<h1 id="this-model-is-v-pred">THIS MODEL IS V-PRED</h1>I tried merge model to give a 3D appearance while keeping the face in an anime style.enjoy it!<hr /><h3 id="recommended-settings">🟦 Recommended Settings</h3>Positive Prompt<code>masterpiece, best quality, absurdres, highres, anime coloring, 3D</code>Feel free to add shiny skin, humid skin to the prompt depending on your preferences.Negative Prompt<code>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</code><hr /><hr /><h3 id="recommended-generation-settings">🔧 Recommended Generation Settings</h3><ul><li>Sampler: <code>Euler a</code>, <code>DPM++ 2M SDE</code></li><li>Scheduler: <code>SGM Uniform</code></li><li>CFG Scale: <code>3–5</code></li><li>Resolution Options:<ul><li><code>960x1280</code></li><li><code>1280x960</code></li><li><code>1128x1128</code></li><li><code>832x1216</code></li><li><code>1216x832</code></li><li><code>1024x1024</code></li></ul></li><li>Sampling Steps: <code>24–30 steps</code></li><li>Hires Settings:<ul><li>Denoising Strength: <code>0.3–0.4</code></li><li>Upscale Steps: <code>10–15 steps</code></li></ul></li></ul><hr />

3D-Stock (3d anime style)

<ul><li>Improved LoRA compatibility (preserves original art style)</li><li>Enhanced anime-style 3D rendering</li><li>Sharper image quality</li><li>Better lighting effects</li><li>Ability to generate high-resolution images (1.5MP)</li><li>Improved object and hand pose accuracy</li></ul>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.<ul><li>recommend positive prompt</li><li>masterpiece, best quality, highres, 3d, anime coloring</li></ul>default recommend prompt has simplified. Feel free to add more prompts to suit your preferences.

3D-Stock_vpred2.0.safetensors

3D-Stock (anime 3d style checkpoint)

v2.0

v4.1FIX

v4.0

v3.0

v1.0

THIS MODEL IS V-PREDI tried merge model to give a 3D appearance while keeping the face in an anime style.enjoy it!🟦 Recommended SettingsPositive Promptmasterpiece, best quality, absurdres, highres, anime coloring, 3DFeel free to add shiny skin, humid skin to the prompt depending on your preferences.Negative Promptlowres, 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<ul><li>Sampler: Euler a, DPM++ 2M SDE</li><li>Scheduler: SGM Uniform</li><li>CFG Scale: 3–5</li><li>Resolution Options:<ul><li>960x1280</li><li>1280x960</li><li>1128x1128</li><li>832x1216</li><li>1216x832</li><li>1024x1024</li></ul></li><li>Sampling Steps: 24–30 steps</li><li>Hires Settings:<ul><li>Denoising Strength: 0.3–0.4</li><li>Upscale Steps: 10–15 steps</li></ul></li></ul>

Files with SHA256: aa943f669e627794f7f4e984dfc0aed6120344a3573183f714e9c3c40c2fa349