Hermes Athena image provider

Hermes backend plugin for the OpenAI-compatible image API exposed by the Athena profile router. The router starts the local FLUX worker on demand, unloads the active LLM and Qwen3-TTS, and restores both after generation.

When the explicit Hermes model restauration is selected, reference-image requests are routed to Athena's HYPIR-SD2 worker. Creative edits in every normal chat model continue to use FLUX. Prompt text is deliberately never used for routing, so words such as "improve" cannot accidentally switch pipelines. No second Hermes provider or desktop installation is required.

Gateway installation

Install this directory on the Hermes gateway, not on each Desktop client:

$HERMES_HOME/plugins/image_gen/athena-local/
  __init__.py
  plugin.yaml

Set these secrets or environment variables on the gateway:

ATHENA_IMAGE_BASE_URL=http://192.168.1.212:8081/v1
ATHENA_IMAGE_API_KEY=<same API key accepted by the Athena router>

Then enable and select the provider:

plugins:
  enabled:
    - image_gen/athena-local

image_gen:
  provider: athena-local
  model: FLUX.2-klein-9B-fp8-beta
  max_parallel_requests: 1

Restart the Hermes gateway after changing plugin files or configuration. A second computer connected to the same gateway needs no plugin installation.

Optional overrides:

ATHENA_IMAGE_MODEL defaults to FLUX.2-klein-9B-fp8-beta.
ATHENA_RESTORATION_MODEL defaults to HYPIR-SD2.
ROUTER_API_KEY is accepted as a migration fallback.
An existing HERMES_CUSTOM_192_168_1_212_8081_API_KEY is accepted as the final fallback, so an existing Athena chat-provider setup needs no duplicate secret.