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

Wire Qwen Edit Start still to image_1 and PE-I2I identity keep.

Browse Source 
Edit no longer invents strangers when the prompt omits <image1> or PE drops image tokens; Hero stays Klein-only.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Towsty
2026-09-26 14:27:36 -05:00
co-authored by Cursor
parent ecc4c69a8b
commit 30be4bd5b0
6 changed files with 74 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/qwen21.md
+3 -1
View File
@@ -35,12 +35,14 @@ Restart Comfy **only when idle** (`COMFY_CONTROL_URL/status` → `gpu.busy=false
- Engine key: `qwen21` · UI label: **Qwen 2.1**
- **Generate** (T2I) and **Edit** (same checkpoint, second graph). Compose / Iterate / Video / Extend / Music stay disabled unless a graph exists.
- Edit requires Start still → `images.image_1`; prompt slots use `<image1>` / `<image2>`. If the user omits `<image1>`, the runner prepends `Keep the subject in <image1>.`
- Edit requires Start still → `images.image_1`; prompt slots use `<image1>` / `<image2>`. If the user omits `<image1>`, the runner prepends `Keep the identity, face, body, and pose of the person in <image1>. Apply only this change:` then their text. Hero is Klein-only and is ignored (never image_1).
- 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 Generate canvas follows the bench Aspect control on the Qwen-safe ~1 MP grid (`EmptyLatentImage`): 1:1 → 1024×1024, 16:9 → 1536×864, 9:16 → 864×1536 (and the other table rows). PE `wh_ratio` is advisory only and never sizes the canvas. Do not use native 2K bins on 16 GB.
- Edit follows `image_1` via the encode node’s latent (resolution long-edge ~1024). Do not inject a picker EmptyLatentImage onto the edit sampler.
- 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.
- 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).