Modelpublic

ScottzillaSystems/qwen-image-edit-plus-nsfw-lora

sourceHugging Faceopenrail++updated 5mo agoView on Hugging Face

439likes196kdownloads

Model Card

MCNL v1 — Multi Concept NSFW LoRA for Qwen Image Edit

A LoRA adapter for the Qwen-Image-Edit-2511 diffusion pipeline, enabling NSFW content generation and editing capabilities.

Model Details

Property	Value
Base Model	Qwen/Qwen-Image-Edit-2511
Architecture	QwenImageTransformer2DModel (MMDiT) LoRA
File Size	~563 MB
Format	safetensors
License	OpenRAIL++

Usage

With the ScottzillaSystems Image Editor Space

The easiest way to use this LoRA is through the ScottzillaSystems Image Editor — select "🔥 MCNL-NSFW-v1" from the adapter dropdown.

Programmatic Usage

python

from diffusers import QwenImageEditPlusPipeline
import torch

pipe = QwenImageEditPlusPipeline.from_pretrained(
    "Qwen/Qwen-Image-Edit-2511",
    torch_dtype=torch.bfloat16
).to("cuda")

# Load this LoRA
pipe.load_lora_weights(
    "ScottzillaSystems/qwen-image-edit-plus-nsfw-lora",
    weight_name="qwen-image-edit-plus-nsfw-lora.safetensors",
    adapter_name="mcnl-nsfw-v1"
)
pipe.set_adapters(["mcnl-nsfw-v1"])

# Edit an image
from PIL import Image
image = Image.open("input.jpg").convert("RGB")
result = pipe(
    image=image,
    prompt="nsfw",
    num_inference_steps=40,
    true_cfg_scale=4.0,
    negative_prompt=" ",
).images[0]
result.save("output.jpg")

Trigger Words

Use these concepts in your prompts to activate specific capabilities: