anima_pencil-XL_clearGuide (External site): English | JapaneseHugging FaceCompare to Animagine-XL_3.0 (Original)Animagine-XL_3.0_clear | Animagine-XL_3.0 (Original)A fine-tuned version of Animagine-XL_3.0 model, designed to produce clearer and more vibrant outputs.Compared to the original, this model generates illustrations with higher contrast, richer colors, and more refined details.Recommended SettingsGeneralCFG scale: 4-6Sampler: DPM++ SDE, Euler Ascheduler: betaSteps: 15-25 (around 20)Upscaleryour choice, examples:RealESRGAN_x4Plus Anime 6B (Commercial use)IllustrationJaNai_V1_ESRGAN (No-Commercial use)Detailerworks well.Merge RecipeUNET: Animagine-XL_3.0time_embed.: x0.95input_blocks.0: x0.92CLIP: Animagine-XL_3.0clip_l.embeddings: x0.5clip_l.encorder_layers.1: x0clip_g.encorder_layers.31: x0VAE: SDXL_clear_vaeTips (External site)Steps and Scheduler: English | JapaneseUpscalers: English | JapaneseNegative Prompt: English | JapaneseImproving Prompt Encoding in SDXL: English | JapaneseLicenseFair AI Public License 1.0-SDLicense Official Page
