What is this LoRa?This LoRa has been trained on Visual Novel dialogue text boxes on the SD3.5 Large base modelRecommended LoRa strength: 0.5CLIP skip: 1The keyword for this Lora is "vndb" and "vndb subtitle text" . The prompts are created using JoyCaption: <a target="_blank" rel="ugc" href="https://colab.research.google.com/github/camenduru/joy-caption-jupyter/blob/main/joy_caption_jupyter.ipynb">https://colab.research.google.com/github/camenduru/joy-caption-jupyter/blob/main/joy_caption_jupyter.ipynb</a>Sampler used is DPM++_2M using SGM_uniform scheduler.Training images+prompts: <a target="_blank" rel="ugc" href="https://imgur.com/gallery/visual-novel-style-sd3-5l-lora-data-s4fpDxQ">https://imgur.com/gallery/visual-novel-style-sd3-5l-lora-data-s4fpDxQ</a>You can download the training data for this LoRa here:<a target="_blank" rel="ugc" href="https://huggingface.co/datasets/codeShare/lora-training-data/tree/main">https://huggingface.co/datasets/codeShare/lora-training-data/tree/main</a>

Visual Novel Style LoRa SD3.5L

Epoch 22 for SD3.5 Large base modelLoss rate : 0.117Works 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 modelRecommended LoRa strength: 0.5CLIP skip: 1The keyword for this Lora is "vndb" and "vndb subtitle text" . The prompts are created using JoyCaption: <a target="_blank" rel="ugc" href="https://colab.research.google.com/github/camenduru/joy-caption-jupyter/blob/main/joy_caption_jupyter.ipynb">https://colab.research.google.com/github/camenduru/joy-caption-jupyter/blob/main/joy_caption_jupyter.ipynb</a>Sampler used is DPM++_2M using SGM_uniform scheduler.Training images+prompts: <a target="_blank" rel="ugc" href="https://imgur.com/gallery/visual-novel-style-sd3-5l-lora-data-s4fpDxQ">https://imgur.com/gallery/visual-novel-style-sd3-5l-lora-data-s4fpDxQ</a>You can download the training data for this LoRa here:<a target="_blank" rel="ugc" href="https://huggingface.co/datasets/codeShare/lora-training-data/tree/main">https://huggingface.co/datasets/codeShare/lora-training-data/tree/main</a>

Files with SHA256: a25067c02770e3f20352832da0658cee583ffb16759a16600c0e77f4c52e78bc