Add global specialist caption override

This commit is contained in:
Sleeps
2026-10-07 13:23:50 +01:00
parent e1be6c7991
commit 80f0f41a53
+3
View File
@@ -186,6 +186,7 @@ A lightweight local image classifier routes each frame to the appropriate captio
OLLAMA_URL=http://127.0.0.1:11434
CAPTION_GENERAL_MODEL=huihui_ai/qwen3-vl-abliterated:4b-instruct-q4_K_M
CAPTION_SPECIALIST_MODEL=aha2025/llama-joycaption-beta-one-hf-llava:Q4_K_M
CAPTION_FORCE_SPECIALIST=false
CAPTION_TIMEOUT_SECONDS=180
CAPTION_MAX_TOKENS=120
CAPTION_PROMPT_FILE=./data/caption_prompt.txt
@@ -210,6 +211,8 @@ ollama pull aha2025/llama-joycaption-beta-one-hf-llava:Q4_K_M
The router model is downloaded automatically by Transformers on the machine running this project the first time it is used.
Set `CAPTION_FORCE_SPECIALIST=true` to bypass the routing classifier entirely and send every selected frame to `CAPTION_SPECIALIST_MODEL`. This is a hard global override: per-item general/specialist tags and the normal router threshold/context are ignored while it is enabled. The override is included in the saved routing policy, so enabling it makes old general routes stale and they are converted to specialist routes on the next caption/resume run without re-running SigLIP. Frames that already have a caption from the specialist model can be retained.
Inspect routing scores without generating captions:
```bash