Ethanfel/ComfyUI-Prompt-Calibrator
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Drop the SxCP prefix from this pack's node names

Browse Source 
SxCP is the Prompt-Builder pack's brand; these are Calibrator nodes. Renamed the
display names (cosmetic only — class_types unchanged, so no workflows/bridge break):
'External Prompt (Receptor)', 'Audio Prompt Guide', 'Audio Wave + Segments'; renamed
the JS extension id too. Kept the genuine Prompt-Builder (SxCP) references in the docs.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Ethanfel
2026-07-04 22:36:50 +02:00
co-authored by Claude Opus 4.8
parent 57b459b956
commit 98d3520775
6 changed files with 11 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+4 -4
View File
@@ -15,7 +15,7 @@ until the generated image matches the reference.
| Component | What it is |
|---|---|
| `Qwen3-VL Image Judge (Calibrator)` | scores generated vs reference, writes analysis to disk for the agent |
| `SxCP External Prompt (Receptor)` | stable injection point; the agent sets `prompt/negative/seed` here per queue |
| `External Prompt (Receptor)` | stable injection point; the agent sets `prompt/negative/seed` here per queue |
| `agent_bridge.py` | one CLI call = one iteration (inject → `POST /prompt` → wait → print analysis JSON) |
## The "vllm node": `Qwen3-VL Image Judge (Calibrator)`
@@ -62,7 +62,7 @@ Set **`json_output=true`** for JSON-producing system prompts — it extracts the
from the reply (stripping any reasoning, prose, or ```fences) and returns it clean and
re-serialized (falls back to raw text if none parses). Works even with `enable_thinking` on.
## Audio-guided prompts (`SxCP Audio Prompt Guide`)
## Audio-guided prompts (`Audio Prompt Guide`)
For audio-driven video (e.g. LTX prompt-relay timed to music), the `AudioPromptGuide` node
turns an audio clip + your free-text motion **notes** into inputs the vision model can use:
@@ -78,7 +78,7 @@ subject image** and the **waveform**, use the two image slots (chat mode sees bo
```
your subject image ───────────────────────────────────► Judge.reference_image (IMAGE 1)
LoadAudio ─► SxCP Audio Prompt Guide ─┬─ waveform_image ─► Judge.generated_image (IMAGE 2)
LoadAudio ─► Audio Prompt Guide ─┬─ waveform_image ─► Judge.generated_image (IMAGE 2)
(notes: "seg3: fast on the drop") └─ audio_summary ─► Judge.user_prompt
(prompts/ltx_audio_relay_system_prompt.txt) ─────────► Judge.system_prompt
Judge (mode=chat, json_output=true) ─► LTX beats JSON
@@ -101,7 +101,7 @@ seg1: slow dreamy intro # by segment number (also "1:" or "S1:")
cinematic, moody grade # no prefix = global (applies throughout)
```
### Interactive: `SxCP Audio Wave + Segments`
### Interactive: `Audio Wave + Segments`
Same outputs, but with an in-node waveform widget: **upload** an audio clip, **play** it,
and **click the waveform** to place segment boundaries — click to add a split, drag to