demobook

Google Whisk: Generate image-to-video with audio in Google Veo 3

Demo summary

The creator demonstrates using Google Flow to access Veo 3, uploading an image from Open Art, and entering a prompt to generate a video with synchronized audio and dialogue.

Step-by-step

  1. Search for Google Flow and click the first link
  2. Click Create a new project
  3. Switch the model from Text to Video to Frame to Video
  4. Upload your starting image
  5. Crop the image as needed
  6. Enter a detailed prompt describing the desired movement and handheld style
  7. Add the dialogue text at the end of the prompt

Options

  • Generate the initial image using Midjourney, Hicksfield, or Open Art

Tips

  • Include 'no subtitles' in your prompt to avoid broken text overlays in the video
  • Describe the camera style (e.g., 'handheld vlog style at arms length') to increase realism
  • Add specific movement details to the prompt for a more realistic result

Image to Video

  1. 4:512:48Convert images to talking AI videos with Google FloThe creator uses Google Flo AI (incorporating the Vidu 1.5 model) to upload images and JSON prompts from ChatGPT to generate video clips with synchronized dialogue and background music.Learn AI with Ritika
  2. 9:001:53Animate images with Whisk AIThe user demonstrates generating an image from a prompt in Whisk AI and then using the animation icon to transform that static image into a video.AI Playground
  3. 2:030:52Generate image-to-video with audio in Google Veo 3CurrentThe creator demonstrates using Google Flow to access Veo 3, uploading an image from Open Art, and entering a prompt to generate a video with synchronized audio and dialogue.Dan Kieft
  4. 10:360:39Create a consistent character in Google FlowThe creator demonstrates how to upload a reference image of himself to Google Flow, name the character, and use an '@' mention in a prompt to generate a video of that specific person winning a race.AI Samson
  5. 7:080:42Image-to-video with Google Veo 3The user demonstrates the 'frames to video' feature in Google Flow by uploading a jungle scene image and providing a complex prompt to animate specific animals within the frame.Tim Harris AI