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("AlloReview/flux-lora-undraw")
prompt = "A man writing \"Flux\" on a giant whiteboard in the style of UndrawPurple"
image = pipe(prompt).images[0]undraw
- Prompt
- A man writing "Flux" on a giant whiteboard in the style of UndrawPurple
Model description
An experimental lora fine-tuned of Flux to produce image in the style of unDraw. It was trained using this Replicate, with ~20 images with no caption.
Trigger words
You should use in the style of UndrawPurple 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
- 50
Model tree for AlloReview/flux-lora-undraw
Base model
black-forest-labs/FLUX.1-dev