multimodalart/vintage-ads
Viewer • Updated • 17 • 17 • 7
How to use multimodalart/vintage-ads-flux 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("multimodalart/vintage-ads-flux")
prompt = "A vintage ad of a roomba robot while a person on the couch vntgads, it reads \"I clean, you chill\", \"roomba\" brand on the bottom right"
image = pipe(prompt).images[0]





Model trained on public domain Vintage Ads
You should use a vintage ad of to trigger the image generation.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Training was done using fal.ai/models/fal-ai/flux-lora-general-training.
Base model
black-forest-labs/FLUX.1-dev