import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("lstep1/reglisse-sheltie-sheepdog")
prompt = "-"
image = pipe(prompt).images[0]reglisse-sheltie-sheepdog
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
Model description
Lora for Shetland Sheepdogs, also know as Shelties dogs. I couldn't find any model/checkpoint/lora that displays correctly a sheltie (especially the ears and the long nose). So I took pictures of my dog Reglisse (a black and white 4 years old sheltie).
The result is really nice, and by specifying fur color, you can generate other than B&W sheltie with really good results.
Here is the real one:
Trigger words
You should use R3gliss3D0g 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
- 4
Model tree for lstep1/reglisse-sheltie-sheepdog
Base model
black-forest-labs/FLUX.1-dev