Sign In

Anime Denser Lora

13

166

16

4

Verified:

SafeTensor

Type

LoRA

Stats

90

6

22

Reviews

Published

Aug 16, 2025

Base Model

Qwen

Training

Steps: 10,000

Hash

AutoV2
F830698CE3
tarn59's Avatar

tarn59

Using the dataset and script from https://civitai.com/user/seruva19 (Please give him all the credit)

In this Lora, https://civitai.com/models/1753118/anime-denser-wan21-t2v-14b

This is Hidream version of that same concept lora -3 strength less density +3 strength more density.

I used ai-toolkit to train both the positive and negative lora's and used the same difference_lora.py script to make the final lora.

* The only change I had to make for the difference_lora.py script was change the ".lora_down.weight" references into ".lora_A.weight" references (different names but same concepts).