Creating Images, Video and Music
Swipe um das Menü anzuzeigen
Most assistants hand creative generation off to a separate product. Gemini keeps it in the chat, and that placement is the point: you refine an image or a video by continuing the conversation instead of rewriting a prompt from scratch in another tab.
Images
Pick the image tool and describe what you want. Then keep talking to it. Change the background, drop an object, adjust the color, or ask for the same character again in a different scene, and the edit applies to the picture you already have.
With Photos connected, you can put yourself or people you know into a generated scene without uploading anything manually.
Video
The video tool takes text, a still image, or footage you already shot, and produces a short video. It also edits uploaded clips from a plain description rather than a timeline: change the background, apply an effect, use a template, or drop in an avatar that looks and sounds like you.
Video is the most expensive thing in the app. It sits on paid tiers and consumes far more of your allowance than text, so plan the shot before you generate rather than iterating twenty times.
Music
The music tool generates instrumental tracks from a description of mood, genre, tempo, and instruments. It fits background audio for a video or a presentation, where you need something that does not clash with the narration and does not require a license.
Everything generated here carries an invisible SynthID watermark identifying it as AI-made. Check the rules of wherever you plan to publish, since many platforms now require AI content to be labeled.
Danke für Ihr Feedback!
Fragen Sie AI
Fragen Sie AI
Fragen Sie alles oder probieren Sie eine der vorgeschlagenen Fragen, um unser Gespräch zu beginnen