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 SDEScheduler:
SGM UniformCFG Scale:
3–5Resolution Options:
960x12801280x9601128x1128832x12161216x8321024x1024
Sampling Steps:
24–30 stepsHires Settings:
Denoising Strength:
0.3–0.4Upscale Steps:
10–15 steps
Description
FAQ
Comments (2)
This is pretty nice! Can I ask with which model you merged, or which base model to do the merge? It seems the dataset is a bit updated vs base illu (it knows more ZZZ chars)
this model was originally a merged one from a long time ago, and I later added additional lora merges on top. i don’t remember the exact recipe, but I believe the overall character knowledge is heavily influenced by 'NAI-XL_vpred1.0_2.5dac' model.
or since it includes lora trained on 3D game characters such as those from ZZZ dataset. it may also contain extra knowledge derived from those lora.
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.