Sign In

Ghibli Style

82

Updated: May 31, 2026

styleghiblianime

Download

1 variant available

SafeTensor

132.33 MB

Verified:

Type

LoRA

Stats

226

4

9

Reviews

Published

May 31, 2026

Base Model

Anima

Hash

AutoV2
DE10902B5E

Trigger Words

Ghibli Style
default creator card background decoration
Supporter Badge October 2023
Estylon's Avatar

Estylon

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

This LoRA is designed to infuse your generations with the timeless and enchanting style reminiscent of Studio Ghibli films.

This model was trained on a curated set of Ghibli-style synthetic images, allowing it to capture the beloved aesthetic with clean, modern clarity and avoiding the common yellow tint often found in other models.

Expect soft, painterly visuals with gentle, warm color palettes, and an atmosphere filled with a sense of wonder and nostalgia. Characters come to life with soft, rounded features, expressive eyes, and that unmistakable Ghibli charm, feeling as if they were hand-drawn for a classic animated feature. Environments become breathtaking landscapes rich in detail and mood—from sun-dappled forests and serene countrysides to cozy, cluttered interiors.

The goal of this LoRA is to capture the exact feeling that makes the Ghibli aesthetic so beloved: a mix of gentle whimsy, deep respect for nature, and heartfelt storytelling. If you’re looking to create characters and scenes that radiate warmth, innocence, and a storybook-like charisma, this LoRA will help you achieve it.

For those who want custom-tailored styles or specific commissions, I also offer LoRA commission work. You can reach out to me directly via Private Message or visit my DeviantArt page:

👉 https://www.deviantart.com/estylonshop

Enjoy experimenting with this model, and don’t forget to share your results—I’d love to see what you create