这是一个 LoRA,用于增强/减少细节,同时保持整体风格/特征;它适用于各种基础模型(包括动漫和现实模型)/风格LoRA/角色LoRA等。
应用自己的体重;该 LoRA 可用于任何重量上/下至 2/-2 的重量!
小技巧:LoRA模型 好比皮肤 需要结合其它大模型使用,只需要在正常生成流程中添加触发词,即可启用LoRA模型附着添加到图像上
注意:使用负权重来减少细节!
⚠️警告
- 因不道德使用本模型而产生的任何法律责任由您自行承担
- 对于一般个人用途以外的任何用途,请务必与作者联系
本文件转载免费提供无需付费,请勿再次转载出售,一切版权归作者所有,仅允许个人学习交流使用,禁止商用,由此引起一切问题有使用违规者承担
范例:
(volumetric lighting, Highres), (Detailed Illustration), Ultra-Detailed, 8k, sam yang,
1girl, animal on shoulder, bird, black-framed eyewear, red eyes, black hair, blue sky, highly detailed background, cityscape, clear sky, coat, day, earrings, eyewear hang, eyewear removed, fur coat, jacket, jewelry, long hair, looking to the side, outdoors, power lines, red lips, sky, smile, snow, solo, sunglasses, white bird, white coat, winter, winter clothes,
((masterpiece))
Negative prompt: simple background, (painting by bad-artist-anime:0.9), (painting by bad-artist:0.9), watermark, text, error, blurry, jpeg artifacts, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, artist name, (worst quality, low quality:1.4), bad anatomy
Steps: 55, VAE: anythingKlF8Anime2VaeFtMse840000_klF8Anime2.safetensors, Size: 512×744, Seed: 2910829878, Model: useless_animerge_25D_v12, Refiner: hardcoreHentai_v12BakedVAE [f2e7c9005b], Version: 1.6.1, Sampler: DPM++ 2M Karras, VAE hash: e9ed949371, CFG scale: 7, Model hash: 0de69859c1, “add_detail: 7c6bad76eb54, Hires steps: 65, hairdetailer: 528c2e4d0627”, Hires upscale: 1.7, Hires upscaler: R-ESRGAN 4x+, Refiner switch at: 0.8, Denoising strength: 0.5