towsty/aigen
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Pass through PE refusals to the raw prompt and pin adult PE system prompts.

Browse Source 
Enhance no longer fails the studio job when the rewrite refuses or comes back empty; host prompt copies keep the official steps plus the adult appendix after a node re-clone.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Towsty
2026-09-26 14:46:24 -05:00
co-authored by Cursor
parent 99b61e67d7
commit a51118d92a
8 changed files with 512 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/qwen21.md
+2
View File
@@ -43,6 +43,8 @@ Restart Comfy **only when idle** (`COMFY_CONTROL_URL/status` → `gpu.busy=false
- Optional **Enhance prompt** (off by default): runs a separate PE-only Comfy graph (`CLIPLoader` + rewrite node), then frees VRAM and queues the existing T2I/Edit graph with the rewritten prompt. Never loads PE CLIP + DiT together on 16 GB. Fail closed if `parse_ok` is false or the rewrite is empty.
- Generate + Enhance → PE-T2I only (`pe_t2i`). No images.
- Edit + Enhance → PE-I2I only (`pe_i2i`) with the same Start still on `image_1`. If the rewrite drops every `<imageN>` token, stitch `Keep the identity…` onto the rewrite before Edit. Never fall back to PE-T2I on Edit.
- If PE refuses or returns an empty/gutted rewrite, the job continues with `promptRaw` (Edit still gets the keep-identity prefix). Details shows `Enhance skipped (model refused) — used your prompt.` (`enhance.refused`).
- Host PE system prompts live in `host/qwen21-pe-prompts/` and are copied onto the node pack by `scripts/setup-qwen21.ps1` (official steps + Adult appendix). Do not swap Heretic PE weights on 16 GB.
- PE weights (int8 only): `text_encoders\qwen3.5_9b_qwen_image_2.1_pe_{t2i,i2i}.int8_convrot.safetensors` — do not replace the image TE `qwen3vl_8b_int8_convrot.safetensors`.
- Optional **Turbo** (off by default): Viggle DMD LoRA `Qwen-Image-2.1-viggle-turbo-v0.2.1-6step-lora-r128.safetensors` on the same Q8 GGUF via `ViggleTurboLora` + `ViggleTurboSigmas` (`1.0, 0.9375, 0.875, 0.75, 0.5, 0.25`), 6 steps, CFG 1, empty negative. Not a new engine. Enhance prompt stays compatible and is recommended with Turbo.
- Custom node: `ComfyUI-Viggle-Turbo` (`viggle_turbo.py`). Do not merge the LoRA with stock `LoraLoaderModelOnly` (lossy on int8/bf16).