[LoRA] WLOP Style LoRA

模型介绍：
WLOP 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 ☕

There is already a model checkpoint for wlop that you should definitely check out. However LoRA's are becoming the new way to basically mix models on the go and add artstyle and characters also combining multiple ones with many different pre-existing models. Wlop style is already used a lot in prompts, especially on Midjourney, so I made this.

For the preview pics I used AnyLoRA and Abyss Orange Mix V2 and a weight of 1 for the offset version (0.6 for the old one). Trigger word is of course wlop. Works well with DreamShaper too but you won't get the perfect style on it (it's trained on anime models). I also used CLIP skip 2.

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: wlop, 1girl, backlighting, bare shoulders, blue eyes, blurry, closed mouth, collarbone, depth of field, dress, expressionless, final fantasy, final fantasy xv, green hair, highres, jewelry, knight, looking at viewer, (lunafreya nox fleuret), necklace, pendant, pink lips, ponytail, short hair, sleeveless, sleeveless dress, solo focus, upper body, white dress <lora:wlop_offset:1>

Negative prompt: mole, anime, (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: 28, CFG scale: 10, Sampler: DPM++ 2M Karras, Seed: 2456899757, ENSD: 31337, Size: 896x1344, Model: AbyssOrangeMix2_nsfw, Mask blur: 4, Model hash: 0873291ac5, Denoising strength: 0.35, Clip skip: 2