CivArchive
    Fluffity (SD1.5) - v2.5-Failed/Last Version
    NSFW
    Preview 15173879
    Preview 15174029
    Preview 15174201
    Preview 15174298
    Preview 15174522
    Preview 15176595
    Preview 15177047

    Huggingface Repo: https://huggingface.co/lex-hue/Fluffity

    Use e621 tags (no underscore), Artist tag are very effective (SD/e621 artist)

    ClipSkip: Stop at CLIP layers=1 (SD=1, NAI=2) [Settings\Stable Diffusion\Clip skip]

    Example Setting

    Txt2img Setting

    • Steps = 15~35

    • Sampler = Any

    • CFG scale = 5~25

    • Negative embeddings = fluffity-neg ※[SD-WebUI\embeddings]

    Hires. fix

    • Hires steps = 15

    • Denoising strength = 0.45~0.5

    • Hires upscaler = 4x-UltraMix_Smooth ※[SD-WebUI\models\ESRGAN]

    Img2img Resize

    • Scale to = 1.5~2.0

    • Denoising strength = 0.45~0.5

    • ControlNet0 = softedge_hed, control_v11p_sd15_softedge

    • ControlNet0 Weight = 0.4~0.5

    • ControlNet0 Pixel Perfect = true

    • ControlNet1 = Reference

    • ControlNet1 Weight = 0.2~0.3

    • ControlNet1 Pixel Perfect = true

    SD Setting

    • Stop at CLIP layers = 1

    • Eta noise seed delta = 0

    Txt2img Animated Diff

    • Steps = 20~50

    Description

    • Small Improvements

    • Last Version of SD1.5 (In short-term Improvement)

    • Planning to either do SDXL or SD1.5 v-pred

    • This version should only improve the overall Quality

    • This model isnt as Great as the other Versions before. There were many errors in Training.

    • Clip skip 2 seems to sometimes work and not work. It was an mistake of mine to think its better than Clip skip 1.

    • There was some Personal Mishaps. v2.5 isnt the most recommended version.

    FAQ

    Checkpoint
    SD 1.5

    Details

    Downloads
    364
    Platform
    CivitAI
    Platform Status
    Available
    Created
    6/8/2024
    Updated
    4/22/2026
    Deleted
    -

    Files

    fluffitySD15_v25FailedLastVersion.safetensors