Original description: *THIS CHECKPOINT IS SDXL1.0 About this version: Less BA-ish, but a good celluloid filter for AnimagineXLv3. Alternate fine-tune on A3-base, use A3's Text Encoder, sacrifice color for better anatomy, will be less cherry-pick than XLv1 (still need tho), but won't get far more better result than XLv1-A3TE. Sometimes one even worse, but other better. TBH, this is pretty much an A3 flat coating DLC, which supports all A3's character. If you want the best BA style result, you'd better use both of v2&v1. Suggestion: - For BA style: XLv2 for generate, XLv1-A3TE for hires-fix, weight 0.55+ - For Celluloid style : A3 for generate, XLv2 for hires-fix., weight 0.6+ ----- TL; DR: Based on Animagine XL V3, use Blue Archive's official artwork as fine-tune dataset for its art style. You are prohibited to use this model for any kind of commercial use. Please read the disclaimer below before you use this model. How-to: a. Suggest prompt order: - character name, 1girl, other tags, quality tags, b. Suggest quality tags (please delete other quality tags in prompts): - flat_coating clear_color highres absurdres best_quality - DO NOT USE 'masterpiece' if you are generating general images. It will ruin the flat coating. c. Suggest negative: - 'nsfw, lowres, worst quality, low quality, bad perspective, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, artist name' d. DO NOT USE blurry as negative prompts. e. Suggest Resolution: same to A3XL, but limited to 1600x900 vertical, horizonal is lower. - Higher resolution = Closer to BA style - CFG 5 Euler A step 25 f. You can treat this like Animagine XL V3, all tag still work at same methods. g. LoRA based on Animagine XL V3 will work fine on it. h. Suggest Upscaler: AnimeVideo v3 i. No color scheme training j. Feel free to give feedback, I need your suggestion for further developments.