Visual Novel Style LoRa SD3.5L版本v1.0 (ID: 1083138)

What is this LoRa?

This LoRa has been trained on Visual Novel dialogue text boxes on the SD3.5 Large base model

Recommended LoRa strength: 0.5

CLIP skip: 1

The keyword for this Lora is "vndb" and "vndb subtitle text" . The prompts are created using JoyCaption: https://colab.research.google.com/github/camenduru/joy-caption-jupyter/blob/main/joy_caption_jupyter.ipynb

Sampler used is DPM++_2M using SGM_uniform scheduler.

Training images+prompts: https://imgur.com/gallery/visual-novel-style-sd3-5l-lora-data-s4fpDxQ

You can download the training data for this LoRa here:https://huggingface.co/datasets/codeShare/lora-training-data/tree/main

描述:

Epoch 22 for SD3.5 Large base model

Loss rate : 0.117

Works best when paired with a finetuned SD3.5L model , if available

//----//

What is this LoRa?

This LoRa has been trained on Visual Novel dialogue text boxes on the SD3.5 Large base model

Recommended LoRa strength: 0.5

CLIP skip: 1

The keyword for this Lora is "vndb" and "vndb subtitle text" . The prompts are created using JoyCaption: https://colab.research.google.com/github/camenduru/joy-caption-jupyter/blob/main/joy_caption_jupyter.ipynb

Sampler used is DPM++_2M using SGM_uniform scheduler.

Training images+prompts: https://imgur.com/gallery/visual-novel-style-sd3-5l-lora-data-s4fpDxQ

You can download the training data for this LoRa here:https://huggingface.co/datasets/codeShare/lora-training-data/tree/main

训练词语: vndb subtitle text ,vndb