import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-Kontext-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("ovi054/extract-clothes-kontext-dev-lora")
prompt = "extract only the clothes over a plain background, product photography style"
input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
image = pipe(image=input_image, prompt=prompt).images[0]extract clothes kontext dev lora
Model description
Trigger words
You should use extract only the clothes over a plain background, product photography style to trigger the image generation.
It is recommened to use specific clothing name, for eg. shirt, pant, dress etc for better results. Example prompt is: extract only the shirt over a plain background, product photography style
📊 Examples
| Input | Output |
|---|---|
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Training at fal.ai
Training was done using fal.ai/models/fal-ai/flux-kontext-trainer.
- Downloads last month
- 130
Model tree for ovi054/extract-clothes-kontext-dev-lora
Base model
black-forest-labs/FLUX.1-Kontext-dev