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/virtual-tryon-kontext-lora")
prompt = "wear it"
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]virtual tryon kontext lora
Model description
Trigger words
You should use wear it to trigger the image generation.
📊 Examples
| Input | Output | Input | Output |
|---|---|---|---|
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
⚙️ How to use
- You need a model image and a garments overlay over it
- You can put garments overlay on model photo with this tool I made.
- Put the trigger word
wear itin your prompt. - Adjust LoRA weight (recommended 1.0)
Try it Online / Demo Space
We have built a demo space to try it easily. Try it now: https://huggingface.co/spaces/ovi054/virtual-tryon-flux-kontext.
Try it Locally with Gradio UI
git clone https://huggingface.co/spaces/ovi054/virtual-tryon-flux-kontext
cd ovi054/virtual-tryon-flux-kontext
pip install -r requirements.txt
python app.py
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
- 43
Model tree for ovi054/virtual-tryon-kontext-lora
Base model
black-forest-labs/FLUX.1-Kontext-dev