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("Hack337/flux-lora-Komaru")
prompt = "a Komaru cat sitting in a box of corn on top of a couch"
image = pipe(prompt).images[0]Komaru
- Prompt
- a Komaru cat sitting in a box of corn on top of a couch
- Prompt
- a Komaru cat laying on its back on the wooden floor
- Prompt
- a person holding a Komaru cat in their hands
- Prompt
- a Komaru cat sitting atop a cardboard box
- Prompt
- a Komaru cat sitting atop a wooden drawer, with a wall on the right side
- Prompt
- a Komaru cat wearing a pink hat with ears, sitting on a wooden surface with a blurred background
Model description
Komaru, a charming Kincalow cat, is the star of this LoRa. Follow her adventures and cuteness on her human's Instagram: @mugimeshi323
Trigger words
You should use Komaru to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Use it with the 🧨 diffusers library
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('Hack337/flux-lora-Komaru', weight_name='komaru')
image = pipeline('a Komaru cat sitting in a box of corn on top of a couch, with a white cloth draped over it').images[0]
image.save("my_image.png")
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers
- Downloads last month
- 8
Model tree for Hack337/flux-lora-Komaru
Base model
black-forest-labs/FLUX.1-dev