martintomov/retrofuturism-flux
Viewer • Updated • 25 • 15
How to use un-43/retrofuturism 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("un-43/retrofuturism")
prompt = "photograph, background of Earth from space, red car on the Moon watching Earth, retrofuturism"
image = pipe(prompt).images[0]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("un-43/retrofuturism")
prompt = "photograph, background of Earth from space, red car on the Moon watching Earth, retrofuturism"
image = pipe(prompt).images[0]Trained for 3000 steps on NVIDIA RTX 4090 (24GB VRAM), Learning Rate 1e-4
Link to Retrofuturism V2
.jpg 512x512 images and 25 .txt captionsYou should use retrofuturism to trigger the image generation






Base model
black-forest-labs/FLUX.1-dev