multimodalart's picture
Upload folder using huggingface_hub
040dca5
metadata
license: other
license_name: bespoke-lora-trained-license
license_link: >-
  https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Rent&allowDerivatives=True&allowDifferentLicense=False
tags:
  - text-to-image
  - stable-diffusion
  - lora
  - diffusers
  - template:sd-lora
  - glitch
  - style
  - artstyle
  - corrupted
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: gltch artstyle
widget:
  - text: ' '
    output:
      url: 2462614.jpeg
  - text: Tokyo city skyline sunset vaporwave (gltch artstyle)
    output:
      url: 2460637.jpeg
  - text: dinosaur eating broccoli (gltch artstyle)
    output:
      url: 2460765.jpeg
  - text: ' '
    output:
      url: 2460488.jpeg
  - text: ' '
    output:
      url: 2460489.jpeg
  - text: dinosaur eating broccoli (gltch artstyle)
    output:
      url: 2460766.jpeg
  - text: ' '
    output:
      url: 2460662.jpeg
  - text: ' '
    output:
      url: 2462615.jpeg
  - text: ' '
    output:
      url: 2460254.jpeg
  - text: ' '
    output:
      url: 2460256.jpeg

GLTCH artstyle "corrupt CR2 Canon RAW files" 218MB LoRA

Prompt
Prompt
Tokyo city skyline sunset vaporwave (gltch artstyle)
Prompt
dinosaur eating broccoli (gltch artstyle)
Prompt
Prompt
Prompt
dinosaur eating broccoli (gltch artstyle)
Prompt
Prompt
Prompt
Prompt

Model description

Trained on corrupted CR2 RAW files taken from a Canon 6D with Magic Lantern installed.
I thought the strange colorful banding from these photographs made for an useful LoRA.

☕ Like what I do? ☕
☕ Buy me a coffee or two! ☕

Trigger words

You should use gltch artstyle 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('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('DoctorDiffusion/gltch-artstyle-corrupt-cr2-canon-raw-files-218mb-lora', weight_name='DD-gltch-artstyle-XL-v1.safetensors')
image = pipeline('`gltch artstyle`').images[0]

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