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
  - style
  - cartoon
  - once upon a time
  - flux style
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: ouat cartoon
widget:
  - text: 'Girl with a pearl earring ouat cartoon '
    output:
      url: 58389185.jpeg
  - text: American gothic by grant wood ouat cartoon
    output:
      url: 58389746.jpeg
  - text: Dr. who next to their TARDIS ouat cartoon
    output:
      url: 58389952.jpeg
  - text: >-
      woman with red hair, playing chess at the park, bomb going off in the
      background ouat cartoon 
    output:
      url: 58390257.jpeg
  - text: 'A socially awkward potato ouat cartoon '
    output:
      url: 58390425.jpeg
  - text: Wonderwoman  eating a small bug
    output:
      url: images/example_18m7ozy6e.png
  - text: Wonderwoman eating a small bug ouat cartoon
    output:
      url: images/example_azh7t9h5r.png
datasets:
  - Norod78/OnceUponATime-florence2-captions

Once upon a time (cartoon) style [FLUX]

Prompt
Girl with a pearl earring ouat cartoon

Prompt
American gothic by grant wood ouat cartoon

Prompt
Dr. who next to their TARDIS ouat cartoon

Prompt
woman with red hair, playing chess at the park, bomb going off in the background ouat cartoon

Prompt
A socially awkward potato ouat cartoon

Prompt
Wonderwoman eating a small bug ouat cartoon

(CivitAI)

Model description

Once Upon a Time... ("Il était une fois...") is a French educational animation franchise.

Use ouat cartoon in your prompts

Fine tuned with Astria AI

A LoRA scale weight of 0.7-1.0 seems to be well

I've made the Florence-2 captioned Dataset availble on Huggingface

Trigger words

You should use ouat cartoon 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

device = "cuda" if torch.cuda.is_available() else "cpu"

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('Norod78/once-upon-a-time-cartoon-style-flux', weight_name='ouat_cartoon-OnceUponATimeV3-Flux-2142990.safetensors')
image = pipeline('A socially awkward potato ouat cartoon ').images[0]

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