# ⚙️ ComfyUI Setup Guide (AMD ROCm)

This guide covers installing ComfyUI with FLUX.1-schnell on a Fedora Linux system with an AMD GPU.

## Prerequisites

- AMD GPU with ROCm support (tested: RX 7900 XTX)
- Fedora Linux (tested: Fedora 43 / kernel 6.19)
- Python 3.11+
- ~15GB free disk space (model weights)
- HuggingFace account with FLUX license accepted

## Step 1: Install ComfyUI

ComfyUI is **not on PyPI** — must be cloned from source:

```bash
cd ~
git clone https://github.com/comfyanonymous/ComfyUI
cd ComfyUI
python -m venv .venv
source .venv/bin/activate

# Install PyTorch ROCm build (CRITICAL for AMD GPUs)
pip install torch torchvision --index-url https://download.pytorch.org/whl/rocm6.2

# Install ComfyUI dependencies
pip install -r requirements.txt
```

## Step 2: Download FLUX.1-schnell

FLUX.1-schnell is **gated on HuggingFace** — you must:
1. Create a HuggingFace account
2. Accept the FLUX.1-schnell license at https://huggingface.co/black-forest-labs/FLUX.1-schnell
3. Generate an access token at https://huggingface.co/settings/tokens

```bash
# Install huggingface_hub
pip install huggingface_hub

# Download model (requires HF token)
huggingface-cli download black-forest-labs/FLUX.1-schnell \
  flux1-schnell.safetensors \
  --local-dir ~/ComfyUI/models/checkpoints \
  --token YOUR_HF_TOKEN_HERE
```

## Step 3: Download VAE and CLIP Models

FLUX.1-schnell also requires VAE and CLIP text encoders:

```bash
# VAE
huggingface-cli download black-forest-labs/FLUX.1-schnell \
  ae.safetensors \
  --local-dir ~/ComfyUI/models/vae

# CLIP models (T5 and CLIP-L)
huggingface-cli download comfyanonymous/flux_text_encoders \
  t5xxl_fp8_e4m3fn.safetensors clip_l.safetensors \
  --local-dir ~/ComfyUI/models/clip
```

## Step 4: Start ComfyUI

```bash
cd ~/ComfyUI

# AMD GPU REQUIRES this environment variable
HSA_OVERRIDE_GFX_VERSION=11.0.0 \
  nohup .venv/bin/python main.py --listen --port 8188 > /tmp/comfyui.log 2>&1 &

echo "ComfyUI PID: $!"
```

> ⚠️ `HSA_OVERRIDE_GFX_VERSION=11.0.0` is mandatory for RX 7900 XTX on ROCm. Without it, model loading fails silently.

## Step 5: Verify ComfyUI is Running

```bash
curl http://localhost:8188/system_stats
# Should return JSON with GPU info
```

## Step 6: Configure mcp-image-gen

```bash
cd /home/pplate/pi_mcps/mcp/mcp-image-gen

# Environment variables (set in .roo/mcp.json or shell):
# COMFYUI_URL=http://localhost:8188
# IMAGE_OUTPUT_DIR=~/Pictures/mcp-generated
# COMFYUI_TIMEOUT=120
```

## Performance

| GPU | Model | Resolution | Steps | Time |
|---|---|---|---|---|
| AMD RX 7900 XTX | FLUX.1-schnell | 1024×1024 | 4 | ~8s |
| AMD RX 7900 XTX | FLUX.1-schnell | 1280×512 | 4 | ~7s |

## Troubleshooting

| Problem | Solution |
|---|---|
| `HTTP 401` downloading model | Accept FLUX license on HuggingFace first |
| GPU not detected | Ensure `HSA_OVERRIDE_GFX_VERSION=11.0.0` is set |
| `Connection refused` from mcp-image-gen | Start ComfyUI first, check port 8188 |
| Slow generation (>60s) | ComfyUI may be running on CPU — check ROCm install |
| Ollama image gen | As of April 2026: macOS-only, not available on Linux |