prithivMLmods/Street-Bokeh-Flux-LoRA

Instalación y uso con Diffusers:

pip install -U diffusers transformers accelerate

import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-dev",
    dtype=torch.bfloat16,
    device_map="cuda"
)

pipe.load_lora_weights("prithivMLmods/Street-Bokeh-Flux-LoRA")

prompt = "Street Bokeh, a young woman with long dark hair, wearing a black hooded jacket, stands in front of a backdrop of colorful lights. The backdrop is blurred, creating a stark contrast with the vibrant colors of the lights."
image = pipe(prompt).images[0]

Configuración alternativa indicada en la tarjeta del modelo:

import torch
from pipelines import DiffusionPipeline

base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)

lora_repo = "prithivMLmods/Street-Bokeh-Flux-LoRA"
trigger_word = "Street Bokeh"
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)

Para obtener mejores resultados, incluir "Street Bokeh" al inicio del prompt.