Sign In

Yuuki Hana Style

2

Updated: Aug 31, 2026

styletouhoutraditional media

Download

1 variant available

bf16 SafeTensor

yuukihana_style.safetensors

BF16, good balance • 132.24 MB

Verified:

Type
LoRA
Stats

90

2

Reviews
Published

Aug 31, 2026

Base Model

Anima

Usage Tips
Strength: 0.8
Hash
AutoV2
DF852EE3D4
Trigger Words
yuukihana_style
touhou
traditional media
marker (medium)
default creator card background decoration
Uploads - 10

10

Followers - 45

45

Likes - 174

174

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

Neurosha_amazing_quality_absurdres_newest_20260831_102055_00001_.png

Yuuki Hana Style | Anima

A style LoRA inspired by the delicate traditional-media illustrations of Yuuki Hana (jtnp5334).

🔑 Main Trigger

yuukihana_style
traditional media, marker (medium)

For the strongest source-like appearance, especially with Touhou characters:

yuukihana_style, touhou, traditional media, marker (medium)

touhou strengthens the original training aesthetic, but it may also introduce visual associations with Touhou characters. For original characters, try generating without it first.

0.7–1.0

Suggested starting value:

0.8

Lower the strength to approximately 0.6–0.75 when combining this LoRA with other strong styles.

📝 Example Prompt

masterpiece, best quality, safe, yuukihana_style,
traditional media, marker (medium), 1girl, solo,
long white hair, blue eyes, gentle smile,
white dress, holding flowers, flower garden,
soft colors, looking at viewer, upper body

Touhou-style example

masterpiece, best quality, safe, yuukihana_style,
touhou, traditional media, marker (medium),
hakurei reimu, 1girl, solo, shrine maiden,
holding flowers, sunflower field, blue sky,
soft colors, gentle smile, looking at viewer

🚫 Suggested Negative Prompt

worst quality, low quality, score_1, score_2, score_3,
photorealistic, 3d, bad anatomy, bad hands,
extra fingers, missing fingers, deformed,
blurry, jpeg artifacts, text, watermark, artist name
Base model: Anima
Resolution: 1024×1024 or equivalent bucket resolution
Steps: 24–32
CFG: 4–6
LoRA strength: 0.7–1.0

The LoRA understands standard Anima/Danbooru-style tags. Natural-language prompts can also be mixed with tags.

📦 Training Information

Training images: 263
Resolution: 1024 with buckets
Network Dim: 32
Network Alpha: 32
Training steps: 1500
Text Encoder: frozen

The dataset contains general and mature-rated artwork. Images with underage or age-ambiguous sexualized subjects were excluded.

❤️ Credits

The training material was collected from the public Gelbooru artist tag:

Yuuki Hana (jtnp5334) on Gelbooru

This is an unofficial fan-made style LoRA. It is not affiliated with or endorsed by the original artist. All rights to the original illustrations belong to their respective creator and copyright holders.

Please use the LoRA responsibly, credit the original artist when appropriate, and do not present generated images as authentic works by the artist.