⌦abliteratedmodels.org

krea2-turbo-uncensored-v1.1

krea2-turbo-uncensored-v1.1 is a abliterated and uncensored variant of conradlocke/krea2-identity-edit, published on Hugging Face by ChrisColeTech. It is unknown licence. It is distributed across 2 repositories in GGUF format, totalling 11.7K downloads.

Abliteration + uncensored fine-tuneOther↓ 11,744♥ 17
View on Hugging Face ↗Base model ↗

Specification

Model name
krea2-turbo-uncensored-v1.1
Source repository
ChrisColeTech/krea2-turbo-uncensored-v1.1-FP8
Base model
conradlocke/krea2-identity-edit
Publisher
ChrisColeTech
Parameters
Not determinable from name
Hardware class
Unknown
Licence
unknown
Task
Image to image
Context window
Not documented
Ablation scope
Not stated by the publisher
Formats available
GGUF
First indexed
19 Aug 2026
Last updated
24 Aug 2026

Ablation technique

How krea2-turbo-uncensored-v1.1 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

“UPDATED 8/22/2026 - Announcing Krea 2 Turbo Edit v1.1 GGUF and FP8 an all new updated version with bug fixes and major improvements.”

Running it

Commands are templates — confirm the exact repository and quant file before use.

llama.cpp / GGUF
hf download ChrisColeTech/krea2-turbo-uncensored-v1.1-FP8 --local-dir ./krea2-turbo-uncensored-v1.1
llama-cli -m ./krea2-turbo-uncensored-v1.1/<file>.gguf -p "..."
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "ChrisColeTech/krea2-turbo-uncensored-v1.1-FP8"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
    repo, torch_dtype="auto", device_map="auto"
)
vLLM
vllm serve ChrisColeTech/krea2-turbo-uncensored-v1.1-FP8 --trust-remote-code

Downloads and variants (1)

The only published repository of krea2-turbo-uncensored-v1.1.

RepositoryFormatDownloads
ChrisColeTech/krea2-turbo-uncensored-v1.1-FP8sourceGGUF11.7K

Security-team assessment

Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.

  • krea2-turbo-uncensored-v1.1 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.
  • Declared licence is unknown, but the terms that bind you are conradlocke/krea2-identity-edit’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 krea2-turbo-uncensored-v1.1 is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with ChrisColeTech, and does not independently verify publisher claims. See responsible use.