Torino Aqua Style LoRA - CivArchive (CivitAI Archive)

Torino Aqua Style LoRA - offset

NSFW

Torino Aqua style LoRA

Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕

A friend asked me to do this, as Torino Aqua is his favourite artist.
I'm quite happy with the result. I suggest a weight of 1 for the offset version (0.6 for the old one) on Anything V4.5 or Abyss Orange V2. Trigger word is of course torino aqua. Second image courtesy of Gozogo123〔✯〕 from Discord.

How to use LoRA's in auto1111:

Update webui (use git pull like here or redownload it)
Copy the file to stable-diffusion-webui/models/lora
Select your LoRA like in this video
Make sure to change the weight (by default it's :1 which is usually too high)

Description

FAQ

Comments (6)

AiHanaJan 30, 2023· 1 reaction

CivitAI

LoRA model torinoAquaStyleLora_v1(6cb1243fe18c) loaded: IncompatibleKeys(missinkeys=['lora_te_wrapped_transformer_text_model_encoder_layers_0_self_attn_k_proj.alpha', "... and 263 alphas. The model doesn't have alpha, use dim (rannk) as alpha. You can ignore this message."], unexpected_keys=[])

setting (or sd model) changed. New networks created.

i got this message while trying to run with this. Any help would be nice

Lykon

Author

Jan 30, 2023

I'd need more info. Like what you're using to load it, on which model, etc. However first try to redownload it, maybe it's just corrupted. That hash doesn't match with the one on civitai

AiHanaJan 31, 2023

@lykon so i load with with abyss orange mix 2 hard safetensors with the orangmix vae using automatic1111 webui.

Lykon

Author

Jan 31, 2023

@AiHana but how are you loading it?

AiHanaFeb 1, 2023

@lykon i followed this guide https://github.com/kohya-ss/sd-webui-additional-networks

edit: nvm, i think i managed to fix it. instead of using the guide above, i used the build in Lora. Also, in the examples, it uses this <lora:torino_aqua:0.6> and the correct way is <lora:torinoAquaStyleLora_v1:0.6> since it should follow the file name

mpzFeb 6, 2023

@Lykon your work is nice. i want to know which code you used to trainning? is it kohya-ss/sd-scripts? if it is the code from kohya-ss/sd-scripts, can you tell me how should i set Trigger Word for trainning, like your "torino aqua". i will be grateful for your gracious help.

LORA

SD 1.5

by Lykon

Download (Beta) View on CivitAI