The previous version (4.5) was retrained using 15,000 images. About 3,000 artistic photographs were used. Generates realism well and a little pornography. If the images are blurry, I recommend using Lora Uncensored 2.
Trigger words are not needed, but Lora likes extended prompts.
Description
The dataset has been expanded to 2910 images. Fine-tuning of the Lora blocks has been performed.
Details
Downloads
779
Platform
CivitAI
Platform Status
Deleted
Created
4/24/2025
Updated
4/24/2025
Deleted
4/24/2025
Files
Flux_Perfect body_v4.5.safetensors
Mirrors
Huggingface (2 mirrors)
CivitAI (1 mirrors)