Image generation: create images from a text prompt

What Image generation is for

The image generation tool lets Hermes turn a prompt into a picture during a conversation. FAL.ai is the main backend, with a default fast FLUX model and a menu of others that trade speed against cost. You can also route through OpenAI, OpenRouter, xAI, Krea, Meta's model API, or the Nous Tool Gateway if you have a paid Nous Portal subscription. You choose the backend and model interactively in hermes tools, and the choice is saved to config.yaml. It suits thumbnails, social graphics and quick concept images without leaving the chat.

What you need

• Credentials for the active backend, for example FAL_KEY, OPENAI_API_KEY or KREA_API_KEY
• Or a paid Nous Portal subscription to use the Tool Gateway instead of your own FAL key

Set it up

1. 1

   Create an API key in your fal.ai dashboard and add FAL_KEY to your environment

2. 2

   Run hermes tools, select Image Generation, choose a backend, then pick a model

3. 3

   Or set it directly, for example hermes config set image_gen.provider fal and hermes config set image_gen.model <model-id>

Check it works

• hermes tools marks the active model as currently in use
• Confirm image_gen.provider and image_gen.model in config.yaml
• Set IMAGE_TOOLS_DEBUG=true and inspect the per-session debug log under ./logs/

Limits and failure points

• Image editing only works on edit-capable models; text-to-image-only models reject image inputs
• Backend image URLs expire after hours or days, though Hermes caches files locally
• Unsupported parameters are silently dropped, and per-image backends do not record token usage

Spotted something wrong or out of date? Tell us on X at @HermesWatcher↗ (opens in a new tab) and we will fix it.