Depthforge is an Apple Vision Pro app from Forward Thinkers Labs that generates AI images as immersive 3D spatial photos from simple text prompts. It is aimed at artists, designers and other creative users who want AI art with depth that can be placed in the room around them rather than flat pictures, and Forward Thinkers Labs built it exclusively for Vision Pro.
A user describes the desired scene in a text prompt, with help from a built-in prompt generator and an AI-enhanced prompt system, and Depthforge generates an image with depth in landscape or portrait orientation. Results are Apple Spatial Photos that save directly to the Photos app, and Depthforge keeps depth coherent as the viewer moves, so the images can be viewed across Apple devices.
On Vision Pro, Depthforge uses hand gesture controls, lets users position creations anywhere in their space and supports dynamic depth perception. Version 2.0 added Apple Spatial Photos support, including automatic conversion of existing Depthforge images to spatial photos, along with improved image management and library organization so creations are easy to find and open across devices.
Depthforge is free to download, with in-app purchases: a Basic plan of 50 Generations/Month for $4.99, a Pro plan of 150 Generations/Month for $9.99 and a Depthforge Topup for $1.99. It requires visionOS 2.0 or later on Apple Vision, is available in English and is rated 4+, and the developer states that no data is collected from the app.
Paw Portrait Lab turns one pet photo into an AI portrait in 50+ styles, from royal and oil painting to watercolour, cartoon and memorial art.
Draw Things is an AI-assisted image generation tool for iPhone, iPad, and Mac, offering offline image creation and on-device privacy.
PolaToons turns photos into AI-generated 3D Polaroid-style cartoon images, with paid plans for more generations.
AI Image Editor is a free all-in-one photo AI toolset for image enhancement, watermark removal, background editing, and more.
Seavid AI is a browser platform for making AI videos and images from text, photos and references using third-party models such as Seedance, Veo and Kling.
CannyPen is an AI platform for generating articles, ad copy, images, voiceovers and code, with 70+ templates and support for 54+ languages.