欢迎光临散文网 会员登陆 & 注册

Stable Diffusion AI绘图 (戏装 Chinese Opera

2023-06-07 17:39 作者:PROMETHEUS--X  | 我要投稿

要用到插件:

ControlNet 插件   https://gitcode.net/ranting8323/sd-webui-controlnet.git

stable-diffusion-webui-composable-lora-main   https://github.com/a2569875/stable-diffusion-webui-composable-lora.git

stable-diffusion-webui-two-shot-main   https://github.com/ashen-sensored/stable-diffusion-webui-two-shot.git


parameters:

(8k,best quality,masterpiece:1.2),absurdres,(realistic, photo-realistic:1.3),extremely detailed,ultra detailed,ultra highres,RAW photo,film grain,(Fujifilm XT3),wallpaper,CG unity,official art,extremely delicate and beautiful,(intricate details:1.3), hyper detail, finely detailed,huge filesize,perfect hand,cute,(illustration),

(outdoors, classical Chinese garden),dramatic angle,

AND 1girl,chinese clothes, opera costumes,beautyfull intricacy clothing, decorative pattern details,black hair,<lora:ChineseOperaCostumes_v10:0.7>

AND (xiaosheng),1boy,green chinese cloth,short hair,black hair,<lora:ChineseOperaCostumes_v15:0.75>

Negative prompt:

bad-hands-5 easynegative negative_hand-neg,(worst quality, low quality:1.4), nsfw, (blush:1.3), (extra fingers:1.2),cross-eyed,(signature, watermark, username,letter, letterboxed, copyright name, copyright, chinese text, artist name, name tag, company name, name tag, text, error),


Steps: 38, Sampler: DPM++ 2M Karras, CFG scale: 5.5, Size: 1024x768, Model: GuoFeng3_Fix, Denoising strength: 0.48, ControlNet 0: "preprocessor: canny, model: control_v11p_sd15_canny [d14c016b], weight: 1, starting/ending: (0, 1), resize mode: Crop and Resize, pixel perfect: True, control mode: Balanced, preprocessor params: (512, 100, 200)", Hires upscale: 1.35, Hires upscaler: 4x-UltraSharp


Stable Diffusion AI绘图 (戏装 Chinese Opera的评论 (共 条)

分享到微博请遵守国家法律