参考图都是原图，直接保存放到webui里就能读取参数！如果可以，请在评论区展示一下你们用该模型生成的图片，我想看一下你们使用它的表现^_^

谈秋

PileDream.safetensors

PileDream

愚者漫步

GENERATION DATA FOR IMAGE ONEGENERATION DATA FOR IMAGE TWO1girl, ?, alcohol, blush, brown_background, brown_eyes, drunk, hakama, hakama_skirt, japanese_clothes, kimono, long_hair, looking_at_viewer, miko, off_shoulder, open_mouth, red_hakama, sitting, skirt, solo, twitter_username, white_kimono, white_ribbonNegative prompt: easynegativeENSD: 31337, Size: 512x768, Seed: 2544594555, Model: PileDream, Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 6, Clip skip: 2, Model hash: 59fcda40c7, Hires steps: 10, Hires upscale: 2, Hires upscaler: Latent (nearest-exact), Denoising strength: 0.6, Wildcard negative prompt: easynegative

Files with SHA256: c939e437383a6db55fb3296b10293fe7becfff6a938288c267a8eb6c1485ab5a