Upload folder using huggingface_hub

index.py

@@ -26,9 +26,12 @@ REPLICATE_API_TOKEN = os.getenv('REPLICATE_API_TOKEN')
 
 client = OpenAI()
 
-def main(img):
+def main(img, strength):
     mask = img['layers'][0]
 
+    # Match prompt strength from .4 to 1 (total destruction)
+    prompt_strength = round(-0.6 * strength + 1, 2)
+
     base_image = Image.fromarray(img['background'].astype('uint8'))
     img_base_64 = img_to_base64(base_image)
 
@@ -39,17 +42,17 @@ def main(img):
         mask_base_64 = img_to_base64(mask_img)
 
     prompt = call_openai(img_base_64)
+    #prompt = "The image shows a person wearing sleek, over-ear headphones with a matte finish and a cool, light beige color (Pantone 7527 C), captured under soft, diffused natural lighting, emphasizing the smooth and minimalist design of the headphones."
 
-    output_urls = generate_image(prompt, img_base_64, mask_base_64)
-
+    output_urls = generate_image(prompt, img_base_64, mask_base_64, prompt_strength)
     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):
+def generate_image(prompt, img, mask, prompt_strength):
     input_data = {
         "image": img,
-        "prompt": prompt + ", expensive",
+        "prompt": prompt + " expensive",
         "refine": "no_refiner",
         "scheduler": "K_EULER",
         "lora_scale": 0.8,
@@ -57,10 +60,10 @@ def generate_image(prompt, img, mask):
         "controlnet_1": "edge_canny",
         "controlnet_2": "depth_midas",
         "controlnet_3": "lineart",
-        "guidance_scale": 7.5,
+        "guidance_scale": 4,
         "apply_watermark": False,
-        "negative_prompt":"worst quality, low quality, illustration, 2d, painting, cartoons, sketch",
-        "prompt_strength": 0.75,
+        "negative_prompt":"worst quality, low quality, illustration, 2d, painting, cartoons, sketch, logo",
+        "prompt_strength": prompt_strength,
         "sizing_strategy": "controlnet_1_image",
         "controlnet_1_end": 1,
         "controlnet_2_end": 1,
@@ -80,7 +83,7 @@ def generate_image(prompt, img, mask):
     if mask is not None:
         input_data["mask"] = mask
     else:
-        input_data["prompt_strength"] = .6
+        input_data["prompt_strength"] = .3
 
     output = replicate.run(
         "fofr/realvisxl-v3-multi-controlnet-lora:90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daade",
@@ -133,7 +136,7 @@ def call_openai(image_data):
                 {
                     "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": "text", "text": "Please describe this image in one sentence, with a focus on the material, finish and specific color (color is really important, so provide specific pantone colors), whether the color is warm or cool, and details of the main object in the scene. Mention the type of lighting as well."},
                         {
                             "type": "image_url",
                             "image_url": {
@@ -160,8 +163,9 @@ black_brush = gr.Brush(colors=["#000000"], default_color="#000000", color_mode="
 # 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")]
+    inputs=[gr.ImageEditor(brush=black_brush), gr.Slider(0, 1, step=0.025, value=0.5, label="Image Strength")],
+    #outputs=[gr.Image(type="pil"), gr.Image(type="pil"), gr.Image(type="pil"), gr.Image(type="pil")]
+    outputs=["image", "image", "image", "image"]
 )
 
 demo.launch(share=False)