ly-corporation/favnavi-vision-ecommerce-v1-base

import torch
from transformers import AutoModel, AutoImageProcessor
from transformers.image_utils import load_image

# Load the model and processor
model_name = "ly-corporation/favnavi-vision-ecommerce-v1-base"

model = AutoModel.from_pretrained(model_name, trust_remote_code=True).eval()
processor = AutoImageProcessor.from_pretrained(model_name)

# Load the image
image = load_image("https://huggingface.co/datasets/merve/coco/resolve/main/val2017/000000000285.jpg")
inputs = processor(images=[image], return_tensors="pt").to(model.device)

# Run inference
with torch.no_grad():
    image_embeddings = model.get_image_features(**inputs)

print(image_embeddings.shape)

from transformers import pipeline
from transformers.image_utils import load_image

pipe = pipeline(
    task="image-feature-extraction",
    model="ly-corporation/favnavi-vision-ecommerce-v1-base",
    trust_remote_code=True,
)

image = load_image("https://huggingface.co/datasets/merve/coco/resolve/main/val2017/000000000285.jpg")
embedding = pipe(image, return_tensors=True)
print(embedding.shape)

@misc{favnavi-vision-ecommerce-v1,
  title = {Favnavi Vision E-commerce V1: A Visual Feature Model for Product Retrieval in the E-commerce Domain},
  author = {Nishimura, Shuhei and Doi, Kenji and Yamashita, Fumiya and Yonebayashi, Dai and Iwasaki, Masajiro},
  year = {2026},
  howpublished = {\url{https://huggingface.co/ly-corporation/favnavi-vision-ecommerce-v1-base}}
}