ModelPublicadoExterno

BLIP Image To Recipe

import requests from PIL import Image

Fuentehuggingface.co/fatehmujtaba/BLIP-Image-to-recipe/tree/b206555b13f709db7b8fc5d39b0b5432d8df0965

TipoText modelVersiónmodelCcalidad

Fuente del modelo

Tipo: Text model
Tamaño del archivo: 944 MB
Versión: vmodel
Actualizado: 7 oct 2026
Descargas: 5
Fuente: Hugging Face

Descripción de la fuente

BLIP-Image-to-recip

Inference code

import requests from PIL import Image

from transformers import BlipForConditionalGeneration, AutoProcessor

img_url = 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcSQuFg4LTHUattLGPU0kLzYpBGHRtuqgJY8Gho3uZe_cg&s' image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')

model = BlipForConditionalGeneration.from_pretrained("Fatehmujtaba/BLIP-Image-to-recipe").to(device) processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-base")

inputs = processor(images=image, return_tensors="pt").to(device) pixel_values = inputs.pixel_values generated_ids = model.generate(pixel_values=pixel_values, max_length=50) generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]

Fuentes

1 fuente

Hugging FacePrincipalVersión b206555b13f709db7b8fc5d39b0b5432d8df0965

huggingface.co/fatehmujtaba/BLIP-Image-to-recipe/tree/b206555b13f709db7b8fc5d39b0b5432d8df0965

Verificado 7 oct

Artefactos del modelo

1 artefacto

model.safetensors

safetensors · 944 MB · SHA-256 028246ed7d2f…c43c · Hugging Face

Descargar

Extractos de fuentes

3 extractos

Readme30 julhuggingface.co/fatehmujtaba/BLIP-Image-to-recipe

--- library_name: transformers license: apache-2.0 pipeline_tag: image-to-text --- # BLIP-Image-to-recip # Inference code --- import requests from PIL import Image from transformers import BlipForConditionalGeneration, AutoProcessor img_url = 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcSQuFg4LTHUattLGPU0kLzYpBGHRtuqgJY8Gho3uZe_cg&s' image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB') model = BlipForConditionalGeneration.from_pretrained("Fatehmujtaba/BLIP-Image-to-recipe").to(device) processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-base") inputs = processor(images=image, return_tensors="pt").to(device) pixel_values = inputs.pixel_values generated_ids = model.generate(pixel_values=pixel_values, max_length=50) generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0] ---

Note7 octhuggingface.co/fatehmujtaba/BLIP-Image-to-recipe

Source context: 5 downloads · 0 likes · Pipeline image-to-text · Library transformers · Repo fatehmujtaba/BLIP-Image-to-recipe

Note30 julhuggingface.co/fatehmujtaba/BLIP-Image-to-recipe

Source context: 4 downloads · 0 likes · Pipeline image-to-text · Library transformers · Repo fatehmujtaba/BLIP-Image-to-recipe