Home of this model

moescape.ai is the primary home of this model and a broader collection of additional models. Many of these releases are exclusive to this platform and are not available elsewhere.
More information and related work can be found on my homepage: Ozia.

Creator: Vetehine

Discord: Vetehine

Linktree: https://linktr.ee/Vetehine

Support

Tips help keep me going and allow me to create even better models and LoRAs for the community. Even small support makes a difference.

Please let me know what you think about this Model in the comments.

📋 Usage Guidelines

✅ Merge Friendly: You are free to use this model in your own merges and creative projects.

❌ Commercial Use: Do not resell this model or sell direct merges of it as paid content.

🤝 Credit: Credit is not required, but it is appreciated.

Temptress ILL An experimental flat anime model built to explore different flat-style variations across its versions. Each version focuses on a slightly different approach to linework, shading, and color simplicity.

The model includes baked-in LoRAs along with custom-made LoRAs to create more unique and refined flat styles, while keeping clean rendering and consistency.

“Adetailer ensures cleaner, more accurate faces and eyes.”

AI Image Generation Settings Guide

https://moescape.ai/posts/ai-image-generation-settings-guide

Illustrious-XL

AI Image Generation Settings Guide

https://moescape.ai/posts/ai-image-generation-settings-guide

Illustrious-XL Recommended Settings -

Clip Skip - 2

DPM++ 2M Karras / Euler Ancestral / Restart

Sampling Steps - 25-66

Cfg - 6-7

Hires-

R-ESRGAN 4x+ Anime6B, 4x-AnimeSharp

Steps 10 - 20

Denoising 0.2 - 0.3

ANIMA

ANIMA Recommended Settings -

Recommended settings:

CFG: 4–6

Steps: 30–50

Resolution range: 512–1536

Recommended samplers:

• er_sde

• euler_a

• dpmpp_2m_sde_gpu

er_sde tends to produce cleaner anime-style linework and flatter color control.

euler_a often gives softer lines and a more painterly/2.5D feel.

dpmpp_2m_sde_gpu can create more experimental and creative outputs depending on prompting.

The model responds well to both tag-based prompting and natural language prompting, including mixed prompt structures.

Recommended prompt structure:

[quality/meta tags] → [subject] → [character/series] → [artist/style] → [general details] → [lighting/composition]

Example:

masterpiece, best quality, newest, safe, 1girl, original character, @artistname, white hair, black dress, glowing eyes, cinematic lighting, red moon, wind, night, detailed background

Natural language prompting also works very well:

A pale anime girl with long white hair standing under a crimson moon at night. Cinematic lighting, dark atmosphere, glowing red eyes, wind blowing through her hair, highly detailed illustration.

Mixed prompting:

masterpiece, best quality, newest, 1girl, white hair, black dress, glowing eyes.

A dark fantasy anime scene with cinematic lighting and red atmospheric fog.

Recommended quality/meta tags:

* masterpiece

* best quality

* newest

* highres

* absurdres

* safe / sensitive / nsfw / explicit

Recommended composition and atmosphere tags:

* cinematic lighting

* rim lighting

* depth of field

* dramatic angle

* dutch angle

* off center

* dynamic pose

* wind

* glowing

* blurry background

* bokeh

* atmospheric

* dramatic shadows

Artist prompting:

Artist tags generally work better using:

@artistname

Prompt weighting is supported, though stronger weights may work better than standard SDXL-style prompting.

Example:

(chibi:2)

(red eyes:1.8)

Time period tags

Specific year

year 2025, year 2024, ...

Period

newest, recent, mid, early, old

Meta tags

highres, absurdres, anime screenshot, jpeg artifacts, official art, etc

Safety tags

safe, sensitive, nsfw, explicit

The model generally performs better with:

* clean prompts

* focused styles

* clear character descriptions

* strong lighting descriptions

* balanced atmosphere tags

Overloading prompts with excessive conflicting tags can reduce consistency. Simpler prompts often produce cleaner results.

Legal & Usage Disclaimer

By accessing, using, generating with, or merging this model, you agree to these terms in full, regardless of whether you have read or acknowledged this notice.

This model is provided “as is,” without any warranties, express or implied, including but not limited to fitness for a particular purpose, legality of outputs, or compliance with platform policies.

Under no circumstances shall the author be held liable for any direct, indirect, incidental, consequential, special, or exemplary damages arising from or related to the use, misuse, or inability to use this model. This includes, without limitation, any content generated, modified, merged, distributed, or otherwise produced through the model, as well as any loss of data, loss of profits, reputational harm, legal claims, or third-party disputes resulting from such use.

This limitation of liability applies to all uses of the model, including but not limited to merging, fine-tuning, redistribution, or integration into other works or systems.

You are solely responsible for ensuring that your use complies with all applicable laws, regulations, and platform guidelines.

This disclaimer applies to all Vetehine models and LoRAs, whether or not this notice is explicitly included with a specific model or release.