DigestOps
Search⌘KLog inCreate account
Archived signal · Frontier Models
ComfyUI@ComfyUIx

Manipulate objects in existing videos with Gemini Omni Flash text prompts

  • Gemini Omni Flash can modify objects and environments in existing videos using simple text prompts.
  • Iteration and specific prompting may be needed to achieve desired results.
  • The workflow is available for others to try.
how to reproduce · Use Gemini Omni Flash with a video input and a text prompt describing the desired manipulation. Iterate on the prompt as needed.
♥ 43627.9K views↗ Open the original
Share
Where this lives now

This signal is part of the DigestOps evidence archive. The living answers built on evidence like this are at Frontier Models; agents can query it as JSON at /api/v1/cards/87 or over MCP.