模型简介: Murata Yuusuke (One-Punch Man) style LoRA Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕ Another great mangaka. This LoRA can do colored artworks or b&w stuff and can imitate Murata's style pretty well. I've tested it on some models, but Anything V4.5 seems to be the one that works best here, as it has less of a defined style. Weight is usually around 0.6, but the ideal one can vary between 0.2 and 0.7 (yes, even 0.2, this can be quite strong sometimes). Triggers with murata yuusuke but it's optional. NOTE: this is not a character LoRA. The fact that it can imitate some OPM characters is collateral, but this is very much a style model. If you want OPM characters you'll have to describe them as shown in the examples and you also need a bit of luck. Thanks to Aojiru on Discord for helping me test the model and prepare the Example images. How to use LoRA's in auto1111: ▣ Update webui (use git pull like here or redownload it) ▣ Copy the file to stable-diffusion-webui/models/lora ▣ Select your LoRA like in this video ▣ Make sure to change the weight (by default it's :1 which is usually too high) ~~~~~~~~~~~~~~~~~~~~~~~o(* ̄︶ ̄*)o~~~~~~~~~~~~~~~~~~~~~~~ 示例提示词和参数: Prompt: murata yuusuke, saitama \(one-punch man\), one-punch man, 1boy, bald, casual clothes, shopping bag , white shirt, blue hoodie, outdoors, <lora:murata_yuusuke:0.6> Negative prompt: (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, watermark, signature, text, logo Steps: 30, CFG scale: 9, Sampler: DPM++ 2M Karras, Seed: 4205367616, ENSD: 31337, Size: 512x768, Mask blur: 4, Model hash: 195c43b15e, Denoising strength: 0.13, SD upscale overlap: 64, SD upscale upscaler: 4x_foolhardy_Remacri, Clip skip: 2 |
1人表示很赞