2023.05.27 updated, Charlotte is so cute in new event, so I retrained with more picturesbase model: nai anime full prunedRecommended weight 0.8-1.0Trigger word and prompt:<ul><li>(charlotte_\(genshin\)), 1girl, hat, red headwear, monocle, pink_hair, white_gloves, red_jacket, long_sleeves, off_shoulder, shirt, bare shoulders,</li></ul>Training info:<ul><li>based model：nai anime full pruned</li><li>47 images for 8 repeats, 13 epochs, batch size = 2</li><li>resolution : 768x768</li><li>Optimizer：Lion, rank=32, alpha=16</li><li>Learning rate = 3e-5, Unet learning rate = 1.5e-5, Text Encoder learning rate= 3e-5</li></ul>======= old version =======base model Anything4.5trained for 20 epoches with 20 images(512x768) 10 repeats and merge self-trained painting styleis hard to present the character perfectly, may look slightly different, such as having long hair or the wrong clothes colorbut still cuteRecommended weight 0.8~0.6<a target="_blank" rel="ugc" href="https://www.google.com/search?sxsrf=APwXEde4Dbi3bA4L9CjLN7_p5RD_tKWfWQ:1684091224838&amp;q=prompt&amp;spell=1&amp;sa=X&amp;ved=2ahUKEwiV7ubZwPX-AhXM7GEKHdzfDEUQkeECKAB6BAgIEAE">prompt:</a> 1girl, charlotte, hat, medium_hair, monocle, pink_hair, solo, green_eyes, gloves, red_jacket, long_sleeves, off_shoulder, shirt

Charlotte Genshin Impact

charlotte_v1.safetensors

charlotte_genshin_v1.0

v2.0

Mod from <a target="_blank" rel="noopener noreferrer nofollow" href="https://civitai.com/models/66139?modelVersionId=70787">Charlotte Genshin Impact - charlotte_genshin_v1.0 | Stable Diffusion LoRA | Civitai</a>Trigger WordsCHARLOTTE2023.05.27 updated,Charlotte is so cute in new event, so I retrained with more picturesbase model: nai anime full prunedRecommended weight 0.8-1.0Trigger word and prompt:<ul><li>(charlotte_\(genshin\)), 1girl, hat, red headwear, monocle, pink_hair, white_gloves, red_jacket, long_sleeves, off_shoulder, shirt, bare shoulders,</li></ul>Training info:<ul><li>based model：nai anime full pruned</li><li>47 images for 8 repeats, 13 epochs, batch size = 2</li><li>resolution : 768x768</li><li>Optimizer：Lion, rank=32, alpha=16</li><li>Learning rate = 3e-5, Unet learning rate = 1.5e-5, Text Encoder learning rate= 3e-5</li></ul>======= old version =======base model Anything4.5trained for 20 epoches with 20 images(512x768) 10 repeats and merge self-trained painting styleis hard to present the character perfectly, may look slightly different, such as having long hair or the wrong clothes colorbut still cuteRecommended weight 0.8~0.6<a target="_blank" rel="ugc" href="https://www.google.com/search?sxsrf=APwXEde4Dbi3bA4L9CjLN7_p5RD_tKWfWQ:1684091224838&amp;q=prompt&amp;spell=1&amp;sa=X&amp;ved=2ahUKEwiV7ubZwPX-AhXM7GEKHdzfDEUQkeECKAB6BAgIEAE">prompt:</a> 1girl, charlotte, hat, medium_hair, monocle, pink_hair, solo, green_eyes, gloves, red_jacket, long_sleeves, off_shoulder, shirt

Files with SHA256: bfb991eb7746c8777d3e172b3f5b8be08d640b378a48d7e39c200cbdcdac972d