remove mask generataion

app.py

@@ -39,9 +39,12 @@ dtype = torch.bfloat16
 device = "cuda" if torch.cuda.is_available() else "cpu"
 base_model = "black-forest-labs/FLUX.1-dev"
 
+taef1 = AutoencoderTiny.from_pretrained("madebyollin/taef1", torch_dtype=dtype).to(device)
+good_vae = AutoencoderKL.from_pretrained(base_model, subfolder="vae", torch_dtype=dtype).to(device)
+pipe = FluxInpaintPipeline.from_pretrained(base_model, torch_dtype=dtype, vae=taef1).to(device)
 
-FLORENCE_MODEL, FLORENCE_PROCESSOR = load_florence_model(device=device)
-SAM_IMAGE_MODEL = load_sam_image_model(device=device)
+# FLORENCE_MODEL, FLORENCE_PROCESSOR = load_florence_model(device=device)
+# SAM_IMAGE_MODEL = load_sam_image_model(device=device)
 
 
 class calculateDuration:
@@ -147,9 +150,7 @@ def run_flux(
 ) -> Image.Image:
     print("Running FLUX...")
 
-    taef1 = AutoencoderTiny.from_pretrained("madebyollin/taef1", torch_dtype=dtype).to(device)
-    good_vae = AutoencoderKL.from_pretrained(base_model, subfolder="vae", torch_dtype=dtype).to(device)
-    pipe = FluxInpaintPipeline.from_pretrained(base_model, torch_dtype=dtype, vae=taef1).to(device)
+  
 
     with calculateDuration("load lora"):
         print("start to load lora", lora_path, lora_weights)
@@ -178,62 +179,10 @@ def run_flux(
     
     return genearte_image
 
-@spaces.GPU(duration=10)
-def genearte_mask(image_input: Image.Image, masking_prompt_text: str) -> Image.Image:
-    # generate mask by florence & sam
-    print("Generating mask...")
-    task_prompt = "<CAPTION_TO_PHRASE_GROUNDING>"
-    
-    with calculateDuration("FLORENCE"):
-        print(task_prompt, masking_prompt_text)
-        _, result = run_florence_inference(
-            model=FLORENCE_MODEL,
-            processor=FLORENCE_PROCESSOR,
-            device=device,
-            image=image_input,
-            task=task_prompt,
-            text=masking_prompt_text
-        )
-
-    with calculateDuration("sv.Detections"):
-        # start to dectect
-        detections = sv.Detections.from_lmm(
-            lmm=sv.LMM.FLORENCE_2,
-            result=result,
-            resolution_wh=image_input.size
-        )
-    
-    images = []
-
-    with calculateDuration("generate segmenet mask"):
-        # using sam generate segments images        
-        detections = run_sam_inference(SAM_IMAGE_MODEL, image_input, detections)
-        if len(detections) == 0:
-            gr.Info("No objects detected.")
-            return None
-        print("mask generated:", len(detections.mask))
-        kernel_size = dilate
-        kernel = np.ones((kernel_size, kernel_size), np.uint8)
-
-        for i in range(len(detections.mask)):
-            mask = detections.mask[i].astype(np.uint8) * 255
-            images.append(mask)
-
-        # merge mark into on image
-        merged_mask = np.zeros_like(images[0], dtype=np.uint8)
-        for mask in images:
-            merged_mask = cv2.bitwise_or(merged_mask, mask)
-        
-        images = [merged_mask]
-    
-    return images[0]
-
-
-
 def process(
     image_url: str,
+    mask_url: str,
     inpainting_prompt_text: str,
-    masking_prompt_text: str,
     mask_inflation_slider: int,
     mask_blur_slider: int,
     seed_slicer: int,
@@ -260,26 +209,16 @@ def process(
         result["message"] = "invalid inpainting prompt"
         return json.dumps(result)
     
-    if not masking_prompt_text:
-        gr.Info("Please enter masking_prompt_text.")
-        result["message"] = "invalid masking prompt"
-        return json.dumps(result)
 
     with calculateDuration("load image"):
         image = load_image(image_url)
+        mask = load_image(mask_url)
     
-    mask = genearte_mask(image, masking_prompt_text)
-    
-    if not image:
-        gr.Info("Please upload an image.")
+    if not image or not mask:
+        gr.Info("Please upload an image & mask by url.")
         result["message"] = "can not load image"
         return json.dumps(result)
 
-    if is_mask_empty(mask):
-        gr.Info("Please draw a mask or enter a masking prompt.")
-        result["message"] = "can not generate mask"
-        return json.dumps(result)
-
     # generate
     width, height = calculate_image_dimensions_for_flux(original_resolution_wh=image.size)
     image = image.resize((width, height), Image.LANCZOS)
@@ -321,11 +260,11 @@ with gr.Blocks() as demo:
                     container=False,
                 )
             
-            masking_prompt_text_component = gr.Text(
-                    label="Masking prompt",
+            mask_url = gr.Text(
+                    label="image url of masking",
                     show_label=False,
                     max_lines=1,
-                    placeholder="Enter text to generate masking",
+                    placeholder="Enter url of masking",
                     container=False,
                 )
 
@@ -439,8 +378,8 @@ with gr.Blocks() as demo:
         fn=process,
         inputs=[
             image_url,
+            mask_url,
             inpainting_prompt_text_component,
-            masking_prompt_text_component,
             mask_inflation_slider_component,
             mask_blur_slider_component,
             seed_slicer_component,