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("AP123/flux-jigsaw-v1")
prompt = "totk"
image = pipe(prompt).images[0]flux jigsaw v1
Model description
A jigsaw puzzle LoRA for use with Flux [dev]. Invoke the the lora with: "A jigsaw puzzle in the style of totk".
Trigger words
You should use totk to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Trained with AI Toolkit
Training was done using AI-toolkit by Ostris.
- Downloads last month
- 8
Model tree for AP123/flux-jigsaw-v1
Base model
black-forest-labs/FLUX.1-dev