Take two character concepts beyond a still image with Hotel Lobby AI on Try Nano Banana. Prepare your left and right images as one start frame, describe a modest studio performance and choose an available video model. Image creation and video rendering are separate steps with their own model choices and quotes.
Prepare my duo performanceThe two uploads become one side-by-side start image for image-to-video. Preparation does not remove backgrounds or assign independent face identities. Exact choreography, facial consistency, lip synchronization and an original soundtrack are not guaranteed.
Watch these collected performances for ideas about the orange studio, duo framing and character styling. These are external references, not results generated on this site or one-click templates.
Collected performance reference for duo framing, studio styling and character movement.
Collected performance reference for duo framing, studio styling and character movement.
Collected performance reference for duo framing, studio styling and character movement.
Collected performance reference for duo framing, studio styling and character movement.
Collected performance reference for duo framing, studio styling and character movement.
Collected performance reference for duo framing, studio styling and character movement.
Collected performance reference for duo framing, studio styling and character movement.
Collected performance reference for duo framing, studio styling and character movement.
Collected performance reference for duo framing, studio styling and character movement.
Collected performance reference for duo framing, studio styling and character movement.
Collected performance reference for duo framing, studio styling and character movement.
Explore these collected visual references, then use your own images for the two upload positions above.
Collected visual references; these images are not generated results.
Hotel Lobby AI centers an orange studio, a suspended microphone and a pair of performers. Start by designing two characters whose shapes and colors work together, then use their prepared image for video. The image model used to create a portrait is not automatically the video model for this page. Collected clips demonstrate visual directions rather than a one-click output template.
Finish the clothing, silhouette and expression of your two characters before moving to video. Upload a PNG or JPG for each position, up to 10 MB per image. Keep both faces visible and use similar framing; these uploads are performer positions, not start and end frames.
Sign in and click Prepare duo image to join and upload the characters as one start frame. This step does not submit a video job or spend generation credits. Inspect the crops and background seam, then prepare the pair again after replacing either image.
Select an available image-to-video model and describe one studio action that suits your finished concepts. Check that model's output options and Required Credits before generating; an earlier image task does not determine the video cost. In Your results, compare the full clip with the original character designs.
Create two original portraits with different clothing colors and compatible lighting. Use the orange setting as a simple background goal. Compare the moving result with the image palette rather than adding many new objects.
Try your own mascot designs with readable shapes and a similar body scale. Keep the action to a small nod or sway. Fine logos and lettering can change during animation, so add exact brand elements separately.
Prepare distinct character concepts such as everyday and stage outfits. Put them in separate left and right slots to explore a visual contrast, without assuming the model can preserve two identities perfectly.
Choose the clothing, silhouette and expression before combining the pair. Use image editing for those corrections instead of asking one video prompt to redesign and animate everything.
The preparation step stitches your photos side by side; it does not remove backgrounds or create a seamless orange room. Use compatible source backgrounds and judge the combined frame first.
A previously used image model and its cost do not determine the video quote. Check the actual selected video model, output options and Required Credits before submitting.
Two original character concepts from the prepared image stand side by side in a warm orange studio, a suspended microphone between them. Preserve readable silhouettes and contrasting outfit colors. Gentle head nods, restrained movement and a steady medium camera with both faces unobstructed.
This suggested prompt is a starting brief for a image concepts moving into a separate video workflow. It is not the original prompt for any collected video. Adapt it to the prepared image and review the actual output; a prompt cannot guarantee identity, seamless backgrounds or synchronized lyrics.
Try Nano Banana prepares one side-by-side landscape image with your left and right photos. That single image is the reference for the selected video model. The page does not independently assign a face identity to each performer in a collected clip.
The page uses an available video model for rendering. An image model can help you prepare character pictures first, but the duo upload, video settings and live credit quote belong to a separate video generation step.
No. Collected videos are visual inspiration. Selecting one changes what you can watch; it does not import its choreography, replace its performers or submit it as a hidden generation template. Unknown original prompts and models are not claimed.
Browsing references and preparing a joined image do not submit a video generation. Rendering on Try Nano Banana requires a signed-in account and enough credits for the current quote. Model and output settings determine the cost; review your balance and pricing before submitting.
Clear inputs and small movements make your image concepts moving into a separate video workflow easier to evaluate, but consistency is not guaranteed. Check both faces, outfits and left/right positions from beginning to end. Fix a poor crop before generation and reduce movement if details drift.
The image pair contains no music. Audio support follows the selected model and its displayed settings. The page does not guarantee a reference song, precise synchronized lyrics or matching choreography. Check sound separately and use audio you are permitted to publish.
It joins the two uploaded images without removing their backgrounds. Use compatible photos and inspect the composition before requesting studio details in your prompt. A seamless scene remains an output to review rather than a guaranteed preparation result.
Prepare two images that express your concept, describe one small action and review the selected video model. Compare the complete output with the original character designs before trying another direction.
Prepare my duo performance