File size: 2,219 Bytes
fe15a96 5fd680d 71f1200 9160ce9 5fd680d 71f1200 5fd680d 71f1200 5fd680d 71f1200 5fd680d 71f1200 5fd680d 325ea2b 5fd680d a7a9bdc 5fd680d 77d1bb4 171063f f0c2761 ef54300 90b9489 77d1bb4 e6d2f53 |
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 |
import gradio as gr
from PIL import Image
import requests
import base64
import io
import os
os.system("pip install openai")
import openai
openai.api_key = ""
openai.api_base = "https://api.deepinfra.com/v1/openai"
def todataimage(file, ext):
buffered = io.BytesIO()
file.save(buffered, format=ext)
return "data:image/png;base64,"+base64.b64encode(buffered.getvalue()).decode("utf-8")
def caption(file, ext):
datimg = todataimage(file, ext)
response = requests.post("https://russellc-comparing-captioning-models.hf.space/run/predict", json={
"data": [
datimg,
]}).json()
print(response)
data = response["data"]
chat_completion = openai.ChatCompletion.create(
model="jondurbin/airoboros-l2-70b-gpt4-1.4.1",
messages=[{"role": "system", "content": "you will be given descriptions of one image from a varity of image captioning models with a varity of quality, what you need to do is combine them into one image caption and make that be your output, no extras words like \"here is your output\", remeber, don't take too much information from low quality, or too little from high. do NOT contain ANY text other than the description"},{"role":"user", "content":"High Quality:\n"+data[1]+"\n"+data[3]+"\nMedium Qualitt:\n"+data[2]+"\nLow Quality\n"+data[0]}],
)
return chat_completion.choices[0].message.content
def image_predict(image):
return caption(image, "png")
examples = [["penguin.png"], ["stop.png"], ["stick.png"]]
title = "Generating Captions For Images Using ImCap v1"
description = """ImCap v1 uses a varity of image caption generators, then plugs it into LLaMA 2 to get a final caption.<br/>
<a href="https://huggingface.co/spaces/SFP/ImCap_v1?duplicate=true"
style="display: inline-block;margin-top: .5em;margin-right: .25em;" target="_blank">
<img style="margin-bottom: 0em;display: inline;margin-top: -.25em;"
src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
if there is a queue (free CPU works fine as it uses apis)."""
iface = gr.Interface(image_predict, inputs=gr.Image(type="pil"), outputs="label", flagging_options=[], title=title, examples=examples, description=description)
iface.launch(show_api=False) |