ModelListadosExterno

Blip Flickr8k Caption

Fine-tuned BLIP image captioning model trained on Flickr8k.

Fontehuggingface.co/muhammedaydiiinnn/blip-flickr8k-caption/tree/e59afdc652d5e24385ea8b3101e2779090f97539

TipoText modelVersãomodelCnota

Fonte do modelo

Tipo: Text model
Tamanho do arquivo: 944 MB
Versão: vmodel
Atualizado: 8 de mar. de 2026
Downloads: 3
Fonte: Hugging Face

Descrição da fonte

BLIP Flickr8k Caption Model

Fine-tuned BLIP image captioning model trained on Flickr8k.

Base model

Salesforce/blip-image-captioning-base

Usage

from transformers import BlipProcessor, BlipForConditionalGeneration
from PIL import Image
import torch

model_id = "muhammedaydiiinnn/blip-flickr8k-caption"

processor = BlipProcessor.from_pretrained(model_id)
model = BlipForConditionalGeneration.from_pretrained(model_id)

image = Image.open("test.jpg").convert("RGB")
inputs = processor(images=image, return_tensors="pt")

with torch.inference_mode():
    output = model.generate(**inputs, max_new_tokens=30)

caption = processor.decode(output[0], skip_special_tokens=True)
print(caption)

Fontes

1 fonte

Hugging FacePrimárioVersão e59afdc652d5e24385ea8b3101e2779090f97539

huggingface.co/muhammedaydiiinnn/blip-flickr8k-caption/tree/e59afdc652d5e24385ea8b3101e2779090f97539

Verificado 3 de set.

Artefatos de modelo

1 artefato

model.safetensors

safetensors · 944 MB · SHA-256 6e023c44a52a…1015 · Hugging Face

Baixar

Trechos de fonte

2 trechos

Readme3 de set.huggingface.co/muhammedaydiiinnn/blip-flickr8k-caption

--- language: - en library_name: transformers pipeline_tag: image-to-text tags: - image-captioning - blip - vision-language license: mit --- # BLIP Flickr8k Caption Model Fine-tuned BLIP image captioning model trained on Flickr8k. ## Base model Salesforce/blip-image-captioning-base ## Usage ```python from transformers import BlipProcessor, BlipForConditionalGeneration from PIL import Image import torch model_id = "muhammedaydiiinnn/blip-flickr8k-caption" processor = BlipProcessor.from_pretrained(model_id) model = BlipForConditionalGeneration.from_pretrained(model_id) image = Image.open("test.jpg").convert("RGB") inputs = processor(images=image, return_tensors="pt") with torch.inference_mode(): output = model.generate(**inputs, max_new_tokens=30) caption = processor.decode(output[0], skip_special_tokens=True) print(caption)