LoRA trained on AhriAnime models arent that good yet on sdxl but some 2.5D/3D checkpoints are really really goodmodels: <a target="_blank" rel="ugc" href="https://civarchive.com/models/122822/crystal-clear-xl">Crystal Clear XL - CCXL</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/5273?modelVersionId=137252">WyvernMix (1.5 &amp; XL) - XL v1.1</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/118009">国风4 GuoFeng4 XL - V1.0-Real-Beta</a>comfyui workflow is embedded in the picturesthis embedding helps with hands: <a target="_blank" rel="ugc" href="https://civarchive.com/models/119032/unaestheticxl-or-negative-ti">unaestheticXL | Negative TI - v1.3</a>ComfyUI custom notes that were used:<a target="_blank" rel="ugc" href="https://civarchive.com/models/33192/comfyui-impact-pack">comfyui impact pack</a>SDXL <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0.safetensors">Base Model</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/blob/main/sd_xl_refiner_1.0.safetensors">Refiner</a> and <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/sdxl-vae/blob/main/sdxl_vae.safetensors">VAE</a>Recommended settings:<ul><li>Make sure you are aware on the usage instructions of LORA</li></ul><ul><li>VAE: <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/sdxl-vae/blob/main/sdxl_vae.safetensors">sdxl_vae.safetensors · stabilityai/sdxl-vae at main (</a><a target="_blank" rel="ugc" href="http://huggingface.co">huggingface.co</a><a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/sdxl-vae/blob/main/sdxl_vae.safetensors">)</a></li></ul><ul><li>Sampler: DPM++ SDE Karras or DPM++ 2M Karras</li><li>Steps: 20 to 35</li><li>Clipskip: 1</li><li>Upscaler : <a target="_blank" rel="ugc" href="https://mega.nz/folder/qZRBmaIY#nIG8KyWFcGNTuMX_XNbJ_g/file/vRYVhaDA">4x-UltraSharp(for 2,5D &amp; realistic)</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/konohashinobi4/4xAnimesharp/tree/main">4xAnimesharp(for anime)</a></li><li>CFG Scale : 5 to 9 (mostly 7)</li><li>LORA weight for txt2img: 0.5-1 (for the examples i mostly used 0.8 and 1)</li></ul><ul><li>Denoise strength upscaling: 0.3 to 0.55</li></ul>For full body shots i recommend using: <a target="_blank" rel="ugc" href="https://civarchive.com/models/33192/comfyui-impact-pack">ComfyUI Impact Pack</a>or the a1111 alternative <a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">GitHub - Bing-su/adetailer</a>

Ahri SDXL | League of Legends

ahri_sdxl_lowlearningrate-000024.safetensors

v1.0

Ahri

ahri, 1girl, long hair, animal ears, whisker markings, korean clothes, cleavage, detached sleeves

Files with SHA256: f2d9a830f8abc2a86a4c2baeb56e2310833178e0ec78ac97e863108ae5b34829