CivArchive
    BAXL | Blue Archive Flat Celluloid Style Fine-tune - XLv3-Δ
    Preview 1
    Preview 2
    Preview 3
    Preview 4
    Preview 5
    Preview 6
    Preview 7
    Preview 8
    [VAE Suggested] [SD1.5 + SDXL] Model trainer/creator: 4BEraser Uploaded to MoescapeA by Laanver Phi [Please view the full model detail on CivitAI] DBv1 Source: https://civitai.com/models/212253?modelVersionId=239341 XLv1 Source: https://civitai.com/models/212253?modelVersionId=299095 XLv1-A3TE Source: https://civitai.com/models/212253?modelVersionId=363094 XLv2 Source: https://civitai.com/models/212253?modelVersionId=362412 XLv3-Δ Source: https://civitai.com/models/212253?modelVersionId=426588

    Description

    Original description: *THIS CHECKPOINT IS SDXL1.0 About this version: Base model change to Kohaku Delta. ----- How-to: Prompting logic is same to KohakuΔ: '1girl, , , ' Negative: 'lowres, error, worst quality, low quality, jpeg artifacts, watermark, signature, username' Keep pr clean and tidy'. Suggest prompt length < 75 tokens. Suggestion: a. CFG: 4-7 (higher will have slightly better anatomy) b. Sampler: Euler A @ 25steps c. Resolution: 768 - 1792(ultrawide only), +32 each step. d. Use DanTagGen. - Set a low temperature (<1) - Ban words: sketch, comic, flat color, .*official.*, .*boy.*, mecha, no humans, text, pixel art, speech bubble - Total tag length: short e. Use Hires.Fix - Upscaler: DATx2 - Denoising: 0.4-0.5 f. Use ADetailer. - face_yolov8n.pt If you want generate typical color, put color scheme to at first. Known issues: - halo / heterochromia / .*focus.* seems to be overfitted in some circumstances. Can be helped by put them in negative tags. - Background is not stable, keen to draw something unnecessary even if you type simple background, white background What you should expected from this update: - Better generalization - Closer to Blue Archive style - Beautiful glare Much improved LoRA compatibility based on KohakuΔ. - What you should NOT expected from this update: - Better anatomy, always good hands and feet - easy to use - focus on given prompts (compare to previous version) - multiple person / nsfw support (this is not gonna get any close to pony.) - detailed background