Spaces:
Sleeping
Sleeping
File size: 4,365 Bytes
4a53687 1da073b 4a53687 2e6449d 4a53687 169c40b 4a53687 c0cfa96 3982129 4a53687 c0cfa96 3982129 4a53687 169c40b 844f195 4a53687 0d14460 4a53687 0d14460 4a53687 7b0889b 4a53687 d8ff2c8 0d14460 d8ff2c8 0d14460 d8ff2c8 0d14460 4a53687 9b754f9 7747217 4a53687 0d14460 |
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 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 |
## App.py
import os
import io
# from IPython.display import Image, display, HTML
from PIL import Image
import base64
from dotenv import load_dotenv, find_dotenv
_ = load_dotenv(find_dotenv()) # read local .env file
hf_api_key = os.environ['HF_TOKEN']
#### Helper function
import requests, json
#Here we are going to call multiple endpoints!
def get_completion(inputs, parameters=None, ENDPOINT_URL=""):
headers = {
"Authorization": f"Bearer {hf_api_key}",
"Content-Type": "application/json"
}
data = { "inputs": inputs }
if parameters is not None:
data.update({"parameters": parameters})
response = requests.request("POST",
ENDPOINT_URL,
headers=headers,
data=json.dumps(data))
return json.loads(response.content.decode("utf-8"))
def get_img_completion(inputs, parameters=None, ENDPOINT_URL=""):
headers = {
"Authorization": f"Bearer {hf_api_key}",
"Content-Type": "application/json"
}
data = { "inputs": inputs }
if parameters is not None:
data.update({"parameters": parameters})
response = requests.request("POST",
ENDPOINT_URL,
headers=headers,
data=json.dumps(data))
return response.content
# return json.loads(response.content.decode("utf-8"))
#text-to-image
TTI_ENDPOINT = "https://api-inference.huggingface.co/models/ZB-Tech/Text-to-Image"
# "http://jupyter-api-proxy.internal.dlai/rev-proxy/huggingface/itt"
# os.environ['HF_API_TTI_BASE']
#image-to-text
ITT_ENDPOINT = "https://api-inference.huggingface.co/models/Salesforce/blip-image-captioning-base"
# "http://jupyter-api-proxy.internal.dlai/rev-proxy/huggingface/tti"
# os.environ['HF_API_ITT_BASE']
## Building your game with `gr.Blocks()`
#Bringing the functions from lessons 3 and 4!
def image_to_base64_str(pil_image):
byte_arr = io.BytesIO()
pil_image.save(byte_arr, format='PNG')
byte_arr = byte_arr.getvalue()
return str(base64.b64encode(byte_arr).decode('utf-8'))
def base64_to_pil(img_base64):
base64_decoded = base64.b64decode(img_base64)
byte_stream = io.BytesIO(base64_decoded)
pil_image = Image.open(byte_stream)
return pil_image
def captioner(image):
base64_image = image_to_base64_str(image)
result = get_completion(base64_image, None, ITT_ENDPOINT)
return result[0]['generated_text']
def generate(prompt):
output = get_img_completion(prompt, None, TTI_ENDPOINT)
image = Image.open(io.BytesIO(output))
return image
# result_image = base64_to_pil(output.content)
# return result_image
### First attempt, just captioning
import gradio as gr
with gr.Blocks() as demo:
gr.Markdown("# Describe-and-Generate game 🖍️")
image_upload = gr.Image(label="Your first image",type="pil")
btn_caption = gr.Button("Generate caption")
caption = gr.Textbox(label="Generated caption")
btn_caption.click(fn=captioner, inputs=[image_upload], outputs=[caption])
# gr.close_all()
# demo.launch(share=True)
# ### Let's add generation
with gr.Blocks() as demo:
gr.Markdown("# Describe-and-Generate game 🖍️")
image_upload = gr.Image(label="Your first image",type="pil")
btn_caption = gr.Button("Generate caption")
caption = gr.Textbox(label="Generated caption")
btn_image = gr.Button("Generate image")
image_output = gr.Image(label="Generated Image")
btn_caption.click(fn=captioner, inputs=[image_upload], outputs=[caption])
btn_image.click(fn=generate, inputs=[caption], outputs=[image_output])
# gr.close_all()
demo.launch(share=True)
### Doing it all at once
# def caption_and_generate(image):
# caption = captioner(image)
# image = generate(caption)
# return [caption, image]
# with gr.Blocks() as demo:
# gr.Markdown("# Describe-and-Generate game 🖍️")
# image_upload = gr.Image(label="Your first image",type="pil")
# btn_all = gr.Button("Caption and generate")
# caption = gr.Textbox(label="Generated caption")
# image_output = gr.Image(label="Generated Image")
# btn_all.click(fn=caption_and_generate, inputs=[image_upload], outputs=[caption, image_output])
# gr.close_all()
# demo.launch(share=True)
# gr.close_all() |