All projects on Solana matching “image”

Build a consistent prompt set for one human character: a canonical image prompt with every appearance fact labelled, negative prompts that stop traits like glasses or a cane from vanishing, a video prompt, and optionally a contact sheet that holds everything fixed and walks one axis. Works with any image or video model. Text keeps wardrobe and framing stable; for the same FACE across images, gener

Video generation from a text prompt, a start image, reference images, or a reference clip (Kling, Seedance, MiniMax H3, Wan, Veo, Grok Imagine, more), billed at the render's actual cost — from about half provider list price, never above list. Per-model length, resolution, and audio options; the call returns finished video URLs. Menu + prices: GET /api/v1/media/models (free).

Write SEO metadata into a JPEG, PNG or WebP image and return the modified image. The picture is never re-encoded and existing metadata of the same kind is replaced, not duplicated. Paid per successful call over x402: the first attempt answers HTTP 402 with the price; a failed call is not charged.

Compress images to reduce file size with configurable quality. A photo compressed to quality 30 is typically 90-95% smaller with acceptable visual quality. Useful for reducing storage costs, optimizing web page load times, preparing image uploads, and bandwidth reduction for mobile users. Accepts PNG, JPEG, WebP, AVIF. Returns JPEG.

Generate a video from a text prompt, or animate an image_url from its first frame. The paid response waits about as long as the model usually takes to render and returns the video URL, else a statusUrl to poll (Prefer: wait=N sets the wait). 8 models including Google Veo 3.1, Kling 3.0, Seedance 2.5, Wan 2.7 and MiniMax Hailuo 3, 4 to 15 seconds, 16:9 or 9:16, from $0.42. GET this URL for every mo

Render any public web page in a real headless Chrome and return a PNG/JPEG screenshot (base64 JSON, or raw image with ?raw=1). Viewport up to 1920x1920, optional full-page capture up to 8000px tall, optional wait for late content. Use when an agent needs to see what a page actually looks like (visual check, JS-rendered content, layout/UI review, evidence capture, feeding a vision model) rather tha

Reader Pro: fetch a public web page and return structured data, no LLM: OpenGraph/meta tags, parsed JSON-LD (schema.org), HTML tables as row objects, deduped internal/external links, emails/phones/social profiles, heading outline, images with alt text, plus optional CSS-selector fields.