A photo cleanup tool that lives entirely in a browser tab: brush over the thing you do not want and the algorithm invents what was behind it. Free use has no image cap at all, and the limit that does exist is measured in pixels rather than in attempts.

A product-image tool aimed at one group only: people who sell online. Cut out, restage, resize and export hundreds at once, with an API to wire the same step into an existing catalogue system. The money question is how the two meters, credits and saves, actually run down.

An enhancement app that pushes the whole job down to a single tap and points it at phones rather than desktops. Both storefronts carry the numbers, the free tier carries advertising, and the question worth asking is what it does to a face that is too far gone.

A text-to-image service sold to developers rather than a drawing website: the in-house engine is exposed through two endpoints, handles plain text, a reference image and text-driven edits, and returns up to eight images per call.

A text-to-image model that draws Chinese hanzi correctly instead of producing gibberish, releases its code and weights, and plugs into an existing generative workflow — while the consumer entry now lives on another platform.

The third generation produces up to thirty seconds of multi-shot footage with dialogue, music and effects in one generation, takes up to twenty multimodal references including documents and web pages, and lets the result be edited and extended.

Image generation, video generation and a canvas that keeps the result editable share one entrance, both the opening and closing frame can be pinned, and the workflow is built around Chinese prompts.

The vector variant writes editable SVG files rather than raster images, a handful of references can lock an entire brand style without training, and text length and placement stay under control.