Update app.py

app.py

@@ -1,12 +1,16 @@
-import torch
-import gradio as gr
+import os
 import gc
-from diffusers import StableDiffusionPipeline, StableDiffusionImg2ImgPipeline
-from PIL import Image
 import uuid
 import time
 import random
-import os
+import requests
+
+import torch
+import gradio as gr
+
+from PIL import Image
+from diffusers import StableDiffusionPipeline, StableDiffusionImg2ImgPipeline
+
 
 # =========================
 # DEVICE
@@ -14,10 +18,17 @@ import os
 device = "cpu"
 
 # =========================
-# MODEL CONFIG
+# DREAMSHAPER MODEL CONFIG
 # =========================
 MODEL_ID = "Lykon/dreamshaper-8"
 
+# =========================
+# GROQ API CONFIG
+# =========================
+GROQ_API_KEY = os.getenv("GROQ_API_KEY", "")
+GROQ_MODEL = os.getenv("GROQ_MODEL", "llama-3.3-70b-versatile")
+GROQ_API_URL = "https://api.groq.com/openai/v1/chat/completions"
+
 # =========================
 # GLOBAL STATE
 # =========================
@@ -25,26 +36,34 @@ current_pipe = None
 current_mode = None
 history = []
 
+
 # =========================
 # STYLE PRESETS
 # =========================
 STYLE_PRESETS = {
     "None": "",
-    "Realistic": "photorealistic, natural lighting, depth of field",
-    "Anime": "anime style, vibrant colors, clean lines",
-    "Cinematic": "cinematic lighting, dramatic shadows, movie composition",
+    "Realistic": "photorealistic, realistic lighting, realistic details, natural skin texture",
+    "Anime": "anime style, vibrant colors, clean line art, detailed anime illustration",
+    "Cinematic": "cinematic lighting, dramatic shadows, film still, movie composition",
+    "Fantasy": "fantasy art, magical atmosphere, epic composition, highly detailed",
+    "Product": "professional product photography, studio lighting, clean background",
 }
 
+
 # =========================
 # NEGATIVE PROMPT
 # =========================
 NEGATIVE_PROMPT = (
     "worst quality, low quality, blurry, bad anatomy, bad proportions, "
-    "extra limbs, distorted, deformed, ugly, watermark"
+    "extra limbs, missing limbs, distorted face, deformed hands, bad hands, "
+    "extra fingers, missing fingers, duplicated body parts, ugly, watermark, "
+    "text, logo, signature, jpeg artifacts, oversaturated"
 )
 
+
 # =========================
-# TRANSLATE ID TO EN SIMPLE
+# SIMPLE LOCAL TRANSLATOR ID TO EN
+# FALLBACK JIKA GROQ API TIDAK AKTIF
 # =========================
 def translate_prompt(prompt):
     if not prompt:
@@ -52,17 +71,25 @@ def translate_prompt(prompt):
 
     mapping = {
         "pria": "man",
+        "laki-laki": "man",
         "wanita": "woman",
+        "perempuan": "woman",
         "anak": "child",
+        "wajah": "face",
+        "potret": "portrait",
         "gunung": "mountain",
         "pantai": "beach",
         "kota": "city",
         "malam": "night",
         "siang": "day",
+        "pagi": "morning",
+        "sore": "afternoon",
+        "senja": "sunset",
         "laut": "sea",
         "langit": "sky",
         "hutan": "forest",
         "mobil": "car",
+        "motor": "motorcycle",
         "rumah": "house",
         "jalan": "street",
         "sungai": "river",
@@ -72,7 +99,29 @@ def translate_prompt(prompt):
         "burung": "bird",
         "bunga": "flower",
         "pohon": "tree",
-        "robot": "robot"
+        "robot": "robot",
+        "hujan": "rain",
+        "salju": "snow",
+        "api": "fire",
+        "air": "water",
+        "cantik": "beautiful",
+        "tampan": "handsome",
+        "futuristik": "futuristic",
+        "tradisional": "traditional",
+        "jawa": "javanese",
+        "indonesia": "indonesia",
+        "desa": "village",
+        "sawah": "rice field",
+        "kerajaan": "kingdom",
+        "istana": "palace",
+        "emas": "gold",
+        "perak": "silver",
+        "hitam": "black",
+        "putih": "white",
+        "merah": "red",
+        "biru": "blue",
+        "hijau": "green",
+        "kuning": "yellow",
     }
 
     prompt = prompt.lower()
@@ -91,12 +140,14 @@ def detect_type(prompt):
 
     portrait_keywords = [
         "person", "man", "woman", "girl", "boy",
-        "face", "portrait", "child"
+        "face", "portrait", "child", "people"
     ]
 
     scene_keywords = [
         "mountain", "city", "forest", "beach", "sky",
-        "sea", "street", "river", "lake", "tree"
+        "sea", "street", "river", "lake", "tree",
+        "village", "landscape", "room", "house",
+        "rice field", "palace"
     ]
 
     if any(k in p for k in portrait_keywords):
@@ -109,31 +160,35 @@ def detect_type(prompt):
 
 
 # =========================
-# AI PROMPT ENGINE
+# LOCAL PROMPT ENGINE
 # =========================
-def build_prompt(prompt, style):
+def build_prompt_local(prompt, style):
+    """
+    Fallback prompt engine lokal jika Groq API tidak tersedia.
+    """
     prompt = translate_prompt(prompt)
     style_text = STYLE_PRESETS.get(style, "")
 
-    base = "masterpiece, best quality, ultra detailed, sharp focus, 4k"
-    detail = "intricate details, HDR, high detail"
+    base = "masterpiece, best quality, ultra detailed, sharp focus, high detail"
+    detail = "intricate details, detailed texture, balanced composition"
 
     ptype = detect_type(prompt)
 
     if ptype == "portrait":
         extra = (
-            "detailed face, skin texture, soft lighting, "
-            "portrait composition, depth of field"
+            "detailed face, natural skin texture, expressive eyes, "
+            "soft lighting, portrait composition, depth of field, "
+            "realistic facial proportions"
         )
     elif ptype == "scene":
         extra = (
             "wide shot, cinematic composition, environmental detail, "
-            "atmospheric lighting"
+            "atmospheric lighting, realistic perspective, immersive scene"
         )
     else:
         extra = (
-            "product photography, centered composition, "
-            "studio lighting"
+            "centered composition, studio lighting, clean background, "
+            "sharp object details, professional photography"
         )
 
     parts = [
@@ -147,6 +202,122 @@ def build_prompt(prompt, style):
     return ", ".join([p for p in parts if p])
 
 
+# =========================
+# GROQ PROMPT ENHANCER
+# =========================
+def enhance_prompt_with_groq(user_prompt, style):
+    """
+    Mengubah prompt Bahasa Indonesia menjadi prompt Bahasa Inggris
+    yang lebih optimal untuk DreamShaper / Stable Diffusion menggunakan Groq API.
+    """
+
+    if not user_prompt:
+        return ""
+
+    if not GROQ_API_KEY:
+        print("GROQ_API_KEY belum diset. Menggunakan prompt lokal.")
+        return build_prompt_local(user_prompt, style)
+
+    system_prompt = """
+You are an expert prompt engineer for Stable Diffusion DreamShaper.
+
+Your task:
+- Convert Indonesian image prompts into high-quality English prompts.
+- Preserve the user's exact visual intent.
+- Do not change the main subject.
+- Do not add unrelated objects.
+- Add useful visual details only when helpful:
+  composition, lighting, atmosphere, camera angle, lens, texture, detail level, realism, style.
+- Make the final prompt suitable for Stable Diffusion / DreamShaper.
+- Return only one final English prompt.
+- Do not use markdown.
+- Do not use bullet points.
+- Do not explain anything.
+
+Important:
+- Keep the output concise but rich in visual detail.
+- Avoid overly long prompts.
+- Keep the prompt general-audience safe.
+- If the request is unsafe or inappropriate, rewrite it into a safe, non-explicit, general-audience visual prompt.
+"""
+
+    selected_style = STYLE_PRESETS.get(style, "")
+
+    user_message = f"""
+User Indonesian prompt:
+{user_prompt}
+
+Selected style:
+{style}
+
+Style keyword:
+{selected_style}
+
+Create one optimized English prompt for DreamShaper.
+"""
+
+    headers = {
+        "Authorization": f"Bearer {GROQ_API_KEY}",
+        "Content-Type": "application/json"
+    }
+
+    payload = {
+        "model": GROQ_MODEL,
+        "messages": [
+            {
+                "role": "system",
+                "content": system_prompt
+            },
+            {
+                "role": "user",
+                "content": user_message
+            }
+        ],
+        "temperature": 0.35,
+        "max_tokens": 300
+    }
+
+    try:
+        response = requests.post(
+            GROQ_API_URL,
+            headers=headers,
+            json=payload,
+            timeout=30
+        )
+
+        response.raise_for_status()
+
+        data = response.json()
+
+        enhanced_prompt = data["choices"][0]["message"]["content"].strip()
+        enhanced_prompt = enhanced_prompt.replace("\n", " ").strip()
+
+        if not enhanced_prompt:
+            return build_prompt_local(user_prompt, style)
+
+        return enhanced_prompt
+
+    except Exception as e:
+        print("Groq prompt enhancer error:", e)
+        print("Fallback ke prompt lokal.")
+        return build_prompt_local(user_prompt, style)
+
+
+# =========================
+# MAIN PROMPT BUILDER
+# =========================
+def build_prompt(prompt, style, use_groq=True):
+    """
+    Prompt utama.
+    Jika use_groq aktif dan API key tersedia, prompt diproses Groq.
+    Jika gagal, fallback ke prompt lokal.
+    """
+    if use_groq:
+        return enhance_prompt_with_groq(prompt, style)
+
+    return build_prompt_local(prompt, style)
+
+
 # =========================
 # LOAD PIPELINE DREAMSHAPER ONLY
 # =========================
@@ -280,6 +451,7 @@ def prepare_img2img_input(input_image):
 def generate_text_to_image(
     prompt,
     style,
+    use_groq,
     steps,
     width,
     height,
@@ -288,7 +460,9 @@ def generate_text_to_image(
 ):
     pipe = load_pipe("txt2img")
 
-    final_prompt = build_prompt(prompt, style)
+    final_prompt = build_prompt(prompt, style, use_groq)
+
+    print("FINAL TXT2IMG PROMPT:", final_prompt)
 
     width = normalize_size(width)
     height = normalize_size(height)
@@ -313,7 +487,7 @@ def generate_text_to_image(
 
     file_path = save_image(image)
 
-    return image, file_path, seed, history
+    return image, file_path, seed, final_prompt, history
 
 
 # =========================
@@ -322,6 +496,7 @@ def generate_text_to_image(
 def generate_image_to_image(
     prompt,
     style,
+    use_groq,
     steps,
     seed,
     input_image,
@@ -329,11 +504,13 @@ def generate_image_to_image(
     up
 ):
     if input_image is None:
-        return None, None, None, history
+        return None, None, None, "Input image belum diisi.", history
 
     pipe = load_pipe("img2img")
 
-    final_prompt = build_prompt(prompt, style)
+    final_prompt = build_prompt(prompt, style, use_groq)
+
+    print("FINAL IMG2IMG PROMPT:", final_prompt)
 
     seed = normalize_seed(seed)
     input_image = prepare_img2img_input(input_image)
@@ -357,7 +534,7 @@ def generate_image_to_image(
 
     file_path = save_image(image)
 
-    return image, file_path, seed, history
+    return image, file_path, seed, final_prompt, history
 
 
 # =========================
@@ -366,6 +543,7 @@ def generate_image_to_image(
 def run_txt2img(
     prompt,
     style,
+    use_groq,
     steps,
     width,
     height,
@@ -377,6 +555,7 @@ def run_txt2img(
             return generate_text_to_image(
                 prompt,
                 style,
+                use_groq,
                 steps,
                 width,
                 height,
@@ -388,12 +567,13 @@ def run_txt2img(
             gc.collect()
             time.sleep(2)
 
-    return None, None, None, history
+    return None, None, None, "Generation failed. Check Space logs.", history
 
 
 def run_img2img(
     prompt,
     style,
+    use_groq,
     steps,
     seed,
     input_image,
@@ -405,6 +585,7 @@ def run_img2img(
             return generate_image_to_image(
                 prompt,
                 style,
+                use_groq,
                 steps,
                 seed,
                 input_image,
@@ -416,7 +597,7 @@ def run_img2img(
             gc.collect()
             time.sleep(2)
 
-    return None, None, None, history
+    return None, None, None, "Generation failed. Check Space logs.", history
 
 
 # =========================
@@ -454,23 +635,31 @@ def clear_history():
     return [], None, None
 
 
+def check_groq_status():
+    if GROQ_API_KEY:
+        return f"✅ Groq API aktif. Model: `{GROQ_MODEL}`"
+
+    return (
+        "⚠️ `GROQ_API_KEY` belum ditemukan. "
+        "Prompt enhancer akan memakai fallback lokal."
+    )
+
+
 # =========================
 # UI
 # =========================
 with gr.Blocks() as demo:
-    gr.Markdown("# 🚀 AI Image Studio - DreamShaper Edition")
+    gr.Markdown("# 🚀 AI Image Studio - DreamShaper + Groq Prompt Enhancer")
+
     gr.Markdown(
         """
-        Semua fitur menggunakan **DreamShaper**.
-
-        Fitur:
-        - Text to Image
-        - Image to Image
-        - History otomatis
-        - Re-use gambar dari History ke Image to Image
+        Masukkan prompt dalam **Bahasa Indonesia**.  
+        Jika **Groq Prompt Enhancer** aktif, prompt akan diubah otomatis menjadi prompt Bahasa Inggris yang lebih optimal untuk DreamShaper.
         """
     )
 
+    gr.Markdown(check_groq_status())
+
     selected_history_index = gr.State(value=None)
 
     with gr.Tabs(selected="txt2img") as tabs:
@@ -481,8 +670,8 @@ with gr.Blocks() as demo:
         with gr.Tab("Text to Image", id="txt2img"):
             txt_prompt = gr.Textbox(
                 lines=3,
-                label="Prompt",
-                placeholder="Contoh: pria berdiri di kota futuristik malam hari"
+                label="Prompt Bahasa Indonesia",
+                placeholder="Contoh: pria memakai jaket hitam berdiri di jalan kota saat hujan malam hari"
             )
 
             txt_style = gr.Dropdown(
@@ -491,6 +680,11 @@ with gr.Blocks() as demo:
                 label="Style"
             )
 
+            txt_use_groq = gr.Checkbox(
+                label="Gunakan Groq Prompt Enhancer",
+                value=True
+            )
+
             txt_steps = gr.Slider(
                 minimum=10,
                 maximum=30,
@@ -535,6 +729,12 @@ with gr.Blocks() as demo:
                 label="Seed Used"
             )
 
+            txt_final_prompt = gr.Textbox(
+                lines=5,
+                label="Final Prompt ke DreamShaper",
+                interactive=False
+            )
+
             txt_file_output = gr.File(
                 label="Download Image"
             )
@@ -545,8 +745,8 @@ with gr.Blocks() as demo:
         with gr.Tab("Image to Image", id="img2img"):
             img_prompt = gr.Textbox(
                 lines=3,
-                label="Prompt",
-                placeholder="Contoh: ubah menjadi cinematic style, lighting dramatis"
+                label="Prompt Bahasa Indonesia",
+                placeholder="Contoh: ubah menjadi cinematic style, lighting dramatis, detail lebih realistis"
             )
 
             img_input = gr.Image(
@@ -554,6 +754,17 @@ with gr.Blocks() as demo:
                 label="Input Image"
             )
 
+            img_style = gr.Dropdown(
+                choices=list(STYLE_PRESETS.keys()),
+                value="Realistic",
+                label="Style"
+            )
+
+            img_use_groq = gr.Checkbox(
+                label="Gunakan Groq Prompt Enhancer",
+                value=True
+            )
+
             img_strength = gr.Slider(
                 minimum=0.1,
                 maximum=1.0,
@@ -562,12 +773,6 @@ with gr.Blocks() as demo:
                 label="Strength"
             )
 
-            img_style = gr.Dropdown(
-                choices=list(STYLE_PRESETS.keys()),
-                value="Realistic",
-                label="Style"
-            )
-
             img_steps = gr.Slider(
                 minimum=10,
                 maximum=30,
@@ -596,6 +801,12 @@ with gr.Blocks() as demo:
                 label="Seed Used"
             )
 
+            img_final_prompt = gr.Textbox(
+                lines=5,
+                label="Final Prompt ke DreamShaper",
+                interactive=False
+            )
+
             img_file_output = gr.File(
                 label="Download Image"
             )
@@ -606,8 +817,8 @@ with gr.Blocks() as demo:
         with gr.Tab("History", id="history"):
             gr.Markdown(
                 """
-                Gambar yang sudah dibuat dari **Text to Image** atau **Image to Image**
-                akan otomatis muncul di sini.
+                Gambar yang dibuat dari **Text to Image** atau **Image to Image**
+                otomatis muncul di sini.
 
                 Cara memakai ulang:
                 1. Klik salah satu gambar di History
@@ -638,12 +849,12 @@ with gr.Blocks() as demo:
     # EVENTS
     # =========================
 
-    # Text to Image event
     txt_button.click(
         fn=run_txt2img,
         inputs=[
             txt_prompt,
             txt_style,
+            txt_use_groq,
             txt_steps,
             txt_width,
             txt_height,
@@ -654,16 +865,17 @@ with gr.Blocks() as demo:
             txt_result,
             txt_file_output,
             txt_seed_output,
+            txt_final_prompt,
             history_gallery
         ]
     )
 
-    # Image to Image event
     img_button.click(
         fn=run_img2img,
         inputs=[
             img_prompt,
             img_style,
+            img_use_groq,
             img_steps,
             img_seed,
             img_input,
@@ -674,11 +886,11 @@ with gr.Blocks() as demo:
             img_result,
             img_file_output,
             img_seed_output,
+            img_final_prompt,
             history_gallery
         ]
     )
 
-    # Select history image
     history_gallery.select(
         fn=select_history,
         outputs=[
@@ -687,7 +899,6 @@ with gr.Blocks() as demo:
         ]
     )
 
-    # Reuse selected history image to Image to Image tab
     reuse_button.click(
         fn=reuse_history,
         inputs=[
@@ -699,7 +910,6 @@ with gr.Blocks() as demo:
         ]
     )
 
-    # Clear history
     clear_history_button.click(
         fn=clear_history,
         inputs=[],
@@ -710,7 +920,6 @@ with gr.Blocks() as demo:
         ]
     )
 
-    # Load initial history
     demo.load(
         fn=lambda: history,
         inputs=[],