This is a simple merge of the laion clip vision h with someone's NSFW Clip vision H finetune. Using this will increase the quality/consistancy of NSFW Wan gens due to the fact the clip vision can accurately recognize what the image is.
Works on both Wan 14b and 1.3b i2v or t2v
This replaces the clip vision model not the umt5 text encoder.
All characters are 18+. This is intended for mature audiences only you and you alone are responsible for what you generate. THIS MODEL IS NOT TO BE USED ON ANY REAL PERSON! 18+ ONLY!
Description
Details
Downloads
4,741
Platform
CivitAI
Platform Status
Available
Created
7/23/2025
Updated
9/27/2025
Deleted
-
Files
wan21NSFWClipVisionH_v10.safetensors
Mirrors
Huggingface (1 mirrors)
CivitAI (1 mirrors)