metadata
license: mit
language:
- en
pipeline_tag: image-to-text
widget:
- src: https://www.xtrafondos.com/wallpapers/perro-en-el-pasto-5797.jpg
example_title: Dog
- src: https://static.flickr.com/1126/5157409353_805483d0e4.jpg
example_title: Water
Description
It is a ViT model that has been fine-tuned on a Stable Diffusion 2.0 image dataset and applied LORA.
It produces optimal results in a reasonable time. Moreover, its implementation with Pytorch is straightforward.
- Reference: https://huggingface.co/blog/lora
Usage
# Libraries
from transformers import ViTFeatureExtractor, AutoTokenizer, VisionEncoderDecoderModel
# Model
model_id = "nttdataspain/vit-gpt2-stablediffusion2-lora"
model = VisionEncoderDecoderModel.from_pretrained(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id)
feature_extractor = ViTFeatureExtractor.from_pretrained(model_id)
# Predict function
def predict_prompts(list_images, max_length=16):
model.eval()
pixel_values = feature_extractor(images=list_images, return_tensors="pt").pixel_values
with torch.no_grad():
output_ids = model.generate(pixel_values, max_length=max_length, num_beams=4, return_dict_in_generate=True).sequences
preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
preds = [pred.strip() for pred in preds]
return preds
# Get an image and predict
img = Image.open(image_path).convert('RGB')
pred_prompts = predict_prompts([img], max_length=16)