Hugging Face's logo

Spaces:
devisionx
/
autoannotation
Sleeping

App Files Community
autoannotation
File size: 4,189 Bytes 
cef0ce8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
78b95a9
cef0ce8
 
 
 
78b95a9
cef0ce8
78b95a9
 
b7980cb
 
7cd9ea7
 
 
 
 
 
 
 
 
 
 
b7980cb
 
 
 
 
 
 
 
 
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
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
 
import base64
import io
import cv2
import requests
import json
import gradio as gr
import os
from PIL import Image
import numpy as np
from PIL import ImageOps

# Accessing a specific environment variable
api_key = os.environ.get('devisionx')

# Checking if the environment variable exists
if not api_key:
    print("devisionx environment variable is not set.")
    exit()

# Define a function to call the API and get the results

def base64str_to_PILImage(base64str):
    base64_img_bytes = base64str.encode('utf-8')
    base64bytes = base64.b64decode(base64_img_bytes)
    bytesObj = io.BytesIO(base64bytes)
    return ImageOps.exif_transpose(Image.open(bytesObj))

def get_results(image, prompt):
    threshold = 0.5
    
    # Convert the NumPy array to PIL image
    image = Image.fromarray(image)

    # Convert the image to base64 string
    with io.BytesIO() as output:
        image.save(output, format="JPEG")
        base64str = base64.b64encode(output.getvalue()).decode("utf-8")

    # Prepare the payload (Adjust this part according to the API requirements)
    payload = json.dumps({"base64str": base64str, "classes": prompt})

    # Send the request to the API
    response = requests.put(api_key, data=payload)

    # Parse the JSON response
    data = response.json()
    print(response.status_code)
    print(data)

    # Access the values (Adjust this part according to the API response format)
    output_image_base64 = data['firstName']  # Assuming the API returns the output image as base64
    

    # Convert the output image from base64 to PIL and then to NumPy array
    output_image = base64str_to_PILImage(output_image_base64)
    output_image = np.array(output_image)

    return output_image

    
# Define the input components for Gradio (adding a new input for the prompt)
image_input = gr.inputs.Image()
text_input = gr.inputs.Textbox(label="Prompt")  # New input for the text prompt


# Define the output components for Gradio (including both image and text)
outputs = gr.Image(type="numpy", label="Output Image")

# Define the text description within an HTML <div> element
description_html = """
            <div class="footer">
                <p>Model by <a href="https://deci.ai" style="text-decoration: underline;" target="_blank">tuba.ai</a> - Gradio Demo by 🤗 Hugging Face
                </p>
            </div>
            <div class="acknowledgments">
                    <p><h4>LICENSE</h4>
The model is licensed with a <a href="" style="text-decoration: underline;" target="_blank">CreativeML Open RAIL-M</a> license. The authors claim no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in this license. The license forbids you from sharing any content that violates any laws, produce any harm to a person, disseminate any personal information that would be meant for harm, spread misinformation and target vulnerable groups. For the full list of restrictions please <a href="https://huggingface.co/Deci/DeciDiffusion-v1-0/blob/main/LICENSE-WEIGHTS.md" target="_blank" style="text-decoration: underline;" target="_blank">read the license</a></p>
                    <p><h4>Biases and content acknowledgment</h4>
Despite how impressive being able to turn text into image is, beware to the fact that this model may output content that reinforces or exacerbates societal biases, as well as realistic faces, pornography and violence. The model was trained on the <a href="https://laion.ai/blog/laion-5b/" style="text-decoration: underline;" target="_blank">LAION-5B dataset</a>, which scraped non-curated image-text-pairs from the internet (the exception being the removal of illegal content) and is meant for research purposes. You can read more in the <a href="https://huggingface.co/Deci/DeciDiffusion-v1-0" style="text-decoration: underline;" target="_blank">model card</a></p>
               </div>
        """

# Launch the Gradio interface with the description below it
gr.Interface(
    fn=get_results,
    inputs=[image_input, text_input],
    outputs=outputs,
    description=description_html  # Use the HTML description
).launch(share=False)