Released in late 2024, this closed-source foundational model's input consists of a first-frame image plus a text prompt, generating video exclusively at 720p. The model prioritizes accessibility and cost-effectiveness over high-resolution output or advanced control, supporting only basic first-frame conditioning. As a 2024 entry-level model, its visual quality and motion have been surpassed by all subsequent generations. It remains functional for simple animations but is largely obsolete for professional workflows.