Solo anime performer
5 seconds · 720 × 1280 · Wan 2.6 · generated audio
One synthetic portrait becomes an orange-booth performance. The model retains the illustrated look, with blurred padding above and below the reference composition.
REAL GENERATION EXAMPLES
A photo. An actual generated take.
These clips were generated through our production video service on October 4, 2026, using synthetic references. They show actual outputs, including their limitations. The original Hotel Lobby recording and exact song-specific lip sync are not included.
Cat at the microphone
5 seconds · 720 × 1280 · Wan 2.6 · generated audio
A synthetic cat reference becomes an animated performance. Review the mouth and paws throughout the clip; model-generated audio is not the original Hotel Lobby song.
Start with a short take and check identity, framing, movement and sound before making a longer video. A successful render does not guarantee perfect likeness or choreography.
Create your own video →