Add explicit HYPIR restoration profile

This commit is contained in:
Mikei386
2026-09-07 22:52:59 +02:00
parent 2ae61baec7
commit 118e32005e
11 changed files with 593 additions and 32 deletions
@@ -4,6 +4,12 @@ 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:
@@ -40,6 +46,7 @@ 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