metadata
base_model: black-forest-labs/FLUX.1-schnell
license: apache-2.0
language:
- en
- pt
- th
library_name: diffusers
pipeline_tag: text-to-image
tags:
- UnfilteredAI
- 3d
- text-to-image
- not-for-all-audiences
Model Name: UnfilteredAI/NSFW-Flux-v1 🚀
Type: Text-to-Image Generator
Description: Description:
NSFW-Flux-v1 is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. Finetuned by UnfilteredAI, this model is designed to produce a wide range of images, including explicit and NSFW (Not Safe For Work) images from textual inputs. Whether you're looking for artistic, realistic, or fantastical imagery, NSFW-Flux-v1 has got you covered! 🌟
Features:
- 🖼️ Uncensored Output: The model generates uncensored and potentially explicit images based on textual inputs, providing complete creative freedom.
- ⚡ Tensor Type: Utilizes BF16 tensor type for optimized performance and efficiency, ensuring quick and smooth generation.
- 💪 Model Size: With 12 billion parameters, NSFW-Flux-v1 offers an extensive capacity for learning and generating diverse and detailed imagery.
- 🌀 3D Style Rendering: Enhanced with 3D style/image rendering capability to create more lifelike and dynamic images. (Use "3d", "3d style" in your prompt)
- 🔄 Continuous Improvement: The model is continually updated and refined to improve its performance and expand its capabilities.
Usage Guidelines:
- 🛡️ Responsible Use: Exercise discretion and responsibility when generating content with this model. The nature of the content generated can be explicit, so use it wisely.
- 👥 Age Restriction: Due to the explicit nature of the generated content, usage is restricted to individuals over the legal age in their jurisdiction. Ensure compliance with local laws and regulations.
import torch
from diffusers import FluxPipeline
pipe = FluxPipeline.from_pretrained("UnfilteredAI/NSFW-Flux-v1", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload() #save some VRAM by offloading the model to CPU. Remove this if you have enough GPU power
prompt = "A cat holding a sign that says hello world"
image = pipe(
prompt,
guidance_scale=0.0,
num_inference_steps=4,
max_sequence_length=256,
generator=torch.Generator("cpu").manual_seed(0)
).images[0]
image.save("NSFW-Flux-v1.png")