# Qwen Image 2.1 (engine `qwen21`) — host weights + Comfy graph

## Host paths (this RTX 5080 box)

| Role | Resolved path |
|---|---|
| ComfyUI root (Klein / host agent `ComfyUI (1)`) | `C:\Users\ianjm\AppData\Local\Comfy-Desktop\ComfyUI-Installs\ComfyUI (1)\ComfyUI` |
| Models root (Desktop Shared via `shared_model_paths.yaml`) | `C:\Users\ianjm\AppData\Local\Comfy-Desktop\ComfyUI-Shared\models` |

Weights must land under Shared so every Desktop instance sees them:

- `diffusion_models\qwen-image-2.1-Q8_0.gguf` (~7.59 GiB) — from `abenzerps/Qwen-Image-2.1-Uncensored-GGUF`
- `text_encoders\qwen3vl_8b_int8_convrot.safetensors` — from `Comfy-Org/Qwen-Image-2.1` (INT8; BF16 8B VL OOMs on 16 GB)
- `vae\qwen_image_2.1_vae_bf16.safetensors` — from `Comfy-Org/Qwen-Image-2.1` (**not** the old Qwen-Image 1.0 VAE)

Custom node: `custom_nodes\ComfyUI-GGUF` (`UnetLoaderGGUF`). Do not install a second GGUF pack.

## Setup

```powershell
powershell -ExecutionPolicy Bypass -File scripts\setup-qwen21.ps1
```

DiT download uses the exact host invocation:

```powershell
hf download hf://abenzerps/Qwen-Image-2.1-Uncensored-GGUF/qwen-image-2.1-Q8_0.gguf
```

That lands in the Hugging Face hub cache; the setup script copies it into Shared `diffusion_models`. The abenzerps GGUF ships with `kv_count=0` (no `general.architecture`) **and** Q8_0-quantized 1D RMSNorm weights (logical 128 → packed 136), which breaks Comfy’s fused `rms_rope`. `scripts/tag-qwen21-gguf.py` rewrites the file with `general.architecture=qwen_image` and promotes small/1D tensors to F32 so city96 `UnetLoaderGGUF` can load it.

Restart Comfy **only when idle** (`COMFY_CONTROL_URL/status` → `gpu.busy=false`). Confirm `object_info` lists `UnetLoaderGGUF` and the three filenames.

## App

- Engine key: `qwen21` · UI label: **Qwen 2.1**
- Generate (T2I) only in this build. Edit / Compose / Iterate / Video disable with: “Qwen 2.1 is T2I in this build”.
- Sampler defaults: euler / simple / cfg **1** / steps **25** · `ModelSamplingAuraFlow` shift **3.1**
- Default canvas **1024×1024** (aspect 16:9 / 9:16 / 1:1 → long-edge square via `TextEncodeQwenImage21` resolution; multiples of 32). Drop to 768 if VRAM errors.
- No hero / locks / Klein LoRA stack on this engine.

Graph: `server/assets/studio2_qwen21_t2i.json`.