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("lucataco/flux-queso")
prompt = "a portrait photo of TOK"
image = pipe(prompt).images[0]Flux Mona Lisa
- Prompt
- a portrait photo of TOK
- Prompt
- a portrait photo of TOK
Trained on Replicate using:
https://replicate.com/ostris/flux-dev-lora-trainer/train
Trigger words
You should use TOK to trigger the image generation.
Training Details
26 images of Queso (the dog) LoRA trained for 500 steps
prompt: "a photo of TOK"
- Downloads last month
- 15
Model tree for lucataco/flux-queso
Base model
black-forest-labs/FLUX.1-dev