NSFW-GEN-ANIME-v2
Other
from HelpingAI/PixelGen
↓ 22.1K♥ 57
NSFW-gen-v2
NSFW-gen-v2 is a refusal-ablated variant of HelpingAI/PixelGen, published on Hugging Face by UnfilteredAI. It is other licence. It is distributed across 2 repositories in Transformers format, totalling 6.1K downloads.
Specification
- Model name
- NSFW-gen-v2
- Source repository
- UnfilteredAI/NSFW-gen-v2
- Base model
- HelpingAI/PixelGen
- Publisher
- UnfilteredAI
- Parameters
- Not determinable from name
- Hardware class
- Unknown
- Licence
- other
- Task
- Text to image
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers
- First indexed
- 15 Apr 2024
- Last updated
- 5 Aug 2024
Ablation technique
How NSFW-gen-v2 was modified, and what that implies.
Abliteration (directional ablation)
The single residual-stream direction that mediates refusal is identified from harmful/harmless prompt pairs and projected out of the model weights.
Reported scope: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.
From the publisher’s model card
“Description: NSFW-gen is a text-to-image generator developed by UnfilteredAI. This model is designed to generate all kinds of images, including explicit and NSFW (Not Safe For Work) images from textual inputs.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "UnfilteredAI/NSFW-gen-v2"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve UnfilteredAI/NSFW-gen-v2 --trust-remote-codeDownloads and variants (1)
The only published repository of NSFW-gen-v2.
| Repository | Format | Downloads |
|---|---|---|
| UnfilteredAI/NSFW-gen-v2source | Transformers | 6.1K |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- NSFW-gen-v2 will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- Declared licence is other, but the terms that bind you are HelpingAI/PixelGen’s — a re-release cannot grant more than its parent.
Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.
Metadata for NSFW-gen-v2 is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with UnfilteredAI, and does not independently verify publisher claims. See responsible use.