Running the NSFW Version of Qwen-Image-Edit on RunPod

I wanted to generate 3-view reference sheets for a 3D model base mesh, so I tried running the NSFW variant of Qwen-Image-Edit (Phr00t AIO) on RunPod. This comes after checking local specs and putting together a setup guide — this time was the first real run. Things went sideways: RTX 4090 (24GB) didn’t work, and I finally got it running on RTX 5090 (32GB).

What I Tried Today

Failure on RTX 4090 (24GB VRAM)

Environment

• RunPod RTX 4090 (24GB VRAM)
• Template: runpod/comfyui:latest
• ComfyUI path: /workspace/runpod-slim/ComfyUI/

Why It Failed

• Phr00t AIO NSFW v18.1 (28GB) doesn’t fit in 24GB VRAM
• --lowvram option didn’t help
• FP8 version (20GB) requires VAE/Text Encoder separately, making the setup complex

Models I Tried

1. Phr00t AIO NSFW v18.1 (28GB)

• Path: models/checkpoints/v18/Qwen-Rapid-AIO-NSFW-v18.1.safetensors
• Result: Failed — 28GB doesn’t fit in 24GB VRAM, froze during load
• --lowvram didn’t help

2. 1038lab FP8 (20GB)

• Path: models/checkpoints/fp8/Qwen-Image-Edit-2511-FP8_e4m3fn.safetensors
• Result: VAE error — this file is diffusion model only; VAE/Text Encoder required separately
• Error: ERROR: VAE is invalid: None

---

What I Learned

1. Model Configuration Differences

Phr00t AIO Version (All-In-One)

• VAE/CLIP integrated
• Self-contained in one file
• But 28GB doesn’t fit in 24GB VRAM

Official FP8 / 1038lab FP8

• Diffusion model only
• Requires separately:
  • VAE: qwen_image_vae.safetensors
  • Text Encoder: qwen_2.5_vl_7b_fp8_scaled.safetensors

2. Required Custom Node

Standard CLIPTextEncode won’t work — you need TextEncodeQwenImageEditPlus.

This is Phr00t’s modified version of ComfyUI’s standard nodes_qwen.py. Install it with:

# Run from the ComfyUI directory
cd comfy_extras
wget https://huggingface.co/Phr00t/Qwen-Image-Edit-Rapid-AIO/resolve/main/fixed-textencode-node/nodes_qwen.py -O nodes_qwen.py

Source: https://huggingface.co/Phr00t/Qwen-Image-Edit-Rapid-AIO/tree/main/fixed-textencode-node

3. Workflow Differences

Standard SD/FLUX workflow (CheckpointLoader → LoRA → KSampler) doesn’t work. A Qwen-specific node setup is required.

---

Recommended Setup by VRAM Size

VRAM	Recommended Setup	Notes
12GB	GGUF Q2_K (7.4GB)	Lightest, quality somewhat reduced
16GB	GGUF Q4_K_M (13.3GB)	Balanced, recommended
24GB	GGUF Q5_K_M (15.1GB) or Official FP8 split setup	High quality
32GB	Phr00t AIO NSFW (28GB)	Full size, best quality

---

Options for RTX 4090 (24GB VRAM)

Option A: Use GGUF (Recommended)

Q4_K_M is about 13GB, fits comfortably in 24GB VRAM. NSFW-capable GGUF quantization.

Required custom node:

cd /workspace/ComfyUI/custom_nodes
git clone https://github.com/city96/ComfyUI-GGUF
pip install --upgrade gguf

Required files:

models/unet/
  └── Qwen-Rapid-AIO-NSFW-v18.1-Q4_K_M.gguf

models/text_encoders/
  └── Qwen2.5-VL-7B-Instruct-abliterated-Q4_K_M.gguf
  └── mmproj-xxx.gguf (must be in the same directory)

models/vae/
  └── pig_qwen_image_vae_fp32-f16.gguf

Download:

pip install huggingface_hub

# GGUF main model
cd /workspace/ComfyUI/models/unet
python3 -c "from huggingface_hub import hf_hub_download; hf_hub_download('Phil2Sat/Qwen-Image-Edit-Rapid-AIO-GGUF', 'Qwen-Rapid-AIO-NSFW-v18.1-Q4_K_M.gguf', local_dir='./')"

# Text Encoder (abliterated version)
cd /workspace/ComfyUI/models/text_encoders
python3 -c "from huggingface_hub import snapshot_download; snapshot_download('Phil2Sat/Qwen-Image-Edit-Rapid-AIO-GGUF', allow_patterns='Qwen2.5-VL-7B-Instruct-abliterated/*', local_dir='./')"

# VAE
cd /workspace/ComfyUI/models/vae
python3 -c "from huggingface_hub import hf_hub_download; hf_hub_download('calcuis/pig-vae', 'pig_qwen_image_vae_fp32-f16.gguf', local_dir='./')"

Download source: https://huggingface.co/Phil2Sat/Qwen-Image-Edit-Rapid-AIO-GGUF

Option B: Official FP8 Split Setup

SFW version. Loads VAE, Text Encoder, and Diffusion Model separately.

Required files:

models/diffusion_models/
  └── qwen_image_edit_fp8_e4m3fn.safetensors

models/vae/
  └── qwen_image_vae.safetensors

models/text_encoders/
  └── qwen_2.5_vl_7b_fp8_scaled.safetensors

models/loras/
  └── Qwen-Image-Lightning-4steps-V1.0.safetensors (optional, for 4-step generation)

Download:

pip install huggingface_hub

cd /workspace/ComfyUI/models

# Diffusion Model
python3 -c "from huggingface_hub import hf_hub_download; hf_hub_download('Comfy-Org/Qwen-Image-Edit_ComfyUI', 'qwen_image_edit_fp8_e4m3fn.safetensors', local_dir='./diffusion_models/')"

# VAE
python3 -c "from huggingface_hub import hf_hub_download; hf_hub_download('Comfy-Org/Qwen-Image_ComfyUI', 'qwen_image_vae.safetensors', local_dir='./vae/')"

# Text Encoder
python3 -c "from huggingface_hub import hf_hub_download; hf_hub_download('Comfy-Org/Qwen-Image_ComfyUI', 'qwen_2.5_vl_7b_fp8_scaled.safetensors', local_dir='./text_encoders/')"

# Lightning LoRA (optional)
python3 -c "from huggingface_hub import hf_hub_download; hf_hub_download('Comfy-Org/Qwen-Image-Edit_ComfyUI', 'Qwen-Image-Lightning-4steps-V1.0.safetensors', local_dir='./loras/')"

Download sources:

• https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI
• https://huggingface.co/Comfy-Org/Qwen-Image-Edit_ComfyUI

Workflow reference: https://docs.comfy.org/tutorials/image/qwen/qwen-image-edit

---

Reference Links

Workflows

• Phr00t official workflow: https://huggingface.co/Phr00t/Qwen-Image-Edit-Rapid-AIO/blob/main/Qwen-Rapid-AIO.json
• Civitai 3-view workflow: https://civitai.com/models/2061788/qwen-rapid-aio-three-view-workflow
• ComfyUI official tutorial: https://docs.comfy.org/tutorials/image/qwen/qwen-image-edit

Models

• Phr00t AIO: https://huggingface.co/Phr00t/Qwen-Image-Edit-Rapid-AIO
• Comfy-Org official: https://huggingface.co/Comfy-Org/Qwen-Image-Edit_ComfyUI
• GGUF version: https://huggingface.co/Phil2Sat/Qwen-Image-Edit-Rapid-AIO-GGUF

Custom Nodes

• ComfyUI-GGUF: https://github.com/city96/ComfyUI-GGUF
• Comfyui-QwenEditUtils: https://github.com/lrzjason/Comfyui-QwenEditUtils
• Phr00t modified node: https://huggingface.co/Phr00t/Qwen-Image-Edit-Rapid-AIO/tree/main/fixed-textencode-node

---

RunPod Operation Notes

Billing

• RTX 4090: $0.59–0.6/hr (as of January 2026)
• RTX 5090: $0.9/hr (as of January 2026)
• Volume retention (when stopped): $0.022/hr ($0.53/day, ~$16/month)

How to Stop a Pod

Update on April 5, 2026: I consolidated the detailed RunPod shutdown notes into Running Qwen-Image-Edit-2511 on RunPod. My current understanding is that the practical console actions are Stop and Terminate. At the API layer the operation appears as DELETE, and in the CLI it appears as runpodctl remove pod.

For a setup like this one, which uses a volume disk, the simple rule is Stop → Start for short-term reuse and Terminate → deploy a new Pod when moving to a different GPU. Pod migration is still beta, and after trying it two or three times myself, I would not recommend counting on it for recovery.

This Session’s Volume Contents

/workspace/runpod-slim/ComfyUI/models/
├── checkpoints/
│   ├── v18/Qwen-Rapid-AIO-NSFW-v18.1.safetensors (28GB)
│   └── fp8/Qwen-Image-Edit-2511-FP8_e4m3fn.safetensors (20GB)
└── loras/
    └── Multiple-Angles-LoRA/

---

Successful Run (Confirmed 2026/01/24)

Input image:

ComfyUI generation screen:

Environment

• GPU: RTX 5090 (32GB VRAM)
• Template: ashleykza/comfyui:cu128-py312-v0.10.0
• PyTorch: 2.9.1+cu128
• ComfyUI: 0.10.0

Model

• Phr00t AIO NSFW v18.1 (28GB)
• Path: models/checkpoints/v18/Qwen-Rapid-AIO-NSFW-v18.1.safetensors

Workflow

• Phr00t official JSON: https://huggingface.co/Phr00t/Qwen-Image-Edit-Rapid-AIO/blob/main/Qwen-Rapid-AIO.json
• Drag and drop the JSON into ComfyUI

Settings

• steps: 4
• cfg: 1.0
• sampler: sa_solver
• scheduler: beta
• Output size: 768x768 (for testing; 1024 recommended for production)

Default prompt output:

Prompt (for 3D Model Reference Sheet)

Positive:

front view, full body, nude, same character, simple flat colors, white background

Negative:

blurry, bad anatomy, deformed, low quality, text, watermark, clothes

Reference sheet prompt output (no mosaic in the actual output):

Generating a 3-View Sheet

• Generate separately for front view → side view → back view
• Use the same input image for all three

Generation Speed

• Blazing fast (4 steps in a few seconds)

---

Steps for RTX 5090 (32GB VRAM)

1. Create Pod

• GPU: RTX 5090 (32GB VRAM)
• Template: ashleykza/comfyui:cu128-py312-v0.10.0 (RTX 5090 compatible)
• Disk: default is fine

Note: RTX 5090 requires PyTorch 2.8+. Standard ComfyUI templates don’t support it.

2. Download Model (Web Terminal)

Open Web Terminal and run:

pip install huggingface_hub

cd /workspace/ComfyUI/models/checkpoints

python3 -c "from huggingface_hub import hf_hub_download; hf_hub_download('Phr00t/Qwen-Image-Edit-Rapid-AIO', 'v18/Qwen-Rapid-AIO-NSFW-v18.1.safetensors', local_dir='./')"

Note: 28GB, takes about 5 minutes.

3. Load Workflow

1. Open in browser: https://huggingface.co/Phr00t/Qwen-Image-Edit-Rapid-AIO/blob/main/Qwen-Rapid-AIO.json
2. Click “Download” to save locally
3. Drag and drop the JSON file into ComfyUI (Port 3000)

4. Run

• Checkpoint: select v18/Qwen-Rapid-AIO-NSFW-v18.1.safetensors
• Upload an image
• Set prompt and run