Upload 6 files

.gitignore

@@ -0,0 +1,2 @@
+.venv/
+.env

app.py

@@ -0,0 +1,104 @@
+import os
+import io
+from IPython.display import Image
+from PIL import Image
+import base64 
+import gradio as gr 
+
+from dotenv import load_dotenv, find_dotenv
+_ = load_dotenv(find_dotenv()) # read local .env file
+hf_api_key = os.environ['HF_API_KEY']
+
+
+#### 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"))
+
+
+#Here we are going to call multiple endpoints!
+def image_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
+
+
+#text-to-image
+TTI_ENDPOINT ="https://api-inference.huggingface.co/models/cloudqi/cqi_text_to_image_pt_v0"
+#image-to-text
+ITT_ENDPOINT =  "https://api-inference.huggingface.co/models/Salesforce/blip-image-captioning-base"
+
+
+#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 = image_completion(prompt, None, TTI_ENDPOINT)
+    result_image =  Image.open(io.BytesIO(output))
+    print(result_image)
+    return result_image
+
+
+def caption_and_generate(image):
+    caption = captioner(image)
+    image = generate(caption)
+    return [caption, image]
+
+def loadGUI():
+    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)
+
+     
+def main():
+     loadGUI()
+     
+     
+if __name__ == "__main__":
+     main()
+          

requirements.txt

@@ -0,0 +1,76 @@
+accelerate==0.25.0
+aiofiles==23.2.1
+altair==5.2.0
+annotated-types==0.6.0
+anyio==3.7.1
+attrs==23.1.0
+certifi==2023.11.17
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+contourpy==1.2.0
+cycler==0.12.1
+fastapi==0.104.1
+ffmpy==0.3.1
+filelock==3.13.1
+fonttools==4.46.0
+fsspec==2023.12.1
+gradio==4.8.0
+gradio_client==0.7.1
+h11==0.14.0
+httpcore==1.0.2
+httpx==0.25.2
+huggingface-hub==0.19.4
+idna==3.6
+importlib-resources==6.1.1
+Jinja2==3.1.2
+jsonschema==4.20.0
+jsonschema-specifications==2023.11.2
+kiwisolver==1.4.5
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+matplotlib==3.8.2
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.2.1
+numpy==1.26.2
+orjson==3.9.10
+packaging==23.2
+pandas==2.1.4
+Pillow==10.1.0
+psutil==5.9.6
+pydantic==2.5.2
+pydantic_core==2.14.5
+pydub==0.25.1
+Pygments==2.17.2
+pyparsing==3.1.1
+python-dateutil==2.8.2
+python-dotenv==1.0.0
+python-multipart==0.0.6
+pytz==2023.3.post1
+PyYAML==6.0.1
+referencing==0.32.0
+regex==2023.10.3
+requests==2.31.0
+rich==13.7.0
+rpds-py==0.13.2
+safetensors==0.4.1
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.0
+starlette==0.27.0
+sympy==1.12
+tokenizers==0.15.0
+tomlkit==0.12.0
+toolz==0.12.0
+torch==2.1.1
+tqdm==4.66.1
+transformers==4.35.2
+typer==0.9.0
+typing_extensions==4.8.0
+tzdata==2023.3
+urllib3==2.1.0
+uvicorn==0.24.0.post1
+websockets==11.0.3
+text-generation==0.6.1