Upload folder using huggingface_hub

api/index.py

@@ -25,6 +25,7 @@ client = OpenAI()
 
 def call_openai(pil_image):
     # Save the PIL image to a bytes buffer
+    
     buffered = io.BytesIO()
     pil_image.save(buffered, format="JPEG")
     
@@ -62,7 +63,8 @@ def call_openai(pil_image):
         raise gr.Error("Unknown Error")
 
 def image_classifier(moodboard, starter_image, image_strength, prompt):
-
+    raise gr.Error(header)
+    
     if moodboard is not None and starter_image is not None:
 
         # Convert the numpy array to a PIL image
@@ -84,10 +86,10 @@ def image_classifier(moodboard, starter_image, image_strength, prompt):
             # Resize the image
             starter_image_pil = starter_image_pil.resize((new_width, new_height), Image.LANCZOS)
         
-        openai_response = call_openai(pil_image)
-        openai_response = openai_response.replace('moodboard', '')
-        openai_response = openai_response.replace('share', '')
-        openai_response = openai_response.replace('unified', '')
+        #openai_response = call_openai(pil_image)
+        #openai_response = openai_response.replace('moodboard', '')
+        #openai_response = openai_response.replace('share', '')
+        #openai_response = openai_response.replace('unified', '')
 
         # Save the starter image to a bytes buffer
         buffered = io.BytesIO()
@@ -99,35 +101,35 @@ def image_classifier(moodboard, starter_image, image_strength, prompt):
         raise gr.Error(f"Please upload a moodboard to control image generation style")
         
     # Call Stable Diffusion API with the response from OpenAI
-    input = {
-        "width": 768,
-        "height": 768,
-        "prompt": "high quality render of " + prompt + ", " + openai_response[12:],
-        "negative_prompt": "worst quality, low quality, illustration, 2d, painting, cartoons, sketch",
-        "refine": "expert_ensemble_refiner",
-        "image": "data:image/jpeg;base64," + starter_image_base64, 
-        "apply_watermark": False,
-        "num_inference_steps": 25,
-        "prompt_strength": 1-image_strength,
-        "num_outputs": 3
-    }
+    # input = {
+    #     "width": 768,
+    #     "height": 768,
+    #     "prompt": "high quality render of " + prompt + ", " + openai_response[12:],
+    #     "negative_prompt": "worst quality, low quality, illustration, 2d, painting, cartoons, sketch",
+    #     "refine": "expert_ensemble_refiner",
+    #     "image": "data:image/jpeg;base64," + starter_image_base64, 
+    #     "apply_watermark": False,
+    #     "num_inference_steps": 25,
+    #     "prompt_strength": 1-image_strength,
+    #     "num_outputs": 3
+    # }
     
-    output = replicate.run(
-        "stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
-        input=input
-    )
+    # output = replicate.run(
+    #     "stability-ai/sdxl:7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
+    #     input=input
+    # )
     
-    images = []
-    for i in range(min(len(output), 3)):
-        image_url = output[i]
-        response = requests.get(image_url)
-        images.append(Image.open(io.BytesIO(response.content)))
+    # images = []
+    # for i in range(min(len(output), 3)):
+    #     image_url = output[i]
+    #     response = requests.get(image_url)
+    #     images.append(Image.open(io.BytesIO(response.content)))
     
-    # Add empty images if fewer than 3 were returned
-    while len(images) < 3:
-        images.append(Image.new('RGB', (768, 768), 'gray'))
+    # # Add empty images if fewer than 3 were returned
+    # while len(images) < 3:
+    #     images.append(Image.new('RGB', (768, 768), 'gray'))
 
-    return images
+    # return images
 
 header = "Set up APIs on HuggingFace or use free at https://app.idai.tools/"
 demo = gr.Interface(fn=image_classifier, inputs=["image", "image", gr.Slider(0, 1, step=0.05, value=0.2, label="Image Strength"), "text"], outputs=["image", "image", "image"], title=header)