LoRA trained on Lamdimia Do Aximemor 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
Casual Outfit: lamdimia do aximemor, 1girl, suspenders, yellow shirt, skirt, hair bobbles, two side up, long hair
Shop Employee Uniform: lamdimia do aximemor, 1girl, vertical-striped shirt, hair bobbles, two side up, long hair, employee uniform, dress shirt
add "zipper" for the zipper
Gym Outfit: lamdimia do aximemor, 1girl, gym uniform, buruma, hair bobbles, two side up, long hair
Bikini: lamdimia do aximemor, 1girl, hair bobbles, two side up, long hair, white bikini
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
VAE: vae-ft-mse-840000-ema-pruned (for realistic models & 2,5D), kl-f8-anime2, blessed2.vae (for anime models)
Sampler: DPM++ SDE Karras or DPM++ 2M Karras(euler a for img2img upscaling) from time to time im also using DPM++ 2M alt Karras
Steps: 20 to 35
Clipskip: 2
Upscaler : GitHub - pkuliyi2015/multidiffusion-upscaler-for-automatic1111 4x-UltraSharp(for 2,5D & realistic), 4xAnimesharp(for anime)
CFG Scale : 5 to 9 (mostly 7)
LORA weight for txt2img: 0.5-1 (for the examples i mostly used 0.8 and 1)
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
Description
FAQ
Comments (6)
Yo dude, been a while <3 Could you do Broken Covenant Riven next ?
Yo, I have to check if it has enough data. If yes, I'll do it
Thanks man! It's TOP when there are checkpoint comparisons in LORAs, then one has a better idea how it looks like at each one of them :)
Np, yeah, it's also helpful for me to check if the LoRa is working properly or not. Most of the time, this is the first thing I generate, so it gives me an idea of what I should try and which model would look best with the LoRa
@AhriMain so, so :),... please post some info on the last character (Ortinet Airi), if it is possible to realize it or not 🧐
@RiderBond1949 The last time I tried it, the LoRA Quality was quite bad. However, somehow, now it's fine. I retrained it with slightly different tags and settings. I was gone for about 2 weeks, so maybe some settings have been changed. But yeah, it's possible
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.