Sign In
homemodelsimagesvideos3D Modelsarticlescomicsbountieschallengesupdatesshop

Konosuba - Show Style

482

Updated: Aug 12, 2026

stylekonosubashowanime

Download

1 variant available

bf16 SafeTensor

Konosuba_Style_ANI_v2.safetensors

BF16, good balance • 132.24 MB

Verified:

Type
LoRA
Stats

252

12

1

Generation License Fee

1 / 10 images

Reviews

(43)

Published

Aug 12, 2026

Base Model

Anima

Usage Tips
Strength: 0.9
Hash
AutoV2
D7F6D73251
Trigger Words
@nv-st-kono
default creator card background decoration
Writers position #45

#45

Uploads - 293

293

Followers - 8023

8K

Likes - 58181

58.2K

Sleepless GPUs

License:

Anima

The Anima Model is licensed by CircleStone Labs LLC. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

Built on NVIDIA Cosmos

a1.png

Konosuba - Show Style 📺

This LoRA on my screen shots of my favorite anime show [KONOSUBA -God's blessing on this wonderful world!], i mainly targeting the expressions and scenery by training this so its something between a style and a concept i think.

If you didn't watch the show already consider giving it a try it's super funny 💚

Usage Tips (IL) :

  • I personally use it at a weight of 1.1 so i recommend that

  • the LoRA needs to have its trigger word "nv-st-kono, anime coloring," in the prompt

    • in case you wanna mix it with other named artstyles effectively then remove "anime coloring,"

  • so far only tested on WAI-NSFW-illustrious-SDXL V16 (used in the showcase pics)

  • preforms well well on male characters

Training Notes (IL) :

used a manually curated dataset around 200 pics with the following traits:

  • 90 pics main characters / 120 pics non-main characters

  • 30% / 70% male to female ratio

  • 10% non human pics data backgrounds, animals

  • most data cropped to focus on the main subject