ourIllustrious v1 – an all-around model that excels at both realism and anime WITHOUT ANY LORAs.Prompt quality tags:<ul><li>At the start of a positive prompt, I highly recommend adding the word: newest</li><li>At the start of a negative prompt, I highly recommend adding the word: oldest</li><li>If not using Textual inversion (embeddings) in positive prompt, always append at end of positive prompt: masterpiece, best quality</li><li>If not using Textual inversion (embeddings) in negative prompt, always append at start of negative prompt: 3d, worst quality, bad quality, low quality, lowres, blurry, censor, bad anatomy, deformed</li></ul>Style modifiers:<ul><li>For realistic images append at end of prompt: artstation, realistic</li><li>For 2D / anime images append at end of prompt: anime screencap, anime coloring</li></ul>Textual inversion (embeddings): Use lazypos (positive) and lazyneg (negative) from janxd to steer style via textual inversion embeddings. (Recomendation)Sampler &amp; settings:<ul><li>Sampler: DPM++ 2M Karras</li><li>Steps: 30.</li><li>Guidance (CFG scale): 2.</li></ul>Resolution: 1024 × 1536 or any resolution with 1024 width or height.VAE: Skip using VAE; built-in backend already handles it.Model base: WAI-NSFW-illustrious-SDXL v14

ourIllustrious

anyIllustrious_v7_dpoXbodySlideXmyStyleXmaelleXeveStellarXstabil_1058333.safetensors

v1.0

ourIllustrious v1 – an all-around model that excels at both realism and anime WITHOUT ANY LORAs.Prompt quality tags:<ul><li>At the start of a positive prompt, I highly recommend adding the word: newest</li><li>At the start of a negative prompt, I highly recommend adding the word: oldest</li><li>If not using Textual inversion (embeddings) in positive prompt, always append at end of positive prompt: masterpiece, best quality</li><li>If not using Textual inversion (embeddings) in negative prompt, always append at start of negative prompt: 3d, worst quality, bad quality, low quality, lowres, blurry, censor, bad anatomy, deformed</li></ul>Style modifiers:<ul><li>For realistic images append at end of prompt: artstation, realistic</li><li>For 2D / anime images append at end of prompt: anime screencap, anime coloring</li></ul>Textual inversion (embeddings): Use lazypos (positive) and lazyneg (negative) from janxd to steer style via textual inversion embeddings. (Recomendation)Sampler &amp; settings:<ul><li>Sampler: DPM++ 2M Karras</li><li>Steps: 30.</li><li>Guidance (CFG scale): 2.</li></ul>Resolution: 1024 × 1536 or any resolution with 1024 width or height.VAE: Skip using VAE; built-in backend already handles it.Model base: WAI-NSFW-illustrious-SDXL v14

Files with SHA256: 212d525865515398763df0c8a5a4a543bf7cad68427df47170f2ad21f25b85cd