For best outputs: Sampler: Euler a. Steps: 24, cfg 7, CLIP skip 2. VAE: none required. Pos prompt: what you want to see. The model listens well and usually doesn't need big weights. Remember to use the keyword "solo" for 768 x 768 resolutions. Neg prompt: "easynegative, nsfw, 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", being the embedding "easynegative" found in my example runs. Checkpoint Trained.