Fervent Tempo ∆
Character: Rozaliya Olenyeva (Honkai Impact 3)
Battlesuit: Fervent Tempo ∆, original outfit
Pixiv post here
Usage (Important!)
Compatibility
Should work with most anime-like checkpoints. Tested with AOM3, BOM, Hassaku, Grapefruit, PVC-AOAOKO, Cornflower X, etc.
Weight
Recommended 0.825; 0.75~0.90 range works nicely depending on how much flexibility you need.
Trigger Words
No trigger words are required. However:
You can put (mismatched stockings, long hair:1.15) on prompt and (tail, mechanical tail, weapon, sword, holding, holding weapon, holding sword:1.15) on negative prompt for better consistency.
Other
Image Details
Preview images use AOM3 or BOM, unless stated otherwise.
VAE used is orangemix (nai)
Training Details
May vary based on version. See individual versions for details.
Description
Some issues in Release 2 are addressed~!
The training images are the same, but captions isn't. Also moved one image to a lower repeat folder.
Improvements (vs. Release 2):
Tail generation is more controllable with prompts
Slight improvements to outfit accuracy
Slightly more consistent background
Controllable Limitations:
She may have short hair. I don't know why this happens, but adding (long hair:1.25) mitigates this.
Stockings still may be plain black instead of blue + pink. Adding (mismatched stockings:1.15) to your positive prompt mitigates this.
Tails may appear uncontrollably. Adding (tail, mechanical tail:1.15) to negative prompt mitigates this.
Her weapon may appear uncontrollably. Adding (weapon, sword, holding, holding weapon, holding sword:1.15) to negative prompt mitigates this.
Uncontrollable Limitations:
From the viewer's perspective, the right side of her jacket may not be black, and instead gets colored white at times. This is gacha and not controllable.
Some limitations with H content due to training dataset all being SFW.
Training Details (w/ bmaltais/kohya_ss; see Training Data File for full LoRA training parameters extracted with kohya-ss/sd-webui-additional-networks)
Trained on: nai.ckpt (925997e9)
Training Batch Size: 2
LR: 0.0007, UNet LR: 0.0007, TE LR: 0.000175, Scheduler: Cosine w/ Restarts
Epochs: 3, Dim: 32, Alpha: 16, Resolution: 512x512, Clip Skip: 2
*EasyNegative in the example images is an embedding from here.