Search the full model catalog.

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.

Cinematic wildlife documentary videos generated from a single portrait, in the style of nature programming. 13 scenarios across predator hunts, reef encounters and aerial wildlife.

Henshin, outfit cycles, animal/object morphs, age progressions and era shifts generated from a single portrait. 121 scenarios.

Analog horror, ghost and paranormal cinematic short videos from a single portrait. 67 scenarios across uncanny domestic, found-footage and liminal spaces.

Cinematic superhero power-up, aura and transformation videos generated from a single portrait. 35 scenarios.

Cinematic extreme sports videos generated from a single portrait. 27 scenarios across parkour, BMX, surf, ATV, snowboard, MotoGP and lunar skiing.

Cosmic-to-micro scale-shift videos generated from a single portrait. 31 scenarios across galaxy zooms, ant scale, giant stomp and ocean trench dives.

Era-shift cinematic short videos from a single portrait. 33 retro and period-aesthetic scenarios across a century of cinema styles.

Portals, dimensional rifts and reality-warp videos generated from a single portrait. 43 scenarios across sci-fi, surreal and fantasy.

Cinematic product, food and fashion short videos from one photo. 28 scenarios with motion design, slow-mo physics and stylized lighting.

First-person and FPV cinematic adventure videos generated from a single portrait. 61 scenarios across dragon flight, wingsuit, animal POV, parkour, FPV drone racing and lunar handheld footage.

Iconic movie-scene homage videos generated from a single portrait. 24 scenarios across sci-fi action, war epic, noir, samurai and adventure.

Hyperrealistic cinematic disaster videos from a single portrait photo. 14 scenarios across meteor strikes, supervolcanoes, earthquakes, tsunamis and more.

Star in epic cinematic battle videos generated from a single portrait. 92 scenarios across kaiju, fantasy, mecha, samurai, wuxia and modern action.

Cinematic emotional and intimate short films from a single portrait photo. 35 scenarios across cozy, romantic and dramatic moments.