Gemini · Multimodal

Gemini multimodal plan

Plan combining text + image/video inputs.

All topics / Gemini prompts

Prompt shell

Replace highlighted brackets, then copy.

Given text + image/video: summarize content, answer [question], and output next-step suggestions in bullets. Keep to [words] words.
How to use
  • question - replace the bracketed field with your info
  • words - replace the bracketed field with your info
Provide (Inputs)
  • Question
  • Words limit
  • Focus (objects/actions)
  • Tone
Expected output (Outputs)
  • Summary
  • Answer
  • Next steps
Tips
  • State confidence if visuals are unclear.
  • Separate description from inference.
  • Cite any text detected in the media.
Related prompts
More Gemini prompts Ask the encyclopedia