Pai Bloom 1b1 Text2prompt Sd

🚀 BeautifulPrompt

We've open-sourced an automatic Prompt generation model. You can input an extremely simple Prompt and get an optimized one by the language model to easily generate high - quality images.

🚀 Quick Start

We release an automatic Prompt generation model, you can directly enter an extremely simple Prompt and get a Prompt optimized by the language model to help you generate more beautiful images simply.

• Github: EasyNLP

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained('alibaba-pai/pai-bloom-1b1-text2prompt-sd')
model = AutoModelForCausalLM.from_pretrained('alibaba-pai/pai-bloom-1b1-text2prompt-sd').eval().cuda()

raw_prompt = '1 girl'
input = f'Instruction: Give a simple description of the image to generate a drawing prompt.\nInput: {raw_prompt}\nOutput:'
input_ids = tokenizer.encode(input, return_tensors='pt').cuda()

outputs = model.generate(
    input_ids,
    max_length=384,
    do_sample=True,
    temperature=1.0,
    top_k=50,
    top_p=0.95,
    repetition_penalty=1.2,
    num_return_sequences=5)

prompts = tokenizer.batch_decode(outputs[:, input_ids.size(1):], skip_special_tokens=True)
prompts = [p.strip() for p in prompts]
print(prompts)

📚 Documentation

Gallery

Original	BeautifulPrompt
prompt: taylor swift, country, golden, fearless,wavehair	prompt: portrait of taylor swift as a beautiful woman, long hair, country, golden ratio, intricate, symmetrical, cinematic lighting, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration

Original	BeautifulPrompt
prompt: A majestic sailing ship	prompt: a massive sailing ship, epic, cinematic, artstation, greg rutkowski, james gurney, sparth

Notice for Use

⚠️ Important Note

If you want to use this model, please read this document carefully and abide by the terms.

Paper Citation

If you find the model useful, please consider cite the paper:

@inproceedings{emnlp2023a,
  author    = {Tingfeng Cao and
            Chengyu Wang and
            Bingyan Liu and
            Ziheng Wu and
            Jinhui Zhu and
            Jun Huang},
  title     = {BeautifulPrompt: Towards Automatic Prompt Engineering for Text-to-Image Synthesis},
  booktitle = {Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track},
  pages     = {1--11},
  year      = {2023}
}

📄 License

This project is licensed under the Apache-2.0 license.