Gemini: Generate and extend video with 'Metallic' template
Gemini
Demo summary
The creator uses the Gemini Omni 'metallic' template to generate a video of his avatar and then uses a follow-up prompt to continue the scene from the last frame.
Step-by-step
- Select the 'Metallic' template
- Upload or select your avatar
- Generate the initial video without additional prompts
- Enter a follow-up prompt to continue the scene from the last frame
- Specify the desired visual progression for the extension
Options
- Continue the conversation to request specific changes to the video
- Ask the AI to continue the video from the last frame
Tips
- Use the last frame of the previous clip as a reference point to maintain continuity in the next generation
Highlights
“what's really cool about Omni is that you can then continue with the conversation and ask for any changes or for it to continue the video”
All demos from “How To Use Gemini Omni (Google’s Wild Video Model)”
- 1:350:40Generate and extend video with 'Metallic' templateCurrentThe creator uses the Gemini Omni 'metallic' template to generate a video of his avatar and then uses a follow-up prompt to continue the scene from the last frame.Gemini· Video to Video
- 3:180:19Generate video from custom text promptThe user demonstrates Gemini Omni's text-to-video capability by prompting it to show his avatar in a suit eating spaghetti at a restaurant.Gemini· Text to Video
- 6:230:31Add objects to uploaded video footageThe creator uploads a real-world video of mountains and uses Gemini Omni to insert an active volcano into the background of the scene.Gemini· AI Video Editor
- 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.Gemini· Image to Video
- Watch “How To Use Gemini Omni (Google’s Wild Video Model)” →
Video to Video
- 1:350:40Generate and extend video with 'Metallic' templateCurrentThe creator uses the Gemini Omni 'metallic' template to generate a video of his avatar and then uses a follow-up prompt to continue the scene from the last frame.Paul J Lipsky