[LoRA] Mythmaker Irelia | League of Legends

模型介绍：
LoRA trained on Mythmaker Irelia from League of Legends
requested by: @bty_is_within_us
tags: mythmaker irelia, 1girl, hair ornament, hair rings, bare shoulders, dress, detached sleeves, multicolored hair, white hair, earrings, green eyes
add "forehead mark", "thighhighs", for more characteristics
keep in mind that if you add "thighhighs" you'll get more full body shots
anime: YesMix - v1.6 (original), Sweet-mix - v2.1, Zenith - v3
2,5D: Aniverse - Aniverse V1.3, DarkSun, Dark Sushi 2.5D, ERA_09 - v1.0
better hands LoRA: EnvyBetterHands LoCon - beta2
negative embeddings: Fast Negative Embedding (+ FastNegativeV2) - v2

Recommended settings:
▣ Make sure you are aware on the usage instructions of LORA
▣ VAE: vae-ft-mse-840000-ema-pruned (for realistic models & 2,5D), kl-f8-anime2, blessed2.vae (for anime models)
▣ Sampler: DPM++ SDE Karras or DPM++ 2M Karras(euler a for img2img upscaling) from time to time im also using DPM++ 2M alt Karras
▣ Steps: 20 to 35
▣ Clipskip: 2
▣ Upscaler : GitHub - pkuliyi2015/multidiffusion-upscaler-for-automatic1111 4x-UltraSharp(for 2,5D & realistic), 4xAnimesharp(for anime)
▣ CFG Scale : 5 to 9 (mostly 7)
▣ LORA weight for txt2img: 0.5-1 (for the examples i mostly used 0.8 and 1)
▣ Denoise strength upscaling: 0.3 to 0.55

If you want to autocomplete the tags & trigger im using, I recommend using Booru style tag autocompletion for AUTOMATIC1111's Stable Diffusion web UI
For full body shots i recommend using: ComfyUI Impact Pack
or the a1111 alternative GitHub - Bing-su/adetailer

~~~~~~~~~~~~~~~~~~~~~~~o(*￣︶￣*)o~~~~~~~~~~~~~~~~~~~~~~~

示例提示词和参数：
Prompt: (masterpiece, best quality:1.2), intricate details, <lyco:GoodHands-beta2:1>, <lora:lol_mythmaker_irelia-000016:1>, mythmaker irelia, 1girl, hair ornament, hair rings, bare shoulders, dress, detached sleeves, forehead mark, multicolored hair, white hair, earrings, green eyes, textured skin, looking at viewer, solo, light smile, (mature female:1.2)

Negative prompt: FastNegativeV2, drawn by  bad-artist, sketches, (worst quality, low quality:1.5), (extra fingers, deformed hands, polydactyl:1.5), lowres, monochrome, ((grayscale)), bad anatomy, text, watermark, simple background, white background, noise, blurry background, blurry, signature, black background, patreon username

Steps: 35, CFG scale: 7, Sampler: DPM++ 2M Karras, Seed: 3361101774, VAE: vae-ft-mse-840000-ema-pruned.ckpt, Size: 1024x1536, Model: coffeeDonut_21, Version: v1.6.0, VAE hash: c6a580b13a, Model hash: cdfe497045, bad-artist: 2d356134903e", "FastNegativeV2: a7465e7cc2a2, ADetailer model: face_yolov8n.pt, "GoodHands-beta2: c05ed279295e, ADetailer version: 23.8.0, Denoising strength: 0.35, ADetailer mask blur: 4, ADetailer confidence: 0.3, ADetailer dilate/erode: 4, Tiled Diffusion upscaler: R-ESRGAN 4x+ Anime6B, ADetailer inpaint padding: 32, lol_mythmaker_irelia-000016: a9501140f5c7", ADetailer denoising strength: 0.2, Tiled Diffusion scale factor: 2, ADetailer inpaint only masked: True, Clip skip: 2