{"domain":"pictomancer.ai","count":2,"changes":[{"captured_at":"2026-10-22T19:19:58.048168","card_hash":"183bbfa9f3daeb94155172fc84a261d8f9cbf34afa892f8887175454a54674e3","previous_card_hash":"b3e3cfce51499c6f416974f2ffb64b4b2e706a89fa01bfab14e2af0698fddead","diff":{"skills_added":[{"id":"remove_image_background","name":"Remove image background","description":"Cut the subject (person, product, animal, object) out of a photo and return it on a transparent background as png (default), webp or avif. Optional q (1-100) for webp/avif. Runs a segmentation model on CPU, so expect a few seconds per image. $0.01 base.","tags":["image","background","remove-background","cutout","transparent","png","product-photo","e-commerce"],"inputModes":["application/json"],"outputModes":["image/png","image/webp","image/avif"]}],"skills_removed":[],"skills_changed":[{"id":"analyze_image","fields":["description","tags"]},{"id":"optimize_generated_image","fields":["description"]}],"fields_changed":[],"other_changed":true,"is_empty":false,"human_summary":"added 1 skill · updated 2 skills"}},{"captured_at":"2026-09-26T07:50:31","card_hash":"b3e3cfce51499c6f416974f2ffb64b4b2e706a89fa01bfab14e2af0698fddead","previous_card_hash":null,"diff":{"skills_added":[{"id":"analyze_image","name":"Analyze image","description":"Fetch an image and return metadata (file size in bytes). Accepts a public URL or base64-encoded image.","tags":["image","metadata","analyze","size"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"compress_image","name":"Compress image","description":"Re-encode an image with q (1-100) and format options to reduce file size. Supports q (quality), strip, compression. Formats: jpeg, png, webp, tiff, gif, avif. Or set quality_target (0-1] instead of q: the worker searches for the smallest file with SSIM at or above the target (jpeg, webp, avif) and reports the achieved SSIM, final q and encode count. Optional enhancement modifiers: denoise (median, radius 1-3), equalize (auto-contrast), sharpen.","tags":["image","compress","optimize","quality","file-size","ssim","sharpen","denoise","equalize","enhance"],"inputModes":["application/json"],"outputModes":["image/jpeg","image/png","image/webp"]},{"id":"convert_image","name":"Convert image format","description":"Convert an image to a different format. Supports: jpeg, png, webp, tiff, gif, avif. Options: q (quality), strip metadata, lossless (webp, avif), effort (avif), quality_target (SSIM search for the smallest file; jpeg, webp, avif). Optional enhancement modifiers: denoise (median, radius 1-3), equalize (auto-contrast), sharpen.","tags":["image","convert","format","webp","avif","png","jpeg"],"inputModes":["application/json"],"outputModes":["image/jpeg","image/png","image/webp","image/tiff","image/gif","image/avif"]},{"id":"crop_image","name":"Crop image","description":"Extract a rectangular region from an image, in one of three modes. Manual: top-left corner (x, y) and dimensions (width, height) in pixels. Smart crop: gravity (attention, entropy, centre) plus width and height; the window is picked automatically. Trim: trim=true (optional threshold) removes a uniform background border via content detection. Optional enhancement modifiers: denoise (median, radius 1-3), equalize (auto-contrast), sharpen. Output formats: jpeg, png, webp, tiff, gif, avif.","tags":["image","crop","cut","region","trim","smart-crop","gravity"],"inputModes":["application/json"],"outputModes":["image/jpeg","image/png","image/webp"]},{"id":"image_pipeline","name":"Image processing pipeline","description":"Chain multiple image operations in sequence (max 10). Operations: resize, compress, convert, crop. Each step receives the output of the previous one.","tags":["image","pipeline","batch","chain","multi-step"],"inputModes":["application/json"],"outputModes":["image/jpeg","image/png","image/webp"]},{"id":"optimize_for_vision","name":"Optimize image for a vision model","description":"Resize an image to the largest size a given vision model still benefits from, and report what it costs that model in tokens before and after. Every provider downscales oversized input before counting, so this saves bytes and upload latency rather than tokens; pass max_tokens to trade resolution for tokens. Supported models: claude-opus-5, claude-opus-4-8, claude-opus-4-7, claude-sonnet-5, claude-opus-4-6, claude-sonnet-4-6, claude-opus-4-5, claude-sonnet-4-5, claude-haiku-4-5, gpt-4o, gpt-4.1, gpt-4o-mini, o1, o3, gemini-2.5-pro, gemini-2.5-flash.","tags":["image","vision","tokens","llm","resize","cost"],"inputModes":["application/json"],"outputModes":["image/jpeg","image/png","image/webp"]},{"id":"optimize_generated_image","name":"Optimize an AI-generated image for the web","description":"The step after image generation: turn the 2-8 MB PNG that gpt-image, DALL-E, Flux, Midjourney or Stable Diffusion returned into a web-ready webp (default), avif, jpeg or png. Metadata stripped, transparency kept, optional max_dimension cap (never upscales), optional q or quality_target (SSIM). Same price as convert; if the result is not smaller it is free. Reports bytes before and after.","tags":["image","generated","ai-generated","gpt-image","dall-e","flux","midjourney","stable-diffusion","webp","avif","optimize","web"],"inputModes":["application/json"],"outputModes":["image/webp","image/avif","image/jpeg","image/png"]},{"id":"resize_image","name":"Resize image","description":"Scale an image by a factor, or fill an exact box. Supports uniform scaling (scale) or independent axes (scale_x, scale_y). Or set width+height for fill mode: resize and smart-crop to those exact dimensions in one call (optional gravity: attention, entropy, centre). Optional enhancement modifiers: denoise (median, radius 1-3), equalize (auto-contrast), sharpen. Output formats: jpeg, png, webp, tiff, gif, avif.","tags":["image","resize","scale","dimensions","smart-crop","fill"],"inputModes":["application/json"],"outputModes":["image/jpeg","image/png","image/webp"]}],"skills_removed":[],"skills_changed":[],"fields_changed":[{"field":"name","before":null,"after":"Pictomancer.ai"},{"field":"description","before":null,"after":"Agent-to-agent image processing service. Resize, convert, compress, and pipeline images via REST, MCP, or A2A."},{"field":"version","before":null,"after":"0.1.0"},{"field":"protocolVersion","before":null,"after":"1.0"},{"field":"url","before":null,"after":"https://api.pictomancer.ai/a2a"},{"field":"preferredTransport","before":null,"after":"JSONRPC"},{"field":"supportedInterfaces","before":null,"after":[{"url":"https://api.pictomancer.ai/a2a","protocolBinding":"JSONRPC","protocolVersion":"1.0"},{"url":"https://api.pictomancer.ai","protocolBinding":"HTTP+JSON","protocolVersion":"1.0"},{"url":"https://api.pictomancer.ai/mcp","protocolBinding":"MCP","protocolVersion":"1.0"}]},{"field":"securitySchemes","before":null,"after":{}},{"field":"security","before":null,"after":[]},{"field":"capabilities","before":null,"after":{"streaming":false,"pushNotifications":false,"extendedAgentCard":true,"extensions":[{"uri":"https://x402.org","description":"Pay-per-request in USDC on Base L2. First 50 requests free per agent.","required":false,"params":{"chain":"base","token":"USDC","freeTier":50}}]}},{"field":"provider","before":null,"after":{"organization":"Pictomancer.ai","url":"https://pictomancer.ai"}}],"other_changed":true,"is_empty":false,"human_summary":"added 8 skills · name ∅ → Pictomancer.ai · description ∅ → Agent-to-agent image processing service. · version ∅ → 0.1.0 · protocolVersion ∅ → 1.0 · url ∅ → https://api.pictomancer.ai/a2a · preferredTransport ∅ → JSONRPC · supportedInterfaces ∅ → https://api.pictomancer.ai/a2a (JSONRPC) · securitySchemes ∅ →  · security ∅ → [] · capabilities ∅ → extendedAgentCard, extensions, pushNotif · provider ∅ → Pictomancer.ai"}}]}