Sign In

nKrea - Krea2 LoRA experiment

208

Not loaded

Download

1 variant available

bf16 SafeTensor

nKrea_pruned.safetensors

BF16, good balance • 218 MB

Verified:

Type
LoRA
Stats

342

208

312

Generation

Not loaded

Reviews
Published

Aug 21, 2026

Base Model

Krea 2

Training
Steps: 1,200
Epochs: 10
Usage Tips
Strength: 1
Hash
AutoV2
8AF27F0F80
default creator card background decoration
Followers - 3564

3.6K

Likes - 15605

15.6K

Generations - 4928437

4.9M

Kinky boot
f9511008-bbef-4c36-ae98-d7f401c66f9d-022.png

New Update! I have re-tested this LoRA on-site and now, it works (with no action on my side). Welp, in any case, i have re-activated on-site usage :D

Example: https://civitai.red/images/142195454 (remix of one of the pictures from this great article by @arsibalt)

Update: For an unknown reason, all my tests on-site kept failing, i have re-uploaded a pruned version of the LoRA where any unusual layers has been removed but it still doesn't work 😭 So, i have disabled on-site generation 😥

When using generated content for training, you can sometimes get stuck in a cycle of finding what should come first: the egg or the chicken? Well, here is the dinosaur that laid the first egg for my UnNamed upgrades.

Based on some pictures made by @daceheg192491 for DMergeV3 (highly recommended checkpoint!), i captionned some of his work (to avoid re-using prompts), generated a few pictures using Krea2 and some slight img2img using UnNamedIXL, did a training to get a first LoRA, merged my Ai Dolls for Krea2 LoRA in there together with some anti-refusal LoRA and finished with this pretty broken and far to "wet" model very focused on glamorous women.

This allowed me to generate the dataset used afterward for training, but in any case, here is the source LoRA for anyone curious to see it 😉💜