prithivMLmods/Dark-Thing-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/Dark-Thing-Flux-LoRA")

prompt = "Dark Creature, Captured in a vibrant pink background, a large hamburger is prominently displayed in the center of the frame. The burger is adorned with a variety of seeds, including sesame seeds, and a bun with lettuce and a slice of cheese. Surrounding the burger, a white wolf can be seen facing towards the right. The wolf is facing to the left, with its mouth open, while its head turned towards the left. To the right of the hamburger, two white foxes are facing the same direction, while the foxes facing the right are facing away from the camera. The background is a vibrant shade of pink, with a few birds flying in the background."
image = pipe(prompt).images[0]

Configuración alternativa indicada en la ficha:

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/Dark-Thing-Flux-LoRA"
trigger_word = "Dark Creature"
pipe.load_lora_weights(lora_repo)

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