Update app.py

app.py

@@ -25,33 +25,25 @@ pipe.enable_vae_slicing()
 pipe.set_progress_bar_config(disable=True)
 
 # -------------------------------
-# FAST THINKING PROMPT ENGINE
+# PROMPT REFINEMENT
 # -------------------------------
-def refine_prompt_fast(user_prompt: str):
+def refine_prompt(user_prompt: str):
     """
-    Instant deterministic prompt refinement (<1ms)
+    CPU-fast prompt enhancement.
+    Always focuses on a single centered object.
     """
-    known_objects = {"apple","banana","snake","cat","dog","fox","rabbit","dragon","bird","frog","hamster"}
-    object_found = next((w for w in known_objects if w in user_prompt.lower()), None)
-    subject = object_found if object_found else user_prompt.lower().strip()
-
-    style = ""
-    if any(w in user_prompt.lower() for w in ["cute","adorable","kawaii"]):
-        style = ", cute, friendly, rounded body, big eyes, pastel colors, cartoon style"
-    elif any(w in user_prompt.lower() for w in ["realistic","photo","photograph"]):
-        style = ", ultra realistic, natural anatomy, professional photography"
-    else:
-        style = ", high quality, clean background"
-
-    prompt = f"a single {subject}, centered, isolated{style}"
-    negative = "multiple objects, duplicate, blurry, low quality, cropped, out of frame, horror, grotesque, aggressive, weird colors, artifacts"
+    subject = user_prompt.strip()
+    prompt = f"a single {subject}, centered, isolated, high quality, clean background"
+    negative = "multiple objects, duplicate, blurry, low quality, cropped, out of frame, horror, grotesque, weird colors, artifacts"
     return prompt, negative
 
 # -------------------------------
-# REALISTIC ETA CALCULATION
+# ETA ESTIMATION
 # -------------------------------
 def estimate_time(steps, resolution):
-    per_step = {256:6, 512:12, 768:25, 1024:45}[int(resolution)]
+    steps = int(steps)
+    resolution = int(resolution)
+    per_step = {256:6, 512:12, 768:25, 1024:45}[resolution]
     overhead = 2
     est = overhead + steps * per_step
     minutes = est // 60
@@ -59,42 +51,45 @@ def estimate_time(steps, resolution):
     return f"⏱️ Estimated time: ~{int(minutes)}m {int(seconds)}s"
 
 # -------------------------------
-# IMAGE GENERATION WITH PROGRESSIVE BLUR GALLERY
+# IMAGE GENERATION WITH PROGRESSIVE BLUR
 # -------------------------------
 def generate(prompt, resolution, steps):
-    # --- THINKING PHASE ---
-    refined_prompt, neg_prompt = refine_prompt_fast(prompt)
+    steps = int(steps)
+    resolution = int(resolution)
 
-    # --- SHOW WHITE IMAGE WHILE GENERATING ---
-    width, height = int(resolution), int(resolution)
-    blank_img = Image.new("RGB", (width, height), (255, 255, 255))
-    yield [blank_img], ""  # always show gallery placeholder
+    # 1️⃣ Refine prompt
+    refined_prompt, neg_prompt = refine_prompt(prompt)
 
-    # --- GENERATION PHASE ---
+    # 2️⃣ Show blank gallery image while generating
+    blank_img = Image.new("RGB", (resolution, resolution), (255, 255, 255))
+    yield [blank_img]
+
+    # 3️⃣ CPU Image generation
     seed = random.randint(0, 10**9)
     gen = torch.Generator("cpu").manual_seed(seed)
-    pipe.scheduler.set_timesteps(int(steps))
+    pipe.scheduler.set_timesteps(steps)
+
     img = pipe(
         prompt=refined_prompt,
         negative_prompt=neg_prompt,
-        num_inference_steps=int(steps),
+        num_inference_steps=steps,
         guidance_scale=1.2,
-        width=width,
-        height=height,
+        width=resolution,
+        height=resolution,
         generator=gen
     ).images[0]
 
-    # --- PROGRESSIVE BLUR REVEAL ---
-    max_blur = 20  # max blur radius for 100%
+    # 4️⃣ Progressive blur reveal
+    max_blur = 20
     steps_blur = 10
     for i in range(steps_blur):
         blur_percent = 100 - i*10
         blurred_img = img.filter(ImageFilter.GaussianBlur(radius=max_blur * blur_percent / 100))
-        yield [blurred_img], ""  # gallery updated, no status text
+        yield [blurred_img]
         time.sleep(1)  # 1 second per step
 
-    # --- FINAL IMAGE ---
-    yield [img], ""  # fully revealed image
+    # 5️⃣ Fully revealed image
+    yield [img]
 
 # -------------------------------
 # GRADIO UI
@@ -105,14 +100,14 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
     with gr.Row():
         with gr.Column():
             prompt_in = gr.Textbox(label="Prompt", placeholder="cute snake", lines=2)
-            
+
             resolution = gr.Radio([256, 512, 768, 1024], value=512, label="Resolution")
-            
-            steps = gr.Slider(2, 8, value=4, step=1, label="Steps")
-            
+
+            steps = gr.Slider(4, 8, value=4, step=1, label="Steps")  # minimum 4
+
             eta = gr.Markdown("⏱️ Estimated time: ~1m 0s")
             gen_btn = gr.Button("Generate")
-        
+
         with gr.Column():
             gallery = gr.Gallery(columns=1)
 
@@ -124,7 +119,7 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
     gen_btn.click(
         generate,
         inputs=[prompt_in, resolution, steps],
-        outputs=[gallery, gallery]  # gallery updated for progressive blur
+        outputs=[gallery]
     )
 
 demo.launch()