Flux_ Lustly.ai_ Uncensored_nsfw_v1

Introduction

The FLUX_LUSTLY.AI_UNCENSORED_NSFW_V1 model is developed by Lustly AI and offers a text-to-image generation pipeline focusing on uncensored NSFW content. It is designed to produce images with a range of nudity and adult themes.

Architecture

This model leverages the FLUX pipeline for stable diffusion and uses the safetensors library for secure tensor operations. It supports LoRA (Low-Rank Adaptation) to enhance image quality and adaptability.

Training

The model was trained using the FLUX dev and schnell models, with testing primarily conducted in diffusers. The model aims for high-quality outputs, with an emphasis on both female and male nudity.

Guide: Running Locally

To run this model locally, follow these steps:

1. Install Requirements: Ensure you have Python and the necessary libraries installed, including diffusers and torch.

2. Setup Environment:

   from diffusers import AutoPipelineForText2Image
   import torch
   
   pipeline = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
   pipeline.to("cuda")
   

3. Load Model Weights:

   pipeline.load_lora_weights("lustlyai/Flux_Lustly.ai_Uncensored_nsfw_v1",
                              weight_name="flux_lustly-ai_v1.safetensors",
                              adapter_name="v1")
   pipeline.set_adapters(["v1"], adapter_weights=[1])
   

4. Generate Image:

   prompt = "high quality, on the street, a naked woman with purple hair, standing next to a black naked male with big flaccid dick, both hold a neon sign 'lustly.ai'"
   out = pipeline(
       prompt=prompt,
       guidance_scale=4,
       height=768,
       width=768,
       num_inference_steps=20,
   ).images[0]
   display(out)
   

Cloud GPUs

For better performance, consider using cloud-based GPU services like AWS, Google Cloud, or Azure to run the model.

License

This model is distributed under the CreativeML OpenRAIL-M license, which allows for open use with obligations regarding the ethical use of the content generated.