Upload folder using huggingface_hub

.gitignore

@@ -0,0 +1,13 @@
+.vercel
+*.log
+*.pyc
+__pycache__
+
+# Environments 
+.env 
+.venv 
+env/ 
+venv/ 
+ENV/ 
+env.bak/ 
+venv.bak/ 

README.md

@@ -1,12 +1,6 @@
 ---
-title: Generate Renders
-emoji: 🐠
-colorFrom: purple
-colorTo: purple
+title: generate_renders
+app_file: index.py
 sdk: gradio
-sdk_version: 4.37.1
-app_file: app.py
-pinned: false
+sdk_version: 4.36.1
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

index.py

@@ -0,0 +1,167 @@
+import os
+import base64
+import numpy as np
+from PIL import Image
+import io
+import requests
+
+import replicate
+from flask import Flask, request
+import gradio as gr
+
+import openai
+from openai import OpenAI
+
+from dotenv import load_dotenv, find_dotenv
+
+import json
+
+# Locate the .env file
+dotenv_path = find_dotenv()
+
+load_dotenv(dotenv_path)
+
+OPENAI_API_KEY = os.getenv('OPENAI_API_KEY')
+REPLICATE_API_TOKEN = os.getenv('REPLICATE_API_TOKEN')
+
+client = OpenAI()
+
+def main(img):
+    mask = img['layers'][0]
+
+    base_image = Image.fromarray(img['background'].astype('uint8'))
+    img_base_64 = img_to_base64(base_image)
+
+    if is_transparent(mask) == True:
+        mask_base_64 = None
+    else:
+        mask_img = create_mask_image(mask)
+        mask_base_64 = img_to_base64(mask_img)
+
+    prompt = call_openai(img_base_64)
+
+    output_urls = generate_image(prompt, img_base_64, mask_base_64)
+
+    output_images = [download_image(url) for url in output_urls[3:]]  # Start from the 4th image
+
+    return output_images
+
+def generate_image(prompt, img, mask):
+    input_data = {
+        "image": img,
+        "prompt": "highly realistic photograpy " + prompt + ", expensive",
+        "refine": "no_refiner",
+        "scheduler": "K_EULER",
+        "lora_scale": 0.8,
+        "num_outputs": 4,
+        "controlnet_1": "edge_canny",
+        "controlnet_2": "depth_midas",
+        "controlnet_3": "lineart",
+        "guidance_scale": 7.5,
+        "apply_watermark": False,
+        "negative_prompt":"worst quality, low quality, illustration, 2d, painting, cartoons, sketch",
+        "prompt_strength": 0.75,
+        "sizing_strategy": "controlnet_1_image",
+        "controlnet_1_end": 1,
+        "controlnet_2_end": 1,
+        "controlnet_3_end": 1,
+        "controlnet_1_image": img,
+        "controlnet_1_start": 0,
+        "controlnet_2_image": img,
+        "controlnet_2_start": 0,
+        "controlnet_3_image": img,
+        "controlnet_3_start": 0,
+        "num_inference_steps": 30,
+        "controlnet_1_conditioning_scale": 0.8,
+        "controlnet_2_conditioning_scale": 0.8,
+        "controlnet_3_conditioning_scale": 0.75
+    }
+
+    if mask is not None:
+        input_data["mask"] = mask
+    else:
+        input_data["prompt_strength"] = .6
+
+    output = replicate.run(
+        "fofr/realvisxl-v3-multi-controlnet-lora:90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daade",
+        input=input_data
+    )
+
+    return output
+
+def download_image(url):
+    response = requests.get(url)
+    img = Image.open(io.BytesIO(response.content))
+    return img
+
+def create_mask_image(mask_array):
+    # Convert the mask to a numpy array if it's not already
+    if not isinstance(mask_array, np.ndarray):
+        mask_array = np.array(mask_array)
+    
+    # Create a new array with the same shape as the mask, but only for RGB channels
+    processed_mask = np.zeros((mask_array.shape[0], mask_array.shape[1], 3), dtype=np.uint8)
+    
+    # Set transparent parts (alpha=0) to black (0, 0, 0)
+    transparent_mask = mask_array[:, :, 3] == 0
+    processed_mask[transparent_mask] = [0, 0, 0]
+    
+    # Set black parts (RGB=0, 0, 0 and alpha=255) to white (255, 255, 255)
+    black_mask = (mask_array[:, :, :3] == [0, 0, 0]).all(axis=2) & (mask_array[:, :, 3] == 255)
+    processed_mask[black_mask] = [255, 255, 255]
+    
+    return Image.fromarray(processed_mask)
+
+def is_transparent(mask_array):
+    return np.all(mask_array[:, :, 3] == 0)
+
+def img_to_base64(img):
+    # Extract the format of the image (e.g., JPEG, PNG)
+    img_format = img.format if img.format else "PNG"
+    
+    # Convert the image to bytes
+    buffered = io.BytesIO()
+    img.save(buffered, format=img_format)
+    img_base_64 = base64.b64encode(buffered.getvalue()).decode('utf-8')
+    return f"data:image/{img_format.lower()};base64," + img_base_64
+
+def call_openai(image_data):
+    try:
+        response = client.chat.completions.create(
+            model="gpt-4o",
+            messages=[
+                {
+                    "role": "user",
+                    "content": [
+                        {"type": "text", "text": "Please describe this image in one sentence, with a focus on the material and specific color (like pantone level specificity) and details of the main object in the scene. Mention the type of lighting as well."},
+                        {
+                            "type": "image_url",
+                            "image_url": {
+                                "url": image_data,
+                            },
+                        },
+                    ],
+                }
+            ],
+            max_tokens=300,
+        )
+        return response.choices[0].message.content
+    except openai.BadRequestError as e:
+        print(e)
+        print("e type")
+        print(type(e))
+        raise gr.Error(f"You uploaded an unsupported image. Please make sure your image is below 20 MB in size and is of one the following formats: ['png', 'jpeg', 'gif', 'webp']")
+    except Exception as e:
+        raise gr.Error("Unknown Error")
+
+# Define the brush with only black color
+black_brush = gr.Brush(colors=["#000000"], default_color="#000000", color_mode="fixed")
+
+# Using the ImageEditor component to enable drawing on the image with limited colors
+demo = gr.Interface(
+    fn=main,
+    inputs=gr.ImageEditor(brush=black_brush),
+    outputs=[gr.Image(type="pil"), gr.Image(type="pil"), gr.Image(type="pil"), gr.Image(type="pil")]
+)
+
+demo.launch(share=False)

requirements.txt

@@ -0,0 +1,3 @@
+replicate
+gradio
+openai