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.
Vete ┃ Moonlit Vow ILL is a semi-realistic, softly cinematic model built around contrast through restraint rather than force. It focuses on clean structure, luminous skin, and carefully balanced light that feels natural, intimate, and emotionally charged. The visual language sits between realism and stylization, allowing scenes to feel grounded while still carrying a dreamlike, storybook quality.
Lighting is the core strength of Moonlit Vow. Highlights are smooth and controlled, never harsh, creating gentle sheen on skin, hair, and fabric. Shadows are soft-edged and stable, preserving facial structure and depth without crushing detail. Low-light scenes retain clarity, while bright environments stay airy and diffused, making the model equally strong for candlelight interiors, moonlit gardens, and soft daylight compositions.
Color handling is neutral and elegant. Whites remain clean, blacks stay deep without noise, and accent colors such as reds, blush tones, and florals appear rich but contained. There is no heavy color bias; instead, saturation is guided by light, giving images a natural cinematic harmony rather than a stylized filter look.
Detail fidelity is consistent across faces, hands, and materials. Skin avoids waxiness and plastic shine, maintaining subtle texture and believable softness. Hair shows clean strand separation with gentle gloss. Fabrics like lace, chiffon, silk, and matte cotton read clearly, reacting naturally to light without overpowering the subject.
Moonlit Vow ILL is suited for romantic, gothic, soft fantasy, and emotional portrait work, but remains flexible enough for modern or minimal scenes. It performs well both as a standalone model and as a merge component, adding refined lighting behavior, smooth tonal transitions, and calm visual coherence to other bases.
This model is designed for creators who value atmosphere, clarity, and control where mood is carried by light and composition rather than excessive effects.
AI Image Generation Settings Guide
https://moescape.ai/posts/ai-image-generation-settings-guide
Recommended Settings -
Clip Skip - 2
DPM++ 2M Karras
Sampling Steps - 25-50 (Recommended: 37 Steps)
Cfg - 6-7
Recommended Settings -
Clip Skip - 2
Euler Ancestral (Recommended: 30 Steps)
Sampling Steps - 25-35
Cfg - 6-7
Recommended Settings -
Clip Skip - 2
Restart
Sampling Steps - (Recommended: 66 Steps)
Cfg - 6-7
Hires-
R-ESRGAN 4x+ Anime6B, 4x-AnimeSharp
Steps 10 - 20
Denoising 0.2 - 0.3
Note: Using LoRAs/Spells may affect model performance or stability. Apply them with your own settings and discretion.
Description
This version introduces a cleaner visual style with improved consistency across faces, anatomy, and lighting. The merge includes the most up-to-date datasets currently available, helping produce more natural poses, stronger proportions, and more stable character structure.
Rendering is smoother and more controlled, with clearer skin tones, refined hair detail, and better material definition for fabrics, leather, lace, and metallic elements. Lighting behavior is also improved, allowing soft highlights, cinematic glow, and balanced shadows without losing detail.
Overall, this update focuses on stability, cleaner outputs, and better pose quality while keeping the elegant aesthetic and versatility of Vete ┃ Moonlit Vow ILL.