THIS MODEL IS V-PRED

I tried merge model to give a 3D appearance while keeping the face in an anime style.

enjoy it!

🟦 Recommended Settings

Positive Prompt

masterpiece, best quality, absurdres, highres, anime coloring, 3D

Feel free to add shiny skin, humid skin to the prompt depending on your preferences.

Negative Prompt

lowres, bad quality, low quality, worst quality, text, error, fewer, extra, missing, jpeg artifacts, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, artistic username, scan, abstract, 4koma, surreal, abstract, dissolving, multiple views, grey background, sepia, futanari, furry, lips

🔧 Recommended Generation Settings

Sampler: Euler a, DPM++ 2M SDE
Scheduler: SGM Uniform
CFG Scale: 3–5
Resolution Options:
- 960x1280
- 1280x960
- 1128x1128
- 832x1216
- 1216x832
- 1024x1024
Sampling Steps: 24–30 steps
Hires Settings:
- Denoising Strength: 0.3–0.4
- Upscale Steps: 10–15 steps

Description

Improved LoRA compatibility (preserves original art style)
Enhanced anime-style 3D rendering
Sharper image quality
Better lighting effects
Ability to generate high-resolution images (1.5MP)
Improved object and hand pose accuracy

The details of object-grasping or holding actions have been greatly improved. but compared to the previous version, there seems to be an increase in cases where the number of fingers or toes is incorrect in some images.