from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-schnell', torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('huggingface-meta/concorde', weight_name='concorde')
image = pipeline('Nikon Photography of a silver chrome concorde flying with the orange moon in the background, night shot, clouds, 90s picture').images[0]
image.save("my_image.png")

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers

WIP

An interface that let people use this HuggingFace space to collaboratively generate images of the Concorde, and curate the best images with an external model.

Credit

Thanks to the AI Toolkit by Ostris for help with training.