Animagine-XL_4.0_Opt_clear

Animagine-XL_4.0_Opt_clearGuide (External site): English | JapaneseHugging FaceCompare to Animagine-XL_4.0_Opt (Original)Animagine-XL_4.0_Opt_clear | Animagine-XL_4.0_Opt (Original)A fine-tuned version of Animagine-XL 4.0 Opt 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.INT8_ConvRot_HQ (light weight)INT8_ConvRot_HQ is a lightweight version. The CLIP and VAE remain unchanged, while only the intermediate layers of the UNet have been converted to INT8_ConvRot format.Image quality is slightly lower than the original v2, but it is particularly well-suited for fast generation in low-VRAM environments (4-6 GB).INT8_ConvRot is currently supported in ComfyUI and Stable Diffusion webUI Forge NEO.Recommended SettingsGeneralCFG scale: 4-6Sampler: DPM++ 2M SDE (Euler a)scheduler: betaSteps: 15-25 (around 20)Quality Enhancement Tags (same with Animagine-XL 4.0)masterpiece, high score, great score, absurdresRecommended Negative Prompt (same)lowres, bad anatomy, bad hands, text, error, missing finger, extra digits, fewer digits, cropped, worst quality, low quality, low score, bad score, average score, signature, watermark, username, blurryUpscaleryour choice, examples:RealESRGAN_x4Plus Anime 6B (Commercial use)IllustrationJaNai_V1_ESRGAN (No-Commercial use)Detailerworks well.Tips (External site)Steps and Scheduler: English | JapaneseUpscalers: English | JapaneseCFG and Negative Prompt: English | JapaneseImproving Prompt Understanding in SDXL: English | JapaneseLicenseCreativeML Open RAIL++-M