| import gradio as gr |
| import torch |
| from PIL import Image |
| from diffusers import DiffusionPipeline |
| from transformers import pipeline |
|
|
| modeloObtenerTextoImagen = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base") |
| modeloGenerarImagen = DiffusionPipeline.from_pretrained("sd-legacy/stable-diffusion-v1-5", torch_dtype=torch.float32) |
|
|
| def obtenerDescripcion(imagen): |
| resultadoModeloTI = modeloObtenerTextoImagen(Image.fromarray(imagen)) |
| print(f'La frase que se ha obtenido de la imagen es {resultadoModeloTI}') |
| return modeloGenerarImagen(resultadoModeloTI[0]['generated_text']).images[0] |
|
|
| demo = gr.Interface(fn=obtenerDescripcion, inputs="image", outputs="image") |
| demo.launch(share=True) |
