---
language:
- en
pipeline_tag: text2text-generation
inference: false
---
# ViPE-S-CTX7

<!-- Provide a quick summary of what the model is/does. -->

ViPE: Visualize Pretty-much Everything, is the first automated model for translating any arbitrary piece of text into a visualizable prompt. It helps any text-to-image model in figurative or non-lexical language visualizations.

### Model Description

<!-- Provide a longer summary of what this model is. -->

- **Developed by:** [Computer Graphics Group, University of Tuebingen](https://uni-tuebingen.de/fakultaeten/mathematisch-naturwissenschaftliche-fakultaet/fachbereiche/informatik/lehrstuehle/computergrafik/lehrstuhl/)
- **Model type:** Auto-Regressive
- **Language:** English
- **License:** [MIT License for Non-Commercial Use](https://github.com/Hazel1994/ViPE/blob/main/LICENSE)
- **Based on:** [GPT2-Small](https://huggingface.co/gpt2)
- **Versions:** [ViPE-M-CTX7](https://huggingface.co/fittar/ViPE-M-CTX7) (355M parameters) and [ViPE-S-CTX7](https://huggingface.co/fittar/ViPE-S-CTX7) (117M parameters)


### Model Sources

<!-- Provide the basic links for the model. -->

- **Repository:** [Github](https://github.com/Hazel1994/ViPE)
- **Paper:** [EMNLP2023](https://2023.emnlp.org/program/)

### Down Stream Applications
ViPE provides a robust backbone for many practical applications such as music video generation and creative writing.
- #### Music Video Genrations
  - **Repository:** [Github](https://github.com/Hazel1994/ViPE)
  - **Demo:** [ViPE Videos](youtube link)
- #### Creative Writing
  - **Demo:** [Hugging Face Playground](https://huggingface.co/spaces/fittar/ViPE)


### Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

You can directly use the model to generate detailed prompts for any arbitrary text.


```python
from transformers import GPT2LMHeadModel, GPT2Tokenizer


def generate(text, model, tokenizer,device,do_sample,top_k=100, epsilon_cutoff=.00005, temperature=1):
    #mark the text with special tokens
    text=[tokenizer.eos_token +  i + tokenizer.eos_token for i in text]
    batch=tokenizer(text, padding=True, return_tensors="pt")

    input_ids = batch["input_ids"].to(device)
    attention_mask = batch["attention_mask"].to(device)

    #how many new tokens to generate at max
    max_prompt_length=50

    generated_ids = model.generate(input_ids=input_ids,attention_mask=attention_mask, max_new_tokens=max_prompt_length, do_sample=do_sample,top_k=top_k, epsilon_cutoff=epsilon_cutoff, temperature=temperature)
    #return only the generated prompts
    pred_caps = tokenizer.batch_decode(generated_ids[:, -(generated_ids.shape[1] - input_ids.shape[1]):], skip_special_tokens=True)

    return pred_caps

device='cpu'
model = GPT2LMHeadModel.from_pretrained('fittar/ViPE-S-CTX7')
model.to(device)

#ViPE-M's tokenizer is identical to that of GPT2-Small
tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
tokenizer.pad_token = tokenizer.eos_token

# A list of abstract/figurative or any arbitrary combinations of keywords
texts=['lalala', 'I wanna start learning', 'free your mind; you will see the other side of life', 'brave; fantasy']

prompts=generate(texts,model,tokenizer,do_sample=True,device=device)
for t,p in zip(texts,prompts):
    print('{} --> {}'.format(t,p))

lalala -->  A group of dancers performing an extravagant traditional dance, lalala in Spanish
I wanna start learning -->  A student intently sitting at a desk, surrounded by books and notes
free your mind; you will see the other side of life -->  A view of the night sky, stars and planets shining bright, while a woman in a field of flowers looks up in awe
brave; fantasy -->  A knight in shining armor riding a gallant horse through a sunlit valley

```


### Recommendations

You can use either a comma or a semicolon to combine multiple keywords. for example ['dark, fantasy, brave'] or  ['This is gonna be the best day of my life; do you agree?'].
However, a semicolon draws a stronger boundary between the keywords and encourages the model to transfer the last keyword in a given context (previous keywords).


## Training Details

### Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

[More Information Needed]

### Training Procedure 

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->


## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->


## Citation

If you find ViPE useful, please cite our paper.

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->


## Model Card Contact

[Hassan Shahmohammadi](https://fittar.me/)