OmniShow

OmniShow is an AI-powered video generation platform that creates studio-quality human‑object interaction (HOI) videos from a single product photo plus optional text, audio, and pose inputs.

• Four generation modes: R2V (photo+text), RA2V (photo+text+audio), RP2V (photo+text+pose), RAP2V (all four inputs) – all in a single pass.
• Generates up to 10‑second continuous clips with stable hand‑object contact, natural grip, and frame‑locked product consistency.
• Supports lip‑sync, pose control, and talking‑avatar creation from a portrait and audio.
• Targeted at e‑commerce sellers, social‑commerce brands, creators, marketing teams, and AI researchers.
• Delivers cinematic product demos for Amazon, Shopify, TikTok Shop, etc., eliminating the need for studios, crews, or filming.

Built on peer‑reviewed research (ByteDance, CUHK, Monash, HKU) and open‑sourced on GitHub, OmniShow is validated on the HOIVG‑Bench benchmark and outperforms baseline models in visual fidelity, motion naturalness, identity consistency, and condition alignment.