Trained on 512x512. Best merged with the 768x768 version.
These loras are mostly to be used to merge into other models using Kohya_ss script/bmaltais Kohya_ss gui. You can merge any lora you find to a model with the script/gui so experiment to get the type of look/composition you want in your final model.
The merging of loras work the same as models. The more you merge, the more 'muddy' the output becomes. You can think of it like mixing all the colors on a painter's pallet. It's better to have some restraint when mixing.
An example mix:
SD Model:
./Stable-diffusion/darksun_v60AkaFutasun.safetensors
LoRA model "A" - Model A merge ratio: 0.25
./stable-diffusion-webui/models/Lora/futanarimixV7-v1.1.2-Lora-DAdaptLion-D256-A1-000040.safetensors
LoRA model "B" - Model A merge ratio: 0.25
./stable-diffusion-webui/models/Lora/futanarimixV7-v1.1.3-Lora-DAdaptLion-D256-A1-000025.safetensors
LoRA model "C" - Model A merge ratio: 0.4
./stable-diffusion-webui/models/Lora/futanarimixV6-v1.1.9-Lora-DAdaptLion-D16-A8.safetensors
LoRA model "D" - Model A merge ratio: 0.25
./stable-diffusion-webui/models/Lora/futaveiny.safetensors
Out:
./stable-diffusion-webui/models/Stable-diffusion/futanarimix.safetensors
Description
Not better or worse than epoch-5, just more trained.
FAQ
Comments (3)
should we use these as standalone or use https://civitai.com/models/58633/futanarimix-large-futanari-erection-locon for the standalone lora use??
There's no issues using this lora by itself using whatever model understands futanari. Using it as is will change the style of your output.
I've added a recipe or creating your own model with the style you want using this lora to add futanari to it. The benefit of creating your own model mix is that you will always have the style you want and have futanari at the same time.
@screamlouder understood, but which is the recommended version to use though, this one or the previous one :P they see mto do the same thing