Tiramisu drawer AI video: the Solo demo.
One character, one spoon, one very unconvincing alibi. Watch our illustrated Solo demo from inside the fridge, with the dessert tray in the foreground and the snack thief leaning into view.
- 10 seconds
- 9:16 vertical
- AI-generated fiction
Demo available now. Public generation and purchases are not open yet.
Preview solo mode ↗Watch without an account. Video model: Kling 2.5 Turbo.
Published November 2, 2026 · Curated for pacing
A tiramisu drawer idea, told from one fixed camera
The phrase “tiramisu drawer” brings together the dessert and the place where the surprise happens. This particular demo uses a foil tray on a refrigerator shelf. The camera looks outward from the left side of the fridge, while the illustrated character occupies the right side of the composition. You can see the face and the cake together, so the action has a clear beginning and payoff.
Solo gives the viewer one expression to follow. A quick snack becomes funny when the character pauses beside the evidence. The clip stays with the inside-fridge view instead of cutting to other rooms, making it easy to read as a short vertical story.
What to notice in the ten-second demo
First, find the tray in the foreground and the spoon near the character. Follow the change in the dessert as the snack unfolds. Around the six-second point, the creative target is an empty tray; the remaining time belongs to the character’s reaction. That reaction matters as much as the eating action because it gives the scene its guilty, caught-in-the-act mood.
This is a curated AI example. Timing, hand movement and continuity can vary between generations. Watch the complete clip rather than treating a single frame as a promise about every output.
Preparing a reference for a Solo fridge video
Choose one clear image with one visible face. A front-facing or gently turned portrait makes the expression easier to read than a distant full-body photo. Leave some space around the head, avoid heavy filters and keep sunglasses or hands from covering the eyes. The reference guides appearance and style; it is not a recording of a real snack.
The illustrated portrait shown here is the original character reference, not the exact opening frame fed to the video model. That fridge-scene frame was prepared separately. The customer workflow is configured to prepare a scene with Nano Banana 2 before animating it with Kling 2.5 Turbo, both through Kie.ai.
How this demo was made
The video uses Kling 2.5 Turbo (Image to Video Pro) through Kie.ai. Its opening and ending scene images were prepared separately with OpenAI image generation. We do not have a verified model-version identifier for those demo frames. They are curated examples of the direction, not unedited customer outputs.
The configured customer image model is Nano Banana 2 (Google Gemini 3.1 Flash Image), also accessed through Kie.ai. Learn more in our model disclosure, or read the fridge cam video guide for a closer look at the viewpoint, pacing and AI limitations.
