Brainblip

🚀 BrainBLIP

BrainBLIP is a model fine - tuned to generate more natural captions for text - to - image datasets, emphasizing natural language and adding minimal context tags.

🚀 Quick Start

⚠️ Important Note

This model is not ready for production use and is in preliminary stages of training. Use at your own risks

💻 Usage Examples

Basic Usage

from transformers import AutoProcessor, BlipForConditionalGeneration
from PIL import Image

processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("braintacles/brainblip").to("cuda")

image_path_or_url = r"https://imagePath_or_url.jpg"
raw_image = Image.open(requests.get(image_path_or_url, stream=True).raw) if image_path_or_url.startswith("http") else Image.open(image_path_or_url)

inputs = processor(raw_image, return_tensors="pt").to("cuda")
out = model.generate(**inputs, min_length=40, max_new_tokens=75, num_beams=5, repetition_penalty=1.40)
caption = processor.decode(out[0], skip_special_tokens=True)
print(caption)

🔧 Technical Details

Training Data

All captions for this data have been written by myself by hand with some occasional help from GPT4. Very special thanks to the following people who also have contributed a huge amount of time hand captioning some data:

• Temporarium
• HailoKnight

📄 License

The model uses the BSD 3 - Clause license.