Gemini Media

Google Gemini image (Nano Banana) and video (Gemini Omni) generation backends for image_generate and video_generate, in one plugin built on the google-genai SDK. Image: text-to-image and reference-guided editing (up to 14 images). Video: text-, image- and reference-to-video with native audio. Model picker comes from the key's live models.list.

Good to know before installing

Prompts, reference images and the Gemini API key (GEMINI_API_KEY, falling back to GOOGLE_API_KEY, the key Hermes's own Gemini chat provider uses) are sent to generativelanguage.googleapis.com; reference-image URLs are downloaded by the plugin (public hosts only, redirects re-checked) and a local reference path can be any image file the user can read (accepted only after a magic-byte check); generation is billed to the API key's Google project; writes generated media under $HERMES_HOME/cache/generated/ and a model-list cache (key hash only) under $HERMES_HOME/cache/gemini_media/; no telemetry, shell commands, background processes or self-updates. Installs google-genai.

From the plugin's catalog listing.

How to install

Install it. Hermes asks for any API keys it needs (this one needs GEMINI_API_KEY), then asks whether to turn it on.
hermes plugins install gemini-media
Said no? Turn it on later:
hermes plugins enable gemini-media
Restart Hermes so it loads the plugin.

Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide (opens in a new tab).

Category: Images, video, music & 3D
Maintained by: bytecakelake (Community)
Needs: GEMINI_API_KEY API key
Needs Hermes: 0.21.0 or newer
Version: 0.1.2
In the catalog: 2026-10-25

Full setup & settings ↗Source code ↗

More in images, video, music & 3d

All images, video, music & 3d plugins

New Hermes Agent updates every day on X. Follow @HermesWatcher

← All plugins