate variations by incrementing seed while keeping other parameters constant","Track which seeds produced high-quality results for future reference","Export generation history for analysis or sharing with team members"],"best_for":["Artists needing reproducible results for iteration and refinement","Teams tracking which seeds/parameters produce best results for specific use cases","Developers debugging generation quality issues by reproducing specific seeds"],"limitations":["Generation history is ephemeral (lost on plugin reload) — no persistent history database","Seed reproducibility is only guaranteed within same backend and model version — different backends or model updates may produce different results with same seed","History export is manual (JSON file) — no automatic backup or cloud sync","History size is unbounded — large histories (>1000 generations) may cause memory pressure"],"requires":["Seed value (integer, typically 0-2^32-1)","Generation parameters (prompt, model, sampler, etc.)"],"input_types":["Seed value (integer or 'random' for random seed)","Seed increment value (for generating variations)","Generation parameters (prompt, model, sampler, etc.)"],"output_types":["Generation history entry (seed, prompt, parameters, output image)","History export (JSON file)"],"categories":["memory-knowledge","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-abdullahalfaraj--auto-photoshop-stablediffusion-plugin__cap_2","uri":"capability://image.visual.controlnet.guided.image.generation.with.preset.management","name":"controlnet-guided image generation with preset management","description":"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.","intents":["Guide image generation using edge detection, depth maps, or pose skeletons to maintain structural consistency","Apply style transfer while preserving composition by using ControlNet with image-to-image generation","Quickly apply common ControlNet configurations via preset dropdown instead of manual parameter entry","Extract control images from Photoshop selections to use as conditioning for generation"],"best_for":["Artists needing structural control over generated images (maintaining poses, compositions, or perspectives)","Designers using style transfer with composition preservation","Teams with standardized ControlNet workflows (e.g., always using Canny edges for line art)"],"limitations":["ControlNet support requires backend extension (Automatic1111 ControlNet extension or ComfyUI ControlNet nodes) — not available on Stable Horde","Control image preprocessing (edge detection, depth estimation) is backend-dependent — plugin cannot perform local preprocessing","Preset system is static and requires code modification to add new presets — no runtime preset creation UI","Multiple ControlNets per generation not supported — limited to single control image per request"],"requires":["Backend with ControlNet support (Automatic1111 with ControlNet extension or ComfyUI with ControlNet nodes)","Control image (edge map, depth map, pose skeleton, etc.) either from Photoshop selection or external file","ControlNet model weights downloaded to backend (e.g., control_canny-fp16.safetensors)"],"input_types":["Control image (PNG/JPEG)","Control type (canny, depth, pose, etc.)","Control strength (0.0-1.0 float)","Text prompt and negative prompt"],"output_types":["Generated image conditioned by control input","Generation metadata including control type and strength used"],"categories":["image-visual","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-abdullahalfaraj--auto-photoshop-stablediffusion-plugin__cap_3","uri":"capability://image.visual.segment.anything.model.sam.integration.for.automatic.mask.generation","name":"segment anything model (sam) integration for automatic mask generation","description":"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.","intents":["Automatically generate precise inpainting masks by clicking on objects in the image (no manual selection drawing)","Remove or replace specific objects in images by using SAM segmentation followed by inpainting","Reduce manual selection effort for complex object boundaries that are difficult to trace with Photoshop's selection tools","Perform object-aware image editing by segmenting objects and regenerating only selected regions"],"best_for":["Designers and artists working with complex object boundaries that are tedious to select manually","Content creators needing fast object removal or replacement workflows","Teams with SAM service infrastructure already deployed"],"limitations":["Requires separate SAM service running (typically Python-based) — adds deployment complexity beyond plugin","SAM segmentation quality varies by image content — may produce imprecise masks for ambiguous objects or transparent regions","Latency overhead of SAM inference (typically 1-3 seconds per segmentation) adds to overall generation time","SAM masks are binary (hard edges) — no soft feathering, requiring manual refinement for seamless inpainting"],"requires":["Running SAM service (e.g., Meta's segment-anything or ONNX-optimized variant)","Network connectivity from plugin to SAM service","Current image loaded in Photoshop with sufficient resolution for SAM processing"],"input_types":["Click coordinates on Photoshop canvas","Bounding box coordinates (optional)","Current image data from Photoshop"],"output_types":["Binary segmentation mask (PNG or base64)","Photoshop selection from mask","Inpainting mask for subsequent generation"],"categories":["image-visual","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-abdullahalfaraj--auto-photoshop-stablediffusion-plugin__cap_4","uri":"capability://image.visual.image.to.image.transformation.with.style.transfer.and.variation.generation","name":"image-to-image transformation with style transfer and variation generation","description":"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.","intents":["Apply artistic styles to existing images while maintaining composition and structure","Generate variations of an image with different details but similar overall composition","Perform guided image editing by specifying prompts that modify specific aspects of an input image","Upscale or enhance images by using img2img with low denoising strength and upscaling prompts"],"best_for":["Digital artists exploring style variations on existing artwork","Designers needing quick style transfer without manual artistic work","Content creators generating image variations for A/B testing or portfolio expansion"],"limitations":["Denoising strength is a single global parameter — cannot apply different strengths to different image regions","Quality heavily depends on input image quality and resolution — low-quality inputs produce low-quality outputs","Style transfer results are non-deterministic (even with fixed seed) due to diffusion sampling variance","Very high denoising strength (>0.9) often produces completely unrelated images, making it difficult to preserve input intent"],"requires":["Input image (from Photoshop selection, layer, or file upload)","Backend support for img2img mode with denoising strength parameter","Text prompt describing desired transformation or style"],"input_types":["Image (PNG/JPEG from Photoshop or file upload)","Text prompt and negative prompt","Denoising strength (0.0-1.0 float)","Sampling method and steps"],"output_types":["Transformed image (PNG/JPEG)","Generation metadata (denoising strength, seed, sampler used)"],"categories":["image-visual"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-abdullahalfaraj--auto-photoshop-stablediffusion-plugin__cap_5","uri":"capability://text.generation.language.one.button.prompt.generation.from.image.context","name":"one-button prompt generation from image context","description":"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.","intents":["Quickly generate descriptive prompts from existing images without manual writing","Create variations of images by auto-generating prompts that preserve visual characteristics","Reduce friction for users unfamiliar with prompt engineering or descriptive language","Enable rapid iteration by generating new prompts from previous generation results"],"best_for":["Non-technical users or artists unfamiliar with prompt engineering","Rapid prototyping workflows where manual prompt writing is a bottleneck","Iterative image generation where each result becomes input for the next prompt"],"limitations":["Auto-generated prompts are generic and may not capture artistic intent or specific style preferences","Requires external vision API (CLIP interrogation, image captioning) or local model — adds latency (1-3 seconds per image)","Generated prompts often include obvious visual features (colors, objects) but miss nuanced artistic direction","No user control over prompt generation parameters — results are deterministic but not customizable"],"requires":["Current image in Photoshop or selected region","Access to vision model or CLIP interrogation service (local or remote)","Sufficient image resolution for accurate feature extraction (minimum 256x256)"],"input_types":["Image data from Photoshop (selection or layer)","Optional style hints or keywords to incorporate into generated prompt"],"output_types":["Text prompt (string)","Confidence scores or feature list used to generate prompt"],"categories":["text-generation-language","image-visual"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-abdullahalfaraj--auto-photoshop-stablediffusion-plugin__cap_6","uri":"capability://tool.use.integration.multi.backend.configuration.and.switching.with.persistent.settings","name":"multi-backend configuration and switching with persistent settings","description":"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).","intents":["Configure and switch between multiple Stable Diffusion backends without restarting the plugin","Save API keys and endpoint URLs securely for quick backend switching","Test generation on different backends to compare quality or performance","Maintain separate model configurations for different backends (e.g., different base models per backend)"],"best_for":["Teams running multiple Stable Diffusion instances and needing to switch between them","Users comparing output quality across different backends (Automatic1111 vs ComfyUI)","Developers testing plugin compatibility with different backend versions"],"limitations":["Settings storage is browser-based (local storage) — not encrypted and vulnerable to XSS attacks if plugin is compromised","Backend switching does not migrate generation history or cached models — each backend has independent state","API key storage in local storage is a security risk — no built-in encryption or secure credential storage","Backend-specific features (e.g., ComfyUI custom nodes) are not abstracted — users must manually configure compatible features per backend"],"requires":["At least one configured Stable Diffusion backend (Automatic1111, ComfyUI, or Stable Horde account)","API endpoint URL and authentication token (if required by backend)","Network connectivity to configured backend"],"input_types":["Backend type (Automatic1111, ComfyUI, Stable Horde)","API endpoint URL","Authentication token or API key","Model name and other backend-specific settings"],"output_types":["Persisted settings (stored in local storage)","Backend status indicator (connected/disconnected)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-abdullahalfaraj--auto-photoshop-stablediffusion-plugin__cap_7","uri":"capability://tool.use.integration.photoshop.layer.creation.and.image.placement.with.metadata.preservation","name":"photoshop layer creation and image placement with metadata preservation","description":"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.","intents":["Automatically place generated images as new layers in Photoshop without manual copy-paste","Organize generated images into layer groups for non-destructive editing workflows","Preserve generation metadata (prompt, seed) as layer notes for future reference or reproduction","Maintain layer naming conventions that reflect generation parameters for easy identification"],"best_for":["Photoshop power users with established layer organization workflows","Teams needing traceability of AI-generated content (audit trails via layer metadata)","Designers using non-destructive editing with multiple generation iterations"],"limitations":["Layer metadata storage is limited to layer notes (text field) — no structured metadata storage, making programmatic access difficult","Layer naming is limited to 255 characters — long prompts must be truncated or hashed","Automatic layer grouping requires predefined folder structure — no dynamic folder creation based on generation parameters","Layer blending modes are limited to Photoshop's built-in modes — no custom blending logic"],"requires":["Active Photoshop document with at least one layer","Generated image data (PNG/JPEG)","Photoshop UXP API access (available in Photoshop 2022+)"],"input_types":["Generated image (PNG/JPEG or base64)","Layer name (string, max 255 characters)","Generation metadata (prompt, seed, parameters)","Blending mode and opacity (optional)"],"output_types":["New Photoshop layer containing generated image","Layer metadata (notes, custom properties)"],"categories":["tool-use-integration","image-visual"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-abdullahalfaraj--auto-photoshop-stablediffusion-plugin__cap_8","uri":"capability://tool.use.integration.real.time.backend.connectivity.status.monitoring.and.error.handling","name":"real-time backend connectivity status monitoring and error handling","description":"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).","intents":["Quickly identify backend connectivity issues before attempting generation","Understand why generation failed (network error vs API error vs backend overload)","Automatically retry failed requests with exponential backoff to handle transient failures","Provide clear error messages to users so they can troubleshoot backend issues"],"best_for":["Users running self-hosted backends that may be unstable or offline","Teams needing visibility into backend health for debugging generation failures","Developers integrating the plugin into larger workflows where backend availability is critical"],"limitations":["Health checks add network overhead (periodic requests even when not generating) — may impact battery life on laptops","Health check endpoints vary by backend (Automatic1111 vs ComfyUI) — requires backend-specific health check logic","Exponential backoff retry logic may delay generation for several seconds on transient failures","Error messages are limited to HTTP status codes and response text — may not provide actionable debugging information for complex failures"],"requires":["Network connectivity to configured backend","Backend health check endpoint (varies by backend type)"],"input_types":["Backend configuration (URL, type)","Health check interval (seconds)"],"output_types":["Connection status (connected/disconnected/error)","Error message (string)","Timestamp of last successful connection"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-abdullahalfaraj--auto-photoshop-stablediffusion-plugin__cap_9","uri":"capability://image.visual.batch.image.processing.with.parameter.variation.and.grid.generation","name":"batch image processing with parameter variation and grid generation","description":"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.","intents":["Generate multiple image variations with different seeds to explore output diversity","Create parameter exploration grids (e.g., 4 different prompts × 4 different seeds) to compare results","Batch-process multiple images with the same parameters for consistency","Automatically organize batch results into layer groups for easy comparison and selection"],"best_for":["Artists exploring multiple variations to select the best result","Designers comparing parameter effects (e.g., different guidance scales) on output quality","Teams needing consistent batch processing of multiple images with identical parameters"],"limitations":["Batch processing is sequential (one image at a time) — no parallel generation even if backend supports it","Grid generation requires manual parameter specification — no UI for defining parameter ranges","Large batches (>16 images) may take several minutes to complete, blocking UI during processing","No built-in deduplication or quality filtering — all results are kept regardless of quality"],"requires":["Backend support for multiple sequential requests","Sufficient backend VRAM to handle batch processing without memory errors","Parameter specifications for each batch item (prompt, seed, etc.)"],"input_types":["Batch configuration (number of images, parameter variations)","Parameter specifications (prompts, seeds, sampling steps, guidance scales)","Grid dimensions (optional, for grid-based exploration)"],"output_types":["Multiple generated images (PNG/JPEG)","Grid image compositing results (optional)","Photoshop layer group containing all batch results"],"categories":["image-visual","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":42,"verified":false,"data_access_risk":"high","permissions":["Adobe Photoshop 2022 or later with UXP support","Running instance of Automatic1111 WebUI, ComfyUI, or Stable Horde account","Network connectivity to backend (local or remote)","TypeScript/JavaScript runtime for plugin execution","Active Photoshop document with at least one layer","Active selection in Photoshop (rectangular or polygonal)","Backend support for inpainting mode (img2img with mask parameter)","Sufficient VRAM on backend for selected image dimensions","Backend API endpoint that exposes available models and samplers (e.g., /api/sd-models for Automatic1111)","At least one model installed on the backend"],"failure_modes":["Requires external Stable Diffusion backend running locally or remotely — no built-in model inference","Session state is ephemeral and lost on plugin reload — no persistent generation history across sessions","Backend communication is synchronous, blocking UI during generation (no streaming progress updates)","Limited to single-image generation per request — batch generation not supported","Selection extraction is limited to rectangular or simple polygonal regions — complex feathered selections may lose precision","Layer placement always creates new layers rather than modifying existing ones — requires manual layer merging","Inpainting quality depends entirely on backend model and mask quality — no built-in mask refinement tools","Large selections (>2048x2048) may cause memory pressure in plugin due to base64 encoding overhead","Model discovery requires backend API call — adds latency on plugin startup (1-2 seconds)","Model caching may become stale if models are added/removed on backend without plugin refresh","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.33252475662934,"quality":0.49,"ecosystem":0.6000000000000001,"match_graph":0.25,"freshness":0.52,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.15,"match_graph":0.23,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:21.549Z","last_scraped_at":"2026-05-03T13:58:42.319Z","last_commit":"2024-04-22T18:44:01Z"},"community":{"stars":7251,"forks":531,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=abdullahalfaraj--auto-photoshop-stablediffusion-plugin","compare_url":"https://unfragile.ai/compare?artifact=abdullahalfaraj--auto-photoshop-stablediffusion-plugin"}},"signature":"L3YbOaeJ9kiagvOltsQid8eg4NcG7r966TZQgVo203B//AcUeHWhibcAzMGZtN4BZVOHXo8M7UZ0k346cvysDw==","signedAt":"2026-06-21T22:18:23.074Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/abdullahalfaraj--auto-photoshop-stablediffusion-plugin","artifact":"https://unfragile.ai/abdullahalfaraj--auto-photoshop-stablediffusion-plugin","verify":"https://unfragile.ai/api/v1/verify?slug=abdullahalfaraj--auto-photoshop-stablediffusion-plugin","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}