Type a 3D character, then animate it with a phone video
Film yourself on your phone. A 3D character you typed into existence performs your moves. That's V2Fun, one browser tab for the whole pipeline.
Phone video in, performance out.
It starts with an ordinary phone video. Five to thirty seconds, one person, full body in frame works best. The AI lifts the motion off your clip, and your character performs it live in the browser, no suit, no hardware.
Generate here, rig there, capture somewhere else.
Indie game devs, VTubers, and designer-toy makers stitch this from three tools: one to generate the model, one to rig it, then mocap hardware that costs tens of thousands of dollars, or a separate video service.
Prompt → rigged, textured, animated — in one tab.
V2Fun folds it into one tab. Type a prompt or drop an image to get the model. One click rigs it. Textures generate automatically. Animate from a motion library or your own video, and export FBX or GLB.
Every stage exists elsewhere. The tab is the product.
So, is any of this new? Piece by piece, it isn't. Meshy bundles rigging and over five hundred preset motions. DeepMotion and Rokoko pull motion from video. Nobody else has your footage driving your own character in one tab, and it works best with humanoid characters, one performer, prototypes, not final shots.
Free during beta — with one line of fine print.
"all rights, title, and interest … in and to the Output belong to the Service Provider"
licensed back under CC BY 4.0 — paid customers will own their output (terms §6.3(a)/(b))
It's web-based and free during the beta, with fine print worth knowing. For now, V2Fun owns what you make and licenses it back, commercial use is fine with attribution. Paid plans will flip that. It's built by Tammy and the V2Fun team.
V2Fun
One tab takes you from a typed prompt to a character performing your moves, free while the beta lasts.
