Flux Dev 1 model that creates images with both photographic and illustrative elements. Pretty cool right? You can also run the model on Replicate. Let me know your thoughts and have a wonderful day!
It would help if you used in the style of TOK for better style preservation. It is best to place the trigger words first and describe illustrative elements in your scene like clothing or expressive elements.
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('davisbro/half_illustration', weight_name='flux_train_replicate.safetensors')
image = pipeline('A 50mm bokeh photo of a fashion show in paris, midday sun, surrounded by the colorful friendly rock and roll text "Paris" and other french themed doodles').images[0]