The model natively supports images larger than 1024×1024. It is recommended to try 1024×1536, which yields quite good results. The latest LoRA trained with WAI_NSFW-illustrious-SDXL_v14, Recommended parameters: Euler A, CFG: 6.0, 832x1216, 768x1344. Initial prompt: Positive: masterpiece, best quality, amazing quality. negative：lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry 该模型原生支持大于1024×1024的生图，建议尝试一下1024×1536，效果挺好的用WAI_NSFW-illustrious-SDXL_v14训练的最新lora， 用WAl-illustrious V13训练的lora 推荐参数Eluer A，CFG：6.0, 832x1216,768x1344，起手式:正向：masterpiece, best quality, amazing quality, 负向：lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry，（Extra fingers：1.4）