An AI image and video tool that swaps prompt roulette for stage building: layer compositing, three dimensional scenes, character poses, and more than sixty models in one canvas.

One workbench for retouching, design and collage, running in a browser and as a desktop program. One tap enhancement, portrait tools, template driven posters and social images, and batch adjustments. The basics are free; advanced features and watermark removal need a subscription.

Instead of one trick per site, this puts upscaling, sharpening, denoising, restoration, colourisation and a video line under one account and one credit balance. There is also a desktop build that keeps files on your own machine and does not spend credits at all.

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.

Not an application but a paper and its reference implementation, trained purely on synthetic degradations and loosely licensed enough that a whole shelf of GUI products wraps it. Three ways in, with different costs.

A desktop application that enlarges images on your own graphics card and touches no network. The catch is stated early: it needs a Vulkan-capable GPU, and a cloud tier handles the jobs your hardware cannot.

Tools are organised by what went wrong with the frame, not by the order of a workflow. Rendering runs locally by default so files stay on the machine, with unlimited cloud rendering when the graphics card is the bottleneck.

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.

The in-house models are trained only on licensed and public-domain material, output without a beta label is cleared for commercial work, and generative fill lives inside Photoshop instead of beside it.