1 image = few seconds(8 steps/cfg scale 1.5~2.5), more "clear" colors compared to normal sdxl turbo LoRA/sdxl lightning LoRAFor Pony/SD XL anime models and realistic(juggernautXL and similars) modelsUPDATE v3: lightning version(sdxl_lightning_8step_lora), same speed better qualityUPDATE v2: With a low cfg(1.5~2.5) now the images are not blurred like in v1shiny_style_xl_turbo is a LoRA based on sdxl turbo, you can use the TURBO with any stable diffusion xl checkpoint, few seconds = 1 image(3 seconds with a nvidia rtx 3060 12 GB with 1024x768 resolution)Merged: sd xl lightning LoRA + selected imagesRecommended anime checkpoint: base_anime_style_xl, true_anime_style_xl, Animagine XL V3.1, AAM XL (Anime Mix), autismmixSDXL_autismmixConfetti, Confetti Comrade Mix, Pony Diffusion and similarsRecommended realistic checkpoint: juggernautXL and similarsWeight: 1 recommendedSampling method: LCM(install animatediff extension if you don't see it in sampling list)/Euler ASampling steps: 8+v2/v3:CFG Scale: 1.5~2.5v1:CFG Scale: 3~5(cfg with higher value than "normal" sd xl turbo)Stable Diffusion XL Lightning LoRa: https://huggingface.co/ByteDance/SDXL-LightningStable Diffusion XL Turbo LoRA: https://civitai.com/models/215485Stable Diffusion XL Turbo Checkpoint : https://huggingface.co/stabilityai/sdxl-turbo---Buy me a Kofi(if you like my works): https://ko-fi.com/shiroppoPatreon: https://www.patreon.com/ShiroppoFellow Me on Twitter/X: https://twitter.com/ShiroppoTwitPixiv: https://www.pixiv.net/users/7058273Instagram: https://www.instagram.com/shiroppo_real/My pages: https://solo.to/shiroppoPlease rate my works, if you have time, thank you!---
