File size: 1,205 Bytes
66ab5ba a7aae14 66ab5ba a7aae14 66ab5ba a7aae14 655ad30 66ab5ba 63d7e75 655ad30 c7ad52e a7aae14 adffcb2 655ad30 f81830f 655ad30 63d7e75 adffcb2 c7ad52e 66ab5ba 63d7e75 0206a66 63d7e75 1ccbcc4 63d7e75 66ab5ba |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 |
import base64
import os
from io import BytesIO
import gradio as gr
from huggingface_hub import InferenceClient
PROMPT = os.environ.get("PROMPT", "Describe this image.")
client = InferenceClient(model="https://text.pollinations.ai/openai")
def image_to_base64(image):
buf = BytesIO()
image.save(buf, "JPEG")
buf.seek(0)
return base64.b64encode(buf.getvalue()).decode("utf-8")
def caption(image, prompt):
image = image_to_base64(image)
return client.chat.completions.create(
model="openai-large",
messages=[
{
"role": "user",
"content": [
{
"type": "image_url",
"image_url": {"url": f"data:image/jpeg;base64,{image}"}
},
{"type": "text", "text": prompt}
]
}
],
max_tokens=1024
).choices[0].message.content
gr.Interface(
caption,
inputs=[
gr.Image(type="pil", label="Image"),
gr.TextArea(label="Prompt", value=PROMPT)
],
outputs=gr.Textbox(label="Caption", show_copy_button=True),
title="Image Captioning"
).launch(debug=True) |