README.md

---
library_name: transformers
license: apache-2.0
datasets:
- Jialuo21/Science-T2I-Trainset
base_model:
- laion/CLIP-ViT-H-14-laion2B-s32B-b79K
---


<img src="teaser.png" align="center">

# SciScore
SciScore is finetuned on the base model [CLIP-H](https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K) using [Science-T2I](https://huggingface.co/datasets/Jialuo21/Science-T2I-Trainset) dataset. It takes an implicit prompt and a generated image as input and outputs a score that represents the scientific alignment between them.


## Resources
- [Website](https://jialuo-li.github.io/Science-T2I-Web/)
- [arXiv: Paper](https://arxiv.org/abs/2504.13129)
- [GitHub: Code](https://github.com/Jialuo-Li/Science-T2I)
- [Huggingface: Science-T2I-S&C Benchmark](https://huggingface.co/collections/Jialuo21/science-t2i-67d3bfe43253da2bc7cfaf06)
- [Huggingface: Science-T2I Trainset](https://huggingface.co/datasets/Jialuo21/Science-T2I-Trainset)

## Feature
<img src="exp.png" align="center">

## Qick Start
```
from transformers import AutoProcessor, AutoModel
from PIL import Image
import torch

device = "cuda"
processor_name_or_path = "Jialuo21/SciScore"
model_pretrained_name_or_path = "Jialuo21/SciScore"

processor = AutoProcessor.from_pretrained(processor_name_or_path)
model = AutoModel.from_pretrained(model_pretrained_name_or_path).eval().to(device)

def calc_probs(prompt, images):
    
    image_inputs = processor(
        images=images,
        padding=True,
        truncation=True,
        max_length=77,
        return_tensors="pt",
    ).to(device)
    
    text_inputs = processor(
        text=prompt,
        padding=True,
        truncation=True,
        max_length=77,
        return_tensors="pt",
    ).to(device)

    with torch.no_grad():
        image_embs = model.get_image_features(**image_inputs)
        image_embs = image_embs / torch.norm(image_embs, dim=-1, keepdim=True)
    
        text_embs = model.get_text_features(**text_inputs)
        text_embs = text_embs / torch.norm(text_embs, dim=-1, keepdim=True)
    
        scores = model.logit_scale.exp() * (text_embs @ image_embs.T)[0]
        probs = torch.softmax(scores, dim=-1)
    return probs.cpu().tolist()

pil_images = [Image.open("./examples/camera_1.png"), Image.open("./examples/camera_2.png")]
prompt = "A camera screen without electricity sits beside the window, realistic."
print(calc_probs(prompt, pil_images))
```

## Citation

```
@misc{li2025sciencet2iaddressingscientificillusions,
  title={Science-T2I: Addressing Scientific Illusions in Image Synthesis}, 
  author={Jialuo Li and Wenhao Chai and Xingyu Fu and Haiyang Xu and Saining Xie},
  year={2025},
  eprint={2504.13129},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2504.13129}, 
}
```