LTX-2.3-uncensored-v1.4
Otheruncensored
from Lightricks/LTX-2.3
↓ 66.7K♥ 932 repos
NSFW-Uncensored
NSFW-Uncensored is a abliterated and uncensored open-weight language model, published on Hugging Face by Heartsync. It is mit licence. It is distributed across 11 repositories in Transformers format, totalling 18K downloads.
Specification
- Model name
- NSFW-Uncensored
- Source repository
- Heartsync/NSFW-Uncensored
- Base model
- Not declared
- Publisher
- Heartsync
- Parameters
- Not determinable from name
- Hardware class
- Unknown
- Licence
- mit
- Task
- Text to image
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers
- First indexed
- 5 May 2025
- Last updated
- 11 Aug 2026
Ablation technique
How NSFW-Uncensored was modified, and what that implies.
Abliteration + uncensored fine-tune
Directional ablation combined with additional fine-tuning on unfiltered data, so behaviour diverges from the base model beyond refusal removal alone.
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
“This model is a playground that minimizes censorship restrictions, allowing exploration of the technical possibilities of AI-based image generation. Through various prompts, you can test censorship boundaries and verify the actual performance of image generation AI.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "Heartsync/NSFW-Uncensored"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve Heartsync/NSFW-Uncensored --trust-remote-codeDownloads and variants (10)
Every published repository of NSFW-Uncensored, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| Heartsync/NSFW-Uncensoredsource | Transformers | 17.9K |
| gumoraes/NSFW-Uncensored | Transformers | 29 |
| Mspanz88/NSFW-Uncensored | Transformers | 21 |
| RickAlexJoel/NSFW-Uncensored | Transformers | 14 |
| Severelotus/NSFW-Uncensored | Transformers | 14 |
| nnnxnsn/NSFW-Uncensored | Transformers | 13 |
| Aver1t/NSFW-Uncensored | Transformers | 7 |
| WiseRisk/NSFW-Uncensored | Transformers | 3 |
| Bassaro23/NSFW-Uncensored | Transformers | 3 |
| derterin/NSFW-Uncensored | Transformers | 3 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- NSFW-Uncensored 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.
- This release adds fine-tuning on unfiltered data, so its behaviour diverges from the base model beyond refusal removal — differences you measure cannot be attributed to ablation alone.
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-Uncensored is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with Heartsync, and does not independently verify publisher claims. See responsible use.