license: other
license_name: bespoke-lora-trained-license
license_link: >-
https://multimodal.art/civitai-licenses?allowNoCredit=False&allowCommercialUse=RentCivit&allowDerivatives=False&allowDifferentLicense=False
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- migrated
- post apocalyptic
- samurai
- tactical
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: null
widget:
- text: ' '
output:
url: 6746206.jpeg
- text: ' '
output:
url: 6761010.jpeg
- text: ' '
output:
url: 6989996.jpeg
Protocal
- Prompt
- Prompt
- Prompt
Model description
This is somewhat a remake of my Kalakaua model from the ground up.
Great for creating heroes with a Cell shaded inspired look.
The merge option is of the New LoRa with the previous calico 6000 model, giving it even more emphasis on the sharp edges and cell shading look.
The training data included a good amount of images of cowboys and samurai with weapons so those would be a good idea to include in the prompt.
--use words like
"post apocalyptic"
"Vagabon"
"samurai"
"tactical clothing"
for the look and use words like--
"wide shot"
"medium shot"
"upper body torso"
"full body shot"
"white background"
for the view
would be good to give you that dynamic range of images of close to the character or full body shots.
Because of how it is merged, you may get a "halo" so you might want to negative prompt something to that effect to reduce that a bit
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Use it with the 🧨 diffusers library
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('runwayml/stable-diffusion-v1-5', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('brushpenbob/protocal', weight_name='Protocal.safetensors')
image = pipeline('Your custom prompt').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers