``` ==================== USAGE GUIDE ==================== Model Type: Hybrid (supports both tag-based and natural language prompts) Prompt Structure: - Tags: 1girl, solo, haruna, hews, looking at viewer, night, dark, light smile - Natural: A girl named Haruna from Blue Archive, in the style of Hews, looking at the viewer with a light smile in the middle of the night - Hybrid: 1girl, haruna, blue archive, in the style of Hews, she is looking at the viewer and showing a light smile, dark, night ==================== SPECIAL TAGS ==================== Same as Illustrious XL 1.0, with additional newly introduced temporal tags such as: year 2005, year 2015, year 2020, ... year n ==================== RECOMMENDED SETTINGS ==================== Positive Prompt: masterpiece, best quality, very aesthetic, sensitive, absurdres Negative Prompt: lowres, bad quality, worst quality, bad anatomy, bad hands, sketch, jpeg artifacts, ugly, poorly drawn, censor, signature, watermark Sampler Steps: 28 (recommended range 25 – 30) CFG Scale: 5 (recommended range 4 – 7) Preferred Sampler: Euler a ==================== RECOMMENDED RESOLUTIONS ==================== Training Resolution: 1024 × 1024 Supported Native Resolutions: - 1024 × 1024 (1:1, Square) - 1152 × 896 (9:7, Horizontal) - 896 × 1152 (7:9, Vertical) - 1216 × 832 (19:13, Horizontal) - 832 × 1216 (13:19, Vertical) - 1344 × 768 (7:4, Horizontal) - 768 × 1344 (4:7, Vertical) - 1536 × 640 (12:5, Horizontal) - 640 × 1536 (5:12, Vertical) ==================== STYLE SUGGESTIONS ==================== faux traditional media, watercolor, oil painting, impressionism, impasto, abstract, chiaroscuro, fine art parody, art nouveau, etc. ```