所有分类
  • 所有分类
  • 模型
  • 作品
像素动漫角色画风SDXL LoRA

像素动漫角色画风SDXL LoRA

作者:Luminable
基于模型:SDXL 1.0
模型大小:650 MB
下载方式:百度/夸克
资源下载
仅限注册用户下载,请先

本次更新的LoRA各来源的超过40,000张图片训练而成。

由于SDXL的VAE的latent-to-pixel比例为1:8,直接使用此LoRA就能生成较为规整的像素风图像。如果需要更精确的像素风效果,可通过后期处理(使用NEAREST进行1/8缩小再放大)获得严格对齐的像素画。

训练数据量的增加大幅提升了泛化能力,对各种画风标签的适应性更好。

新版本在2048×2048的数据集上进一步训练,高分辨率下的效果得到了提升。

作品参照

像素动漫角色画风SDXL LoRA插图7
fujita kotone,
zolvatory,fukuro_daizi
<lora:pixel_base_vpred1_0:1>
Negative prompt: nsfw, worst quality, old, early, low quality, lowres, signature, username, logo, bad hands, mutated hands, mammal, anthro, furry, ambiguous form, feral, semi-anthro,high contrast
Steps: 28, CFG scale: 4, Sampler: Euler a, Seed: 1040193572, Size: 1280x1792, Model: noobaiXLNAIXL_vPred10Version, Version: f2.0.1v1.10.1-previous-614-ga8de9ae7, Model hash: bb85cf4f43, Schedule type: SGM Uniform, Noise Schedule: Default
像素动漫角色画风SDXL LoRA插图8
aris (maid) (blue archive),tomoo (tomo) ,tatsuya (trypaint) 
 upper body, maid headdress, maid dress, blush :D, (half-closed eyes, seductive smile:1.2), hand on own cheek, looking at viewer, leaning forward, heavy breathing
<lora:pixel_base_vpred1_0:1>
Negative prompt: nsfw, worst quality, old, early, low quality, lowres, signature, username, logo, bad hands, mutated hands, mammal, anthro, furry, ambiguous form, feral, semi-anthro,high contrast, out of frame,
Steps: 28, CFG scale: 4, Sampler: DPM++ 2M SDE, Seed: 2033408785, Size: 1280x1536, Model: noobaiXLNAIXL_vPred10Version, Version: f2.0.1v1.10.1-previous-614-ga8de9ae7, Model hash: bb85cf4f43, Schedule type: SGM Uniform, Noise Schedule: Default
像素动漫角色画风SDXL LoRA插图9
japanese girl,brack short hair,volleyball uniform,
1girl, 
masterpiece, best quality, looking at viewer, CartoonyIllustrious,large breasts, smile
Negative prompt: crown, worst quality, low quality, lowres, jpeg artifacts, bad anatomy, bad hands, watermark
Steps: 14, CFG scale: 4, Sampler: Euler a, Seed: 1956563565, Size: 832x1216, nsfw: false, draft: false, extra: [object Object], width: 832, height: 1216, quantity: 2, workflow: txt2img, baseModel: Illustrious, Created Date: 2024-12-24T1020:45.0928922Z, Clip skip: 2
资源下载
下载价格免费
作者:Luminable
基于模型:SDXL 1.0
模型大小:650 MB
下载方式:百度/夸克
本内容及资源均来自网络,版权归原作者所有,仅供个人学习研究,请勿商用和侵犯他人肖像,如需商用请联系原作者。若原作者内容有侵权之处请速联系我们,我们将会在24小时内删除。
0
显示验证码
没有账号?注册  忘记密码?

社交账号快速登录

微信扫一扫关注
如已关注,请回复“登录”二字获取验证码