Sign In

C4PACITOR

834

12.4k

529

Verified:

SafeTensor

Type

Checkpoint Trained

Stats

299

0

Reviews

Published

Oct 14, 2024

Base Model

Flux.1 S

Training

Steps: 60
Epochs: 6

Trigger Words

nsfw
woman
amateur
sex
anime

Hash

AutoV2
88E5263BB3
default creator card background decoration
c0ur4ge's Avatar

c0ur4ge

License:

GREAT SCOTT! Vivid insanity is here!

===========================================================================

X-V1 - 7/1 - Six months to the day, enjoy x_v1 - it's got a bit more kick than our usual models (extensive anatomy and animation tuning). We hope you enjoy, generate responsibly and share below! :)

V3 - 4/29 - d_v3_alpha Q8/Q4 quants released - here we go! your first taste of something new. Enjoy our first GGUF releases! More to follow very soon!

Note: FP8 = Q8 and NF4 = Q4 for d_v3 only.

X-L16HT - 1/1 - The first in the X-series (NSFW tuned) arrives. Enjoy - more to come, please read the description for usage tips/limitations! This 16-step version precedes an 8-step variant and the main X Series proper. NF4 and more this weekend!

Note: Use LoRA with C4PACITOR at slightly lower than normal weights for best results and to avoid anatomy blending.

===========================================================================

C4PACITOR models are created by DR34MSC4PE with all the trappings you've come to expect as well as some cool bonuses:

  • Enhanced realism and photo-realistic concepts, trained on high quality datasets with the latest techniques.

  • Specific anime/illustration tuning to introduce some lost artistic concepts

  • NSFW tuned and capable of realism and artistic/anime images. Female anatomy is well represented with additional fine tuning in the works.

  • Exceptional performance with character/other/stacking Lora

  • Like our work? Buy us a coffee: https://ko-fi.com/dr34msc4pe

===========================================================================

DR34MSC4PE is

c0ur4ge (training/qa/inference code) /

eraser851 (training/captions/tooling code/data/qa)

===========================================================================

Recommendations by base model:

dev - (d_v1/d_v2/a_v)

===========================================================================

CFG: 3-7

Steps: 22-60

Sampler: RES_2M

Scheduler: Beta/Beta57/Bong Tangent

========================================

Hyper8/L16HT - (x-series)

===========================================================================

CFG: 3-6

Steps: 16-32

Sampler: DEIS

========================================
schnell - (s_v0/s_v1):

===========================================================================

Note: 100% Schnell Base

Steps: 2-14

Sampler: DEIS

===========================================================================