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("masonjames/flux-dev-lora-mj")
prompt = "MasonJames"
image = pipe(prompt).images[0]Model description
I uploaded 16 photos of myself to Replicate.com and created a Flux Lora. This is the result. No one will want this but me and I don't really want it either, but it's an interesating experiment to say the least.
Trigger words
You should use MasonJames to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 3
Model tree for masonjames/flux-dev-lora-mj
Base model
black-forest-labs/FLUX.1-dev