Animate architectural photos with Gemini Omni

Gemini Try it →Watch full video →AI Master · May 2026

Demo summary

The user combines a reference image of a brutalist building with a text prompt to generate a time-lapse video with moving clouds and shadows.

Step-by-step

Upload a reference image of the building or architecture.
Enter a text prompt describing the desired animation and lighting effects.
Combine the text and image inputs to generate the video.

Tips

Use specific descriptive phrases like 'golden hour ending' or 'shadows sweeping' to guide the animation's atmosphere.

Highlights

“The model respected the architecture from the reference photo and animated around it rather than replacing it. That's the Gemini intelligence layer doing real work.”

All demos from “Goodbye Seedance... Gemini Omni: Google’s New AI Video Model is INSANE”

1:500:30Generate physics-based video with Gemini OmniThe user demonstrates Gemini Omni's physics understanding by prompting it to create a video of a ceramic teapot falling and shattering on a tile floor.Gemini· Text to Video
2:200:33Sequence multi-element scenes in Gemini OmniA demonstration of cause-and-effect logic where Gemini Omni generates a street market scene with wind affecting multiple objects in sequence.Gemini· AI Realistic Image Generator
2:550:30Animate architectural photos with Gemini OmniCurrentThe user combines a reference image of a brutalist building with a text prompt to generate a time-lapse video with moving clouds and shadows.Gemini· Image to Video
5:070:45Create a talking AI avatar in Gemini OmniThe video walks through the process of recording a 30-second clip to train Gemini Omni to generate a talking digital avatar of the user.GGoogle Omni· AI Avatar Video Generator
6:271:22Apply visual style presets in Gemini OmniThe user demonstrates various style templates including Noir, 80s music video, Origami, and Pixelate to transform the look of generated video clips.GGoogle Omni· Video to Video
9:010:45Generate animated memes with Gemini OmniThe 'Meme Me' template is shown taking a user photo and automatically applying meme formatting, typography, and subtle facial animation.Gemini· AI GIF Generator
10:000:52Conversational video editing in Gemini OmniThe user demonstrates editing a video by simply typing chat commands to change the environment from a park to a beach without regenerating the subject.Gemini· AI Video Editor
10:520:43Precise object editing and lighting effectsGemini Omni is shown performing micro-edits such as changing a jacket's color and adding a light-tracking lens flare through text commands.Gemini· AI Inpainting
13:340:57Rerender and extend real footageThe user imports handheld footage and uses Gemini Omni to apply a cinematic color grade and extend the camera motion logic.GGoogle Omni· Video to Video
14:540:37Create video sequences from multiple photosGemini Omni takes five separate photos and generates a coherent 10-second video sequence with smooth transitions and a consistent mood.Gemini· Image to Video
15:350:41Animate static infographics with Gemini OmniThe user demonstrates feeding a flat chart into the model and prompting it to animate the data points in a logical reveal sequence.Gemini· AI Animation Generator
Watch “Goodbye Seedance... Gemini Omni: Google’s New AI Video Model is INSANE” →

Image to Video

0:360:05Convert sketches to video with Gemini OmniGemini Omni incorporates visual instructions from a drawing to generate a full, coherent video sequence.Google
6:540:26Create a video montage from imagesThe user demonstrates the 'montage' template in Gemini Omni by uploading four images of dogs to generate a cohesive video clip.Paul J Lipsky
6:450:18Image-to-video with Google VidsThe demo shows using an image created with 'Nano Banana' as a starting point for video generation in Google Vids.Malva AI
2:540:43Animate an image with Google VidsThe user shows how to upload a screenshot and use the 'Animate an image' feature in Google Vids to create a contiguous video scene.Paul J Lipsky
9:451:34Generating AI video with VEO and image referencesShows how to use a text prompt and a reference image to generate a custom 8-second video clip of an avatar in a specific setting using VEO.Dean Stokes - Tech Tutorials
12:471:34AI image generation and animationThe user generates an AI image of a YouTuber at a beach and then uses the 'convert to video' feature to animate it based on a text prompt.Justin Brown - Primal Video
2:550:30Animate architectural photos with Gemini OmniCurrentThe user combines a reference image of a brutalist building with a text prompt to generate a time-lapse video with moving clouds and shadows.AI Master
14:540:37Create video sequences from multiple photosGemini Omni takes five separate photos and generates a coherent 10-second video sequence with smooth transitions and a consistent mood.AI Master
2:192:21Extend AI video duration using image-to-videoThe creator shows a workflow to extend a story by taking a screenshot of the last frame, removing the logo in an external editor, and using the 'animate an image' feature in Google Vids to generate a continuous second clip.Educraft
4:561:19Using 'Ingredients' for object consistency in VeoThe demonstration shows how to upload a specific image (a blue flask) into the 'Ingredients' section of the Veo tool in Google Vids to ensure that specific object appears in the generated video clip.Educraft
6:141:06Animate images with Google Veo 3.1 in Google VidsThe creator demonstrates uploading a still image to Google Vids and using the Veo 3.1 model to generate an animated clip with automatic lip-sync and sound effects.The AI Blueprint
3:001:11Animate an image to continue a sceneThe user takes a screenshot of a generated video frame and uses the 'animate an image' feature to create a follow-up shot where the character turns around.AI Mind Revolution