Pictomancer.ai

Agent-to-agent image processing service. Resize, convert, compress, and pipeline images via REST, MCP, or A2A.

Skills

• Analyze image
  Fetch an image and return metadata: file size, dimensions, source format, per-model vision token cost, and whether it carries a C2PA (Content Credentials) manifest. Accepts a public URL or base64-encoded image.
  imagemetadataanalyzesizeprovenancec2pa
• Resize image
  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.
  imageresizescaledimensionssmart-cropfill
• Compress image
  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.
  imagecompressoptimizequalityfile-sizessimsharpendenoiseequalizeenhance
• Convert image format
  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.
  imageconvertformatwebpavifpngjpeg
• Crop image
  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.
  imagecropcutregiontrimsmart-cropgravity
• Optimize image for a vision model
  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.
  imagevisiontokensllmresizecost
• Optimize an AI-generated image for the web
  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. The input's C2PA manifest is reported but not carried over: re-encoding invalidates it.
  imagegeneratedai-generatedgpt-imagedall-efluxmidjourneystable-diffusionwebpavifoptimizeweb
• Image processing pipeline
  Chain multiple image operations in sequence (max 10). Operations: resize, compress, convert, crop. Each step receives the output of the previous one.
  imagepipelinebatchchainmulti-step

How to call

https://api.pictomancer.ai/a2a

Listed in

Directories this entry was found in.