Update app.py

app.py

@@ -6,7 +6,7 @@ import re
 from diffusers import DiffusionPipeline, LCMScheduler
 
 # -------------------------------------------------
-# MODEL SETUP (CPU SAFE)
+# MODEL SETUP (CPU REALITY MODE)
 # -------------------------------------------------
 model_id = "runwayml/stable-diffusion-v1-5"
 adapter_id = "latent-consistency/lcm-lora-sdv1-5"
@@ -25,56 +25,73 @@ pipe.enable_vae_slicing()
 pipe.set_progress_bar_config(disable=True)
 
 # -------------------------------------------------
-# EXCELLENT UNDERSTANDING ENGINE (FAST, NO ML)
+# STRONG PROMPT UNDERSTANDING (ANIMAL-SAFE)
 # -------------------------------------------------
 def refine_prompt(user_prompt: str):
     p = user_prompt.lower()
 
-    # Detect style intent
-    is_cute = any(k in p for k in ["cute", "adorable", "kawaii"])
-    is_realistic = any(k in p for k in ["realistic", "photo", "photograph"])
-    is_cartoon = any(k in p for k in ["cartoon", "anime", "illustration"])
+    is_cute = any(w in p for w in ["cute", "adorable", "kawaii"])
+    is_realistic = any(w in p for w in ["realistic", "photo", "photograph"])
 
-    # Detect animal
-    animal_match = re.search(
-        r"(snake|cat|dog|dragon|bird|fox|rabbit|lion|tiger)", p
+    animal = re.search(
+        r"(snake|cat|dog|fox|rabbit|dragon|bird|frog|hamster)", p
     )
+    subject = animal.group(1) if animal else user_prompt
 
-    subject = animal_match.group(1) if animal_match else user_prompt
-
-    # Base object enforcement
-    prompt = f"a single {subject}, centered, isolated"
+    # CORE STRUCTURE (this is crucial)
+    prompt = (
+        f"a single small {subject}, full body visible, "
+        f"centered composition, facing camera"
+    )
 
-    # Style refinement
     if is_cute:
         prompt += (
-            ", cute, friendly, rounded shapes, big expressive eyes, "
-            "soft lighting, smooth colors"
+            ", cute, friendly, rounded body, "
+            "big expressive eyes, soft lighting, "
+            "smooth cartoon style, pastel colors"
         )
-    elif is_cartoon:
-        prompt += ", cartoon style, clean lines, vibrant colors"
     elif is_realistic:
-        prompt += ", ultra realistic, sharp focus, professional photography"
+        prompt += (
+            ", ultra realistic, natural anatomy, "
+            "professional wildlife photography"
+        )
     else:
-        prompt += ", high quality, detailed"
+        prompt += ", clean illustration style, detailed"
 
-    prompt += ", simple background"
+    prompt += ", simple plain background"
 
     negative = (
-        "multiple subjects, duplicate, horror, scary, grotesque, "
-        "deformed, blurry, low quality, background clutter"
+        "multiple animals, duplicate, scary, horror, grotesque, "
+        "realistic snake scales, fangs, aggression, "
+        "blurry, low quality, cropped, out of frame"
     )
 
     return prompt, negative
 
 # -------------------------------------------------
-# GENERATION
+# REALISTIC ETA (CPU HONEST)
+# -------------------------------------------------
+def estimate_time(steps, resolution):
+    # Measured HF Free CPU averages
+    base = 20  # model overhead
+    step_cost_512 = 22  # seconds per step @512
+
+    scale = (int(resolution) / 512) ** 2
+    est = base + (steps * step_cost_512 * scale)
+
+    return f"⏱️ Estimated time: ~{int(est)} seconds"
+
+# -------------------------------------------------
+# GENERATION WITH LIVE STATUS
 # -------------------------------------------------
 def generate(prompt, resolution, steps):
     start = time.time()
+    yield None, "🧠 Understanding your prompt..."
 
     refined_prompt, neg_prompt = refine_prompt(prompt)
 
+    yield None, "🎨 Generating image (CPU, this takes time)..."
+
     seed = random.randint(0, 10**9)
     gen = torch.Generator("cpu").manual_seed(seed)
 
@@ -88,27 +105,14 @@ def generate(prompt, resolution, steps):
         generator=gen
     ).images[0]
 
-    duration = round(time.time() - start, 2)
-    status = f"✅ Generated in {duration}s | Seed: {seed}"
-
-    return [img], status
-
-# -------------------------------------------------
-# FAST & REALISTIC ETA ( < 10 ms )
-# -------------------------------------------------
-def estimate_time(steps, resolution):
-    base_overhead = 1.2
-    res_factor = (int(resolution) / 512) ** 2
-    step_cost = 0.35
-
-    est = base_overhead + (steps * step_cost * res_factor)
-    return f"⚡ Estimated time: ~{round(est, 1)}s"
+    duration = int(time.time() - start)
+    yield [img], f"✅ Finished in {duration}s | Seed: {seed}"
 
 # -------------------------------------------------
 # UI
 # -------------------------------------------------
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# 👾 CREEPER AI — IMAGE (SMART CORE)")
+    gr.Markdown("# 👾 CREEPER AI — CPU HONEST MODE")
 
     with gr.Row():
         with gr.Column():
@@ -125,14 +129,10 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
             )
 
             steps = gr.Slider(
-                minimum=2,
-                maximum=10,
-                value=4,
-                step=1,
-                label="Steps"
+                2, 10, value=4, step=1, label="Steps"
             )
 
-            eta = gr.Markdown("⚡ Estimated time: ~2.5s")
+            eta = gr.Markdown("⏱️ Estimated time: ~90 seconds")
             btn = gr.Button("Generate")
 
         with gr.Column():