Wire Qwen Enhance prompt toggle through Studio 2 and the runner.

Queue PE first when enabled, fail closed on parse_ok, free VRAM, then run the existing T2I or Edit graph with the rewrite.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Towsty
2026-09-26 10:25:44 -05:00
co-authored by Cursor
parent e0292c8d2a
commit 2842855c7b
9 changed files with 153 additions and 47 deletions
+4 -2
View File
@@ -39,6 +39,8 @@ Restart Comfy **only when idle** (`COMFY_CONTROL_URL/status` → `gpu.busy=false
- Face / outfit locks stay Klein semantics — they do not drive Qwen slots.
- Sampler defaults: euler / simple / cfg **1** / steps **25**. Edit uses `QwenImage21Cache` (device auto, dtype int8). T2I uses `ModelSamplingAuraFlow` shift **3.1**.
- Default canvas **1024×1024** (aspect 16:9 / 9:16 / 1:1 → long-edge ~1024 via `TextEncodeQwenImage21` resolution; multiples of 32). Edit with aspect `auto` follows `image_1` aspect at ~1024.
- No hero / locks / Klein LoRA stack on this engine.
- 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.
- 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`.
- Custom node: `ComfyUI-Qwen-Image-2.1-Prompt-Enhancer` (`QwenImage21_T2IPromptRewrite` / `QwenImage21_EditPromptRewrite`).
Graphs: `server/assets/studio2_qwen21_t2i.json`, `server/assets/studio2_qwen21_edit.json`.
Graphs: `server/assets/studio2_qwen21_t2i.json`, `server/assets/studio2_qwen21_edit.json`, `server/assets/studio2_qwen21_pe_t2i.json`, `server/assets/studio2_qwen21_pe_edit.json`.