You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

By clicking "Agree", you agree to the License Agreement and acknowledge Stability AI's Privacy Policy.

Log in or Sign Up to review the conditions and access this model content.

Japanese Stable CLIP ViT-L/16

Please note: for commercial usage of this model, please see https://stability.ai/license

ๅ•†็”จๅˆฉ็”จใซ้–ขใ™ใ‚‹ๆ—ฅๆœฌ่ชžใงใฎๅ•ใ„ๅˆใ‚ใ›ใฏใ€€[email protected] ใพใงใŠ้ก˜ใ„่‡ดใ—ใพใ™ใ€‚

Model Details

Japanese Stable CLIP is a Japanese CLIP (Contrastive Language-Image Pre-Training) model that enables to map both Japanese texts and images to the same embedding space. This model alone is capable of tasks such as zero-shot image classification and text-to-image retrieval. Furthermore, when combined with other components, it can be used as part of generative models, such as image-to-text and text-to-image generation.

Usage

  1. Install packages
pip install ftfy pillow requests transformers torch sentencepiece protobuf
  1. Run!
from typing import Union, List
import ftfy, html, re, io
import requests
from PIL import Image
import torch
from transformers import AutoModel, AutoTokenizer, AutoImageProcessor, BatchFeature

# taken from https://github.com/mlfoundations/open_clip/blob/main/src/open_clip/tokenizer.py#L65C8-L65C8
def basic_clean(text):
    text = ftfy.fix_text(text)
    text = html.unescape(html.unescape(text))
    return text.strip()

def whitespace_clean(text):
    text = re.sub(r"\s+", " ", text)
    text = text.strip()
    return text

def tokenize(
    tokenizer,
    texts: Union[str, List[str]],
    max_seq_len: int = 77,
):
    """
    This is a function that have the original clip's code has.
    https://github.com/openai/CLIP/blob/main/clip/clip.py#L195
    """
    if isinstance(texts, str):
        texts = [texts]
    texts = [whitespace_clean(basic_clean(text)) for text in texts]

    inputs = tokenizer(
        texts,
        max_length=max_seq_len - 1,
        padding="max_length",
        truncation=True,
        add_special_tokens=False,
    )
    # add bos token at first place
    input_ids = [[tokenizer.bos_token_id] + ids for ids in inputs["input_ids"]]
    attention_mask = [[1] + am for am in inputs["attention_mask"]]
    position_ids = [list(range(0, len(input_ids[0])))] * len(texts)

    return BatchFeature(
        {
            "input_ids": torch.tensor(input_ids, dtype=torch.long),
            "attention_mask": torch.tensor(attention_mask, dtype=torch.long),
            "position_ids": torch.tensor(position_ids, dtype=torch.long),
        }
    )

device = "cuda" if torch.cuda.is_available() else "cpu"
model_path = "stabilityai/japanese-stable-clip-vit-l-16"
model = AutoModel.from_pretrained(model_path, trust_remote_code=True).to(device)
tokenizer = AutoTokenizer.from_pretrained(model_path)
processor = AutoImageProcessor.from_pretrained(model_path)

# Run!
image = Image.open(io.BytesIO(requests.get('https://images.pexels.com/photos/2253275/pexels-photo-2253275.jpeg?auto=compress&cs=tinysrgb&dpr=3&h=750&w=1260').content))
image = processor(images=image, return_tensors="pt").to(device)
text = tokenize(
    tokenizer=tokenizer,
    texts=["็Šฌ", "็Œซ", "่ฑก"],
).to(device)

with torch.no_grad():
    image_features = model.get_image_features(**image)
    text_features = model.get_text_features(**text)
    text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)

print("Label probs:", text_probs) 
# [[1.0, 0.0, 0.0]]

Model Details

Model ImageNet top-1 accuracy*
Japanese Stable CLIP ViT-L/16 62.06
rinna/japanese-cloob-vit-b-16 54.64
laion/CLIP-ViT-H-14-frozen-xlm-roberta-large-laion5B-s13B-b90k 53
rinna/japanese-clip-vit-b-16 50.69

* Computed scores based on https://github.com/rinnakk/japanese-clip.

Training

The model uses a ViT-L/16 Transformer architecture as an image encoder and a 12-layer BERT as a text encoder with the Japanese tokenizer from rinna/japanese-roberta-base. During training, the image encoder was initialized from the AugReg vit-large-patch16-224 model and we applied SigLIP (Sigmoid loss for Language-Image Pre-training).

Training Dataset

The training dataset includes the following public datasets:

Use and Limitations

Intended Use

This model is intended to be used by the open-source community in vision-language applications.

Limitations and bias

The training dataset may have contained offensive or inappropriate content even though we applied data filters. We recommend users exercise reasonable caution when using these models in production systems. Do not use the model for any applications that may cause harm or distress to individuals or groups.

How to cite

@misc{JapaneseStableCLIP, 
    url    = {[https://huggingface.co./stabilityai/japanese-stable-clip-vit-l-16](https://huggingface.co./stabilityai/japanese-stable-clip-vit-l-16)}, 
    title  = {Japanese Stable CLIP ViT-L/16}, 
    author = {Shing, Makoto and Akiba, Takuya}
}

Contact

  • For questions and comments about the model, please join Stable Community Japan.
  • For future announcements / information about Stability AI models, research, and events, please follow https://twitter.com/StabilityAI_JP.
  • For business and partnership inquiries, please contact [email protected]. ใƒ“ใ‚ธใƒใ‚นใ‚„ๅ”ๆฅญใซ้–ขใ™ใ‚‹ใŠๅ•ใ„ๅˆใ‚ใ›ใฏ[email protected]ใซใ”้€ฃ็ตกใใ ใ•ใ„ใ€‚
Downloads last month
368
Safetensors
Model size
414M params
Tensor type
F32
ยท
Inference Examples
Inference API (serverless) does not yet support model repos that contain custom code.

Collection including stabilityai/japanese-stable-clip-vit-l-16