santa hat
deerdeer nosedeer glow
Sign In

Fino Bloodstone | Yuusha ni Narenakatta Ore wa Shibushibu Shuushoku wo Ketsui Shimashita

170
904
8
Verified:
SafeTensor
Type
LoRA
Stats
694
Reviews
Published
Jul 5, 2023
Base Model
SD 1.5
Training
Steps: 3,672
Epochs: 17
Trigger Words
fino bloodstone, 1girl, yellow apron, ponytail, red apron, puffy short sleeves, red skirt, blonde hair
fino bloodstone, 1girl, track suit, hood, zipper, long hair
fino bloodstone, 1girl, strapless dress, hairband, white dress, hair ornament, bare shoulders, choker, elbow gloves
fino bloodstone, 1girl, asymmetrical shirt, t-shirt, off shoulder, ponytail, blonde hair
Hash
AutoV2
7BC0B1AB24
default creator card background decoration
Holiday 2023: 5 lights
AhriMain's Avatar
AhriMain

LoRA trained on Fino Bloodstone from Yuusha ni Narenakatta Ore wa Shibushibu Shuushoku wo Ketsui Shimashita (I Couldn't Become a Hero, so I Reluctantly Decided to Get a Job I Couldn't Become a Hero, so I Reluctantly Decided to Get a Job)

requested by: @RiderBond1949

Version 2 I experimented with a learning rate of 0.0001 and used six outfits that are closer to the original but less flexible and more overtrained. Version 1 is more stable, so I would generally recommend using it.

models used

anime: Cetus-Mix - V4, YabaL_Mix - V5, MeinaPastel - V6 ( Pastel ), Sweet-mix - v2.1

2,5D: Animesh - Animesh-Full V1.5, PastelDiffusedMix - V2.1

negative embeddings: bad_prompt, negative_hand, ng_deepnegative_v1_75t, bad-artist, EasyNegative

Recommended settings:

  • Make sure you are aware on the usage instructions of LORA

  • Denoise strength upscaling: 0.3 to 0.55

If you want to autocomplete the tags & trigger im using, I recommend using Booru style tag autocompletion for AUTOMATIC1111's Stable Diffusion web UI

For full body shots i recommend using: ComfyUI Impact Pack

or the a1111 alternative GitHub - Bing-su/adetailer