← back to catalog · registered 2026-08-22 13:56

bounel/Flux-uncensored

bounel Flux image-gen
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/bounel%2FFlux-uncensored"
Response includes
  • classification m-uncensored
  • files 4
  • hub_downloads_all_time 522
  • providers 2
  • author_summary 1 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
522
18 last 30d - cooling
Likes
2
Model age
6mo ago
created 2026-04-03
Available via
2 providers
replicate, wavespeed
Downloads over time
Now530→from86↑516%
6423440457486 on Apr 15530 on Oct 11AprMayJunJulAugSepOct
Apr 15 → Oct 11 · 65 snapshots · spans 179 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

Tags
diffusers text-to-image stable-diffusion lora fluxpipeline flux not-for-all-audiences base_model:black-forest-labs/FLUX.1-dev base_model:adapter:black-forest-labs/FLUX.1-dev license:creativeml-openrail-m region:us

Related

Total size
656 MB
Files
4
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-04-03 08:07

Files by quantization

Auxiliary files 4 files 656 MB
lora.safetensors 656 MB 5ad714d2 download
banner.webp 59.5 KB 2bf8a772 download
README.md 3.68 KB 27bba261 download
.gitattributes 1.48 KB a6344aac download

README current version from Hugging Face


tags:

  • text-to-image
  • stable-diffusion
  • lora
  • diffusers
  • fluxpipeline
  • flux
  • not-for-all-audiences
    base_model: black-forest-labs/FLUX.1-dev
    license: creativeml-openrail-m
    pipeline_tag: text-to-image

FLUX Uncensored LoRA

Banner Logo

Model Description

created by https://enhanceai.art

support discord server - https://discord.gg/cuCX9qur6f

The FLUX Uncensored LoRA is an enhancement designed for the base model black-forest-labs/FLUX.1-dev. It enables explicit, unrestricted generation of images using text prompts. The LoRA weights have been fine-tuned to remove the base model's content restrictions, allowing for the generation of NSFW (Not Safe For Work) and other uncensored content.

This LoRA extension can be loaded into the FLUX.1-dev pipeline using the diffusers library. It is optimized for high-quality, explicit image generation based on user-provided prompts. The model is intended for research and personal use, and adheres to the non-commercial license terms.

Warning: This model allows the generation of explicit content. Users should exercise caution and adhere to legal and ethical guidelines.

Donate & Support

Why Support Us?

At EnhanceAI, we build powerful AI tools and models for creators and developers. Your support helps us continue innovating and improving the platform.

How Your Donation Helps

  • Enhance our AI tools and models.
  • Keep the platform running smoothly.
  • Provide you with new features and updates.

Benefits of Donating:

  • Exclusive access to premium tools.
  • Early access to updates.
  • Priority support.

Donate Now

Thank you for helping us grow and continue making AI accessible to all!

License

This LoRA extension follows the FLUX-1-dev Non-Commercial License.

How to Use

Below is an example of how to use the FLUX Uncensored LoRA with the diffusers library:

from diffusers import AutoPipelineForText2Image
import torch

# Load the base model
pipeline = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to('cuda')

# Load the uncensored LoRA weights
pipeline.load_lora_weights('enhanceaiteam/Flux-uncensored', weight_name='lora.safetensors')

# Generate an image with an uncensored NSFW prompt
image = pipeline('a naked cute girl').images[0]
image.show()

Check out more AI tools and models at https://enhanceai.art

print("Visit https://enhanceai.art for more AI tools and image generation models!")

Trigger Words

Use the following trigger words to guide the model toward generating NSFW content:

  • nsfw
  • naked
  • pron
  • kissing
  • erotic
  • nude
  • sensual
  • adult content
  • explicit

These keywords, along with descriptive prompts, help the model generate explicit imagery.

Model Details

  • Base Model: black-forest-labs/FLUX.1-dev
  • LoRA Weights: enhanceaiteam/Flux-uncensored
  • LoRA Weight File: lora.safetensors
  • Torch Data Type: torch.bfloat16
  • Hardware Requirement: CUDA-enabled GPU recommended for optimal performance.

Disclaimer

This model is capable of generating uncensored and explicit content. It should be used responsibly and within the bounds of the law. The creators do not endorse illegal or unethical use of the model. Content generated using this model should comply with platform guidelines and local regulations regarding NSFW material.

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-04-03Duplicate from SERGSSSSSSSS/Flux-uncensoredcaa05b43.7 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration