metadata

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
  - wings
  - style
  - gargoyles
  - the protoart
  - gargoyles comic
  - protoart
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: loincloth
widget:
  - text: ' '
    output:
      url: 26187411.jpeg
  - text: ' '
    output:
      url: 26185137.jpeg
  - text: ' '
    output:
      url: 26182590.jpeg
  - text: ' '
    output:
      url: 26182502.jpeg
  - text: ' '
    output:
      url: 26182501.jpeg

Flux Gargoyles

Model description

Updated version of my XL and original 1.5 model.

Created this LoRa based off of the classic 90s cartoon series "Gargoyles"

Add this to your arsenal of tools to create fun designs- used terms like

"gargoyles" "medieval" "loincloth" "blue skin" "wings"

claws

to aid in the overall results

Tested this using a few different base models such as “anything v3” and some of my own cartoon custom models

Trigger words

You should use loincloth, Gargoyles_comic to trigger the image generation.

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('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('brushpenbob/flux-gargoyles', weight_name='Flux_Gargoyles.safetensors')
image = pipeline('`loincloth`, `Gargoyles_comic`').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers