The LoRA is a personification of Naenara Browser based on Merryweather comics.For this one, i used 2/1 dim/alpha.<h1 id="read-before-using">Read before using</h1><h3 id="how-to-use">How to use</h3>add lora in prompt, then use the trigger keywords.Ideal weight: 1can go from 0.6-1<h3 id="keywords">Keywords</h3>Trigger: naenarachanBase: 1girl,solo,red eyes, black hair,single hair bun,hair stick,long hair,hair ornament,fox ears, fox tail,red tailClothing: korean clothes, red shirt,blue skirt,pleated skirt,long sleeves,hanbok,white bow,red footwear, serafukuThe LoRA is very modular and at this point, I don't know why. All LoRA that i generate demands that whatever details you want should be put in positive prompt. I have no way to fix this man. But i'm researching to fix them.... All critics/recommendations are welcomed so that I can fix what I'm doing wrong.Training Stuff:Colab: <a target="_blank" rel="ugc" href="https://civarchive.com/models/22530">HolowStrawberry's</a>Config:<ul><li>unet: 0.0001</li><li>texenc: 0.00002</li><li>batch size: 2</li><li>repeats: 1</li><li>epoch: 10</li><li>lr scheduler: constants_with_warmup</li><li>lr_warmup_ratio: 0.1</li><li>dim/alpha: 2/1 (yes, you read it right)</li></ul>611021448168921775

Naenara chan | Merryweather comics

naenarachan.safetensors

v1.0

The LoRA is a personification of Naenara Browser based on Merryweather comics.For this one, i used 2/1 dim/alpha.<h1 id="read-before-using">Read before using</h1><h3 id="how-to-use">How to use</h3>add lora in prompt, then use the trigger keywords.Ideal weight: 1can go from 0.6-1<h3 id="keywords">Keywords</h3>Trigger: naenarachanBase: 1girl,solo,red eyes, black hair,single hair bun,hair stick,long hair,hair ornament,fox ears, fox tail,red tailClothing: korean clothes, red shirt,blue skirt,pleated skirt,long sleeves,hanbok,white bow,red footwear, serafukuThe LoRA is very modular and at this point, I don't know why. All LoRA that i generate demands that whatever details you want should be put in positive prompt. I have no way to fix this man. But i'm researching to fix them.... All critics/recommendations are welcomed so that I can fix what I'm doing wrong.Training Stuff:Colab: <a target="_blank" rel="ugc" href="https://civitai.com/models/22530">HolowStrawberry's</a>Config:<ul><li>unet: 0.0001</li><li>texenc: 0.00002</li><li>batch size: 2</li><li>repeats: 1</li><li>epoch: 10</li><li>lr scheduler: constants_with_warmup</li><li>lr_warmup_ratio: 0.1</li><li>dim/alpha: 2/1 (yes, you read it right)</li></ul>611021448168921775

Files with SHA256: a07066885d216f9421732c7f93752a11154ca2985eab8e285e99590aa3e420f7