orcarouter_GLM-5.3-Flash-Uncensored
from orcarouter/GLM-5.3-Flash-Uncensored-FP8
Krea2-Noct-Uncensored is a abliterated and uncensored variant of krea/Krea-2-Turbo, published on Hugging Face by Noctaluna. It is other licence. It is distributed across 2 repositories in Transformers format, totalling 55.9K downloads.
How Krea2-Noct-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
“A photoreal Krea 2 merge for NSFW work, built on the official Krea 2 Turbo. Explicit prompts work with no bypass LoRA, in 8 steps.”
Commands are templates — confirm the exact repository and quant file before use.
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "Noctaluna/Krea2-Noct-Uncensored"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vllm serve Noctaluna/Krea2-Noct-Uncensored --trust-remote-codeThe only published repository of Krea2-Noct-Uncensored.
| Repository | Format | Downloads |
|---|---|---|
| Noctaluna/Krea2-Noct-Uncensoredsource | Transformers | 55.9K |
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
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 Krea2-Noct-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 Noctaluna, and does not independently verify publisher claims. See responsible use.