How to use ttsfashion4/thennow with 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("ttsfashion4/thennow") prompt = "Then-and-now: The foreground image is a black and white photo from the 1920s, depicting a marching band parading down a cobblestone street, with a slightly crumpled edge and a faint shadow from being held just above the background. The background is a modern color photo of the same street, now paved and lined with contemporary buildings. The cobblestone street in the foreground aligns perfectly with the current pavement, while the band membersâ position aligns with the modern-day center of the road, creating a sharp boundary that juxtaposes the festive past with todayâs quieter scene.Then-and-now: The foreground image is a black and white photo from the 1920s, depicting a marching band parading down a cobblestone street, with a slightly crumpled edge and a faint shadow from being held just above the background. The background is a modern color photo of the same street, now paved and lined with contemporary buildings. The cobblestone street in the foreground aligns perfectly with the current pavement, while the band membersâ position aligns with the modern-day center of the road, creating a sharp boundary that juxtaposes the festive past with today's quieter scene." image = pipe(prompt).images[0]
