Final version:
Better hands, faces, eyes.
Reduced NSFW content. LCM with simple, normal, or beta settings. Steps: 6โ12. CFG: 1โ1.4. Clip skip 2. Can generate at 832ร1216 or 1024ร1536.
My custom-merged model produces exceptional results when combined with [LoRAs]. Give it a try!
V1-4 pairs exceptionally well with Simulacrum CLIP-L and CLIP-G.
๐๏ธ V3 Prompt Tips
# POSITIVE PROMPT STARTER:
"masterpiece, Best quality, [your description here]"
# NEGATIVE PROMPT STARTER:
"low quality, worst quality, [unwanted elements]"## ๐ Version Recommendations
- V2: Best for photorealistic outputs
- V1: more like V2 than V3, still great for person loras
- V3: Optimized for artistic quality
## โ๏ธ Recommended Settings (V1-V2)
```yaml
Samplers:
- DPM++ 2M
- DPM++ 2M SDE
Sampling Steps: 30-50
Clip Skip: 1-2
CFG Scale: 4-6
๐ง Optional Enhancements
Use ADetailer for refined faces/hands
Enable Hires.fix for upscaling (recommended: 1.5-2x scale)
Description
FAQ
Comments (5)
V4 is the best xl porn model to date. Did you merge with damn pony or illustrious? Very easily understand poses.
Eyes are not good out of box, this can be improved.
Very good, thanx.
no, I never use pony, I merged them with three very good SDXL models and one illustrious model.
While I commend Mayer2003 on his continued efforts with his Natural Beauty model, there is just no way it is the best XL porn model to date. It seems very limited in its variety of subjects, it is virtually age-blind (try an old man doinking a 25 year old girl), and also seems to have trouble with certain backgrounds (most things seem to end up in a bedroom no matter what you prompt). I gave it a thumbs up because it does consistently produce nice images of good quality.
@Kid_Glitch_63ย Yes, its a merge with Coyotte's illustrious model. It has better pose adherence, than Lustify, because illustrious just knows out of box. Age doesnt work that way, like in SDXL, lighting and background lack of course. But, it think it has better adherence, than any xl model for porn.
what models did you merge with

















