PixAI Membership
PixAI
PixAI
Generate
Sign in
Home
Generation
Models
Studio
NEW
Contest
Create with Mio.2
AI Tools
NEW
Guide

SD

Airfuck's Wild Mix

Create

  • AI Image Generator
  • AI Animation Generator
  • AI Tools
  • Thematic generators
  • Train LoRA
  • Mio.2 Agent
  • Studio

Discover

  • Trending Tags
  • Ranking
  • Model Market
  • Contest
  • News

About

  • Guide
  • PixAI Blog
  • Tsubaki.2
  • Meet Mio, Our Mascot
  • Content Rules

Pricing & Help

  • Membership
  • Buy Credits
  • Contact

Mobile App

  • Get the PixAI app
  • App Store
  • Google Play
© 2026 PixAI
  • Terms of Service
  • Privacy Policy
  • Copyright Policy
  • Attributions
  • Specified Commercial Transactions Law
Airfuck's Wild Mix - AI Model cover image
Uploaded at
Jun 5, 2023, 2:55 AM
Uses
56.1k
Reviews
Excellent  (6)
Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Recommended LoRAs

Add More Details - Detail Enhancer / Tweaker (细节调整) LoRA - AI Model cover image

User LoRA

Add More Details - Detail Enhancer / Tweaker (细节调整) LoRA
23.60k
 Realistic Enhancer - AI Model cover image

User LoRA

Realistic Enhancer
3.08k
Detail Tweaker LoRA  - AI Model cover image

User LoRA

Detail Tweaker LoRA
9.78k
Cartoon dark style - AI Model cover image

User LoRA

Cartoon dark style
76

Description

Credit: https://civitai.com/models/82075?modelVersionId=87131

Airfuck's Wild Mix (AWM)

The idea behind this model merge is to amplify anything male in the base models without sacrificing versatility. As such it can create decent dick quite easily without LoRAs. It's still compatible with a wide range of LoRAs if you wish to use them. The merge includes photorealistic as well as anime elements and therefore allows a wide range of styles, e.g. cartoonish, 2.5d, hyper-realistic, and more.

Tips for model usage

Simple and short prompts without the usual "incantations" (like "masterpiece, 4k, ...") can bring you a long way. Also try to be light on the negatives - I often get good results with just a few textual inversions (e.g. Deep Negative).

Settings that work well are:

Sampling Method: DPM++ SDE Karras

Sampling Steps: 20

CFG Scale: 7

Comments