Search the full model catalog.

Tencent HunyuanVideo-1.5-i2v animates one reference image into a prompt-guided video clip with coherent motion, 480p–1080p presets, and reproducible seeds.

SenseNova U1 8B Visual Understanding creates infographic-style images and prompt-based edits from text and an optional reference image. Built by SenseNova on NEO-Unify.

Netflix VOID Model removes objects from videos and rewrites shadows, reflections, and motion after the edit. Use it for VFX cleanup and counterfactual scene edits.

Tencent’s HunyuanVideo 1.5 T2V turns detailed prompts into MP4 video clips with coherent motion. Control resolution, aspect ratio, frames, steps, and seed.

Generate a lip-synced talking avatar video from a single portrait image plus a script or uploaded audio. Pick a voice, language, and 720p or 1080p output.

Edit a short MP4/MOV clip or generate a new 720p/1080p video from up to 9 reference images and a detailed prompt, with optional watermark and seed control.

Alibaba’s HappyHorse 1.0 generates 5–15s videos from text or a first-frame image. Choose 720p or 1080p, aspect ratio, seed, and watermark.

Casts the person from one portrait as the observer in a nature-documentary clip, with 13 scenarios such as a fox hunting in snow, a cheetah chase and a hammerhead over a coral reef.

121 transformation scenes from one portrait: henshin armor, outfit cycles, werewolf and phoenix shifts, statues that come alive, animated tattoos, age arcs and clones. A few take up to 7 images.

Casts the person from one portrait in 67 horror presets built on ghosts, doppelgangers, reflections that act on their own and empty liminal spaces. Several are styled as CCTV or VHS footage.

Gives the person from one portrait a superhero moment on video: an aura igniting, armor assembling, a plasma blast or a summoned creature. 35 scenarios, from desert power-ups to divine projections.

Action clips with your subject as the athlete or driver: 27 presets including a parkour one-take, a surf barrel, big air snowboarding and skiing on the moon.

Places a portrait in 31 presets built on extreme scale or time, such as a zoom from a galaxy into the subject's eye or the subject growing to giant size on a city avenue.

Recasts one portrait as the lead of a period piece, with 33 presets spanning 1920s Harlem, 1940s noir, 1980s VHS and Y2K digital looks. Five presets take a second person.

Moves the person in one portrait through 43 preset reality warps, such as a corridor of doors that open onto other worlds or a mirror the subject steps into. One preset casts two people.

Turns a product photo, logo or portrait into a short clip from 28 preset scenarios, mostly ads like a cola macro pour or a 360-degree skincare orbit. Four scenarios pair a person with a product.

Turns a portrait into first-person and FPV drone-style footage. The 61 scenes run from dragon riding and wingsuit dives to animal POV hunts, and one also takes two photos of places to pass through.

Puts the person from one portrait into 24 homages to famous film moments, from a rooftop bullet dodge to a bicycle crossing the moon. The scenes cover sci-fi, war, adventure, noir, disaster and samurai cinema.

Fourteen disaster-movie shots with the person from one portrait in the lead role, including a coastal tsunami wall, a supervolcano, a meteor shockwave and an orbital ring collapse.

Puts the person from a portrait in the middle of a fight: kaiju battles, wuxia duels, mecha brawls and boss-style entrances. Eight of the 92 scenes can cast a second real person as the opponent.