comfyui/README: add a from-scratch quickstart

ComfyUI install, node clone, the three model files with direct URLs and sizes,
how to start it and where to open the workflow. Measured: ~2 s per image and
~12.6 GiB peak VRAM at 768x1280 on an RTX 5090.

comfyui/README.md

@@ -7,33 +7,67 @@ This folder contains a ComfyUI workflow that drives **FLUX.2-klein-4B** with the
 - Custom node (the two `KleinAdapter` nodes):
   [github.com/recoilme/klein-qwen3-adapter-comfyui](https://github.com/recoilme/klein-qwen3-adapter-comfyui)
 
-## 1. Install the custom node
+## Quickstart (from scratch)
+
+From an empty machine to a first image — verified end to end on ComfyUI 0.36
+(~8.4 GiB of downloads, ~1.4 GiB more on the first run):
 
 ```bash
-cd ComfyUI/custom_nodes
+# 1. ComfyUI itself — skip if you already have one
+git clone https://github.com/comfyanonymous/ComfyUI
+cd ComfyUI
+python -m venv .venv && . .venv/bin/activate       # Python 3.10+
+pip install -r requirements.txt
+
+# 2. the custom node that provides the two KleinAdapter nodes
+cd custom_nodes
 git clone https://github.com/recoilme/klein-qwen3-adapter-comfyui
-# restart ComfyUI
+cd ..
+
+# 3. models (paths are relative to ComfyUI/)
+mkdir -p models/klein_adapter
+curl -L -o models/diffusion_models/flux-2-klein-4b.safetensors \
+  https://huggingface.co/Comfy-Org/flux2-klein/resolve/main/split_files/diffusion_models/flux-2-klein-4b.safetensors
+curl -L -o models/vae/flux2-vae.safetensors \
+  https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/vae/flux2-vae.safetensors
+curl -L -o models/klein_adapter/adapter_v14_bal.safetensors \
+  https://huggingface.co/AiArtLab/qwen3-0.6b-4b-adapter/resolve/main/adapter_v14_bal.safetensors
+# Qwen3-0.6B (1.4 GiB) needs no manual step: it is pulled from the Hub on the first
+# run. Offline machine: fetch it beforehand with `hf download Qwen/Qwen3-0.6B`.
+
+# 4. start ComfyUI
+python main.py                                      # then open the URL it prints (:8188)
+
+# 5. in the UI: Workflow -> Open ->
+#    custom_nodes/klein-qwen3-adapter-comfyui/workflows/flux2_klein_qwen3_06b_adapter.json
+#    (or drag this folder's JSON onto the canvas), type a prompt, press Run.
 ```
 
-## 2. Put the models in place
+768×1280 with the distilled model takes ~2 s per image on an RTX 5090 and peaks
+at ~12.6 GiB of VRAM (mostly the klein DiT itself).
+
+## Models
 
 ```
 ComfyUI/models/
 ├── diffusion_models/
-│   └── flux-2-klein-4b.safetensors        # distilled klein DiT (stock)
+│   └── flux-2-klein-4b.safetensors        # distilled klein DiT (stock), 7.2 GiB
 ├── vae/
-│   └── flux2-vae.safetensors              # stock Flux2 VAE (untouched)
+│   └── flux2-vae.safetensors              # stock Flux2 VAE (untouched), 321 MiB
 └── klein_adapter/                          # created automatically by the node
-    └── adapter_v14_bal.safetensors        # this adapter
+    └── adapter_v14_bal.safetensors        # this adapter, 840 MiB
 ```
 
-- `flux-2-klein-4b.safetensors`: the klein DiT in ComfyUI format (e.g. from
-  [Comfy-Org/flux2-klein](https://huggingface.co/Comfy-Org/flux2-klein)).
-- `flux2-vae.safetensors`: from [Comfy-Org/flux2-dev](https://huggingface.co/Comfy-Org/flux2-dev).
+- `flux-2-klein-4b.safetensors`: the klein DiT in ComfyUI format, from
+  [Comfy-Org/flux2-klein](https://huggingface.co/Comfy-Org/flux2-klein)
+  (`split_files/diffusion_models/`). The base model `flux-2-klein-base-4b.safetensors`
+  works too (see the settings below).
+- `flux2-vae.safetensors`: from [Comfy-Org/flux2-dev](https://huggingface.co/Comfy-Org/flux2-dev)
+  (`split_files/vae/`).
 - `adapter_v14_bal.safetensors`: from this repo (see above).
 - Qwen3-0.6B is downloaded automatically from HF on first use.
 
-## 3. Run
+## Run
 
 1. Load `flux2_klein_qwen3_06b_adapter.json` in ComfyUI.
 2. Set your prompt in the **Positive prompt** node.