metadata

license: other
license_name: bespoke-lora-trained-license
license_link: >-
  https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Image&allowDerivatives=True&allowDifferentLicense=False
tags:
  - text-to-image
  - stable-diffusion
  - lora
  - diffusers
  - template:sd-lora
  - migrated
  - vintage
  - style
  - vintage style
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Vintage cover
widget:
  - text: ' '
    output:
      url: 25088592.jpeg
  - text: ' '
    output:
      url: 25088594.jpeg
  - text: ' '
    output:
      url: 25088589.jpeg
  - text: ' '
    output:
      url: 25088588.jpeg
  - text: ' '
    output:
      url: 25088593.jpeg
  - text: ' '
    output:
      url: 25088590.jpeg
  - text: ' '
    output:
      url: 25088591.jpeg

Vintage Cover [FLUX]

Prompt
A Vintage cover of a socially awkward potato

Prompt
A Vintage cover featuring Cthulhu rising from the sea in a great storm

Prompt
A Vintage magazine cover of Rick and Morty

Prompt
A Vintage cover featuring Gal Gadot as wonderwoman

Prompt
Portrait of a potato vintage cover

Prompt
Portrait of a vintage cover featuring Snoop Dogg as an alien from another planet

(CivitAI)

Model description

An attempt to train a "Vintage cover" style Flux LoRA (I think I did a better job with the SDXL version)

Use 'Vintage cover' in your prompts

Trigger words

You should use Vintage cover 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('Norod78/vintage-cover-flux', weight_name='b0f2d15fd0d2413bbd1aa12b1dbb4b69_lora.safetensors')
image = pipeline('`Vintage cover`').images[0]

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