Type | |
Stats | 101 449 |
Reviews | (35) |
Published | Sep 5, 2024 |
Base Model | |
Training | Epochs: 25 |
Usage Tips | Clip Skip: 2 |
Trigger Words | SmokerOP white_Smoker_hair, black_Smoker_scar across eye, brown_Smoker_eyes, TashigiOP dark blue_Tashigi_female hair, |
Hash | AutoV2 B47EF898F4 |
Forward together marines!
SMOKER and TASHIGI from ONE PIECE!
πMain Trigger Tagsπ
Pair = SmokerOP, 1boy, couple focus, TashigiOP, 1girl, anime screencap,
Smoker = SmokerOP, 1boy, male focus, anime screencap,
Tashigi = TashigiOP, 1girl, female focus, anime screencap,
You can try using the "hetero" tag :D
βOther Unique Tagsβ
Check out Gallery (Highly Recommended)
Experiment on your own
Do not use all Other Unique Tags on a generation to get the character's outfit. Use only the big tags like the Unique tag for shirt and pants...then the details will follow (not exactly to the T but it will save you from a noisy mess)
π«Dadada's Berriesπ«
Use with Pony Diffusion XL Based models
Remove "Anime screencap" for flexibility
Remove "Other Unique Tags" or the character name within that unique tag for flexibility
πGENDER BENDINGπ
Gender bend by replacing "1boy, male focus" with "1girl, female focus" vice versa
Use with Male centered Pony Diffusion XL Based models or LoRA styles, vice versa
Reduce LoRA weight to 0.9 when prompting for male, vice versa or...
Reduce tag weight of unique tags with [__]
Add tags related to the male anatomy (abs, pecs, penis, etc.), vice versa
π§MODEL CONTROLπ§
Better Checkpoint infusion with LoRA weight 0.6-0.8 along with CFG increase
Some checkpoint models will force additional elements, add undesired elements in negative or specify in positive with "no type undesired element"
Some flowy elements from certain LoRAs are expected to be messy. You may want to add these elements without the other unique clothing tags
You can keep the "Anime Screencap" while lowering the LoRA weight...this helps the checkpoint influence while keeping the Main Character's integrity intact <33
π©π»βπ³BAKING OWN OC!π©π»βπ³
When MIXING Character LoRAs (mine), reduce weight to 0.6-0.8. while keeping their mother tags in.
When MIXING Character LoRAs (not mine but with mine), reduce my LoRAs weight to 0.5-0.8. while keeping their mother tags in.
When influencing own imagination with my LoRA, reduce weight at the minimum of 0.35 and maximum of 0.7
Relationship at Work (?) in TENSORART <@0@>/"""
https://tensor.art/models/769839876960118443/Smoker-and-Tashigi-or-One-Piece!-v1
π©NOTE:
Ask for my permission if you wish to reprint or upload my models on sites I have no knowledge of. I would love it if my LORAs can only be downloaded through CIVIT. Thank you <333