Trained on a wide variety of experimental portraits, from digitally manipulated collages to vortographs of Alvin Langdon Coburn. This LoRA is a bit wild, and not the easiest to control – but I hope you can embrace the randomness in the spirit of experimentation.

Captions used in training (can be used as triggers):
Experimental portrait photography …
… spliced and rearranged
… melted
… multiplied
… crumpled

Add: color if you want to avoid black-and-white photos
Guidance: 2.5
Steps: 20-30

Trigger words

You should use Experimental portrait photography, spliced and rearranged, multiplied, melted to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('WizWhite/wizard-s-experimental-photography-lab', weight_name='Wiz-Experimental_Portrait_Photography.safetensors')
image = pipeline('Experimental portrait color photography spliced and rearranged in a Amorphous pattern, Berber sunshine
').images[0]

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