Create app.py

app.py

@@ -0,0 +1,190 @@
+import streamlit as st
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+import json
+import textwrap
+
+# =========================
+# 1. PAGE CONFIG
+# =========================
+st.set_page_config(
+    page_title="AI Story to Movie Scene Generator",
+    page_icon="🎬",
+    layout="wide"
+)
+
+st.title("🎬 AI Story → Movie Scene Generator (Phase 1)")
+st.write(
+    """
+    Paste a short story, and this app will break it into **cinematic scenes** with:
+    - Scene title  
+    - Setting & mood  
+    - Characters  
+    - Short summary  
+    - A detailed **visual prompt** (for future image generation)  
+    """
+)
+
+# =========================
+# 2. LOAD LLM (FLAN-T5) - CACHED
+# =========================
+
+@st.cache_resource
+def load_scene_model():
+    model_name = "google/flan-t5-base"  # good starting point, can upgrade later
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+    return tokenizer, model
+
+tokenizer, scene_model = load_scene_model()
+
+
+def generate_text(prompt: str, max_new_tokens: int = 256) -> str:
+    """
+    Helper to generate text from Flan-T5 given an instruction-style prompt.
+    """
+    inputs = tokenizer(prompt, return_tensors="pt", truncation=True)
+    output_ids = scene_model.generate(
+        **inputs,
+        max_new_tokens=max_new_tokens,
+        num_beams=4,
+        temperature=0.7,
+        top_p=0.95,
+        early_stopping=True,
+    )
+    return tokenizer.decode(output_ids[0], skip_special_tokens=True)
+
+
+# =========================
+# 3. STORY → CHUNKS → SCENES LOGIC
+# =========================
+
+def split_story_into_chunks(story_text: str, max_chars_per_chunk: int = 600):
+    """
+    Split the story into rough chunks based on paragraphs and length
+    so each chunk can be turned into a scene by the model.
+    """
+    paragraphs = [p.strip() for p in story_text.split("\n") if p.strip()]
+
+    chunks = []
+    current = ""
+    for p in paragraphs:
+        if len(current) + len(p) + 1 <= max_chars_per_chunk:
+            current += "\n" + p
+        else:
+            if current.strip():
+                chunks.append(current.strip())
+            current = p
+    if current.strip():
+        chunks.append(current.strip())
+
+    return chunks
+
+
+def chunk_to_scene(chunk_text: str, scene_id: int):
+    """
+    Convert one story chunk into a structured scene JSON using the LLM.
+    """
+    prompt = f"""
+You are a movie director's assistant.
+
+Read the following part of a story and extract a SINGLE movie scene in structured JSON.
+
+Story chunk:
+\"\"\"{chunk_text}\"\"\"
+
+Return JSON with the following keys:
+- scene_id (integer)
+- title (short scene title)
+- setting (where, when)
+- characters (list of names)
+- mood (emotional tone, e.g. tense, hopeful)
+- summary (2-3 sentences)
+- visual_prompt (a single detailed description to be used for generating a cinematic image, including lighting, style, camera angle)
+
+Only output valid JSON, nothing else.
+"""
+    raw = generate_text(prompt, max_new_tokens=256)
+
+    # Try to parse JSON
+    try:
+        data = json.loads(raw)
+    except Exception:
+        # Fallback: wrap raw text into a basic structure
+        data = {
+            "scene_id": scene_id,
+            "title": f"Scene {scene_id}",
+            "setting": "",
+            "characters": [],
+            "mood": "",
+            "summary": raw.strip(),
+            "visual_prompt": raw.strip()
+        }
+
+    # Ensure scene_id is set correctly
+    data["scene_id"] = scene_id
+    return data
+
+
+def story_to_scenes(story_text: str):
+    """
+    Full pipeline: story text -> chunks -> list of scene dicts.
+    """
+    chunks = split_story_into_chunks(story_text, max_chars_per_chunk=600)
+    scenes = []
+    for i, chunk in enumerate(chunks, start=1):
+        scene = chunk_to_scene(chunk, scene_id=i)
+        scenes.append(scene)
+    return scenes
+
+
+# =========================
+# 4. STREAMLIT UI
+# =========================
+
+st.subheader("📝 Paste Your Story")
+
+default_story = """\
+Once upon a time in a neon city, Aarav wandered the alleys alone.
+He had lost track of time after the government AI marked his family as 'non-compliant'.
+
+One night, while standing on a rooftop, he noticed a masked stranger watching him.
+The stranger claimed to know the truth about the city’s AI and its hidden rules.
+
+Aarav followed reluctantly, unaware that every step was being monitored by invisible drones.
+"""
+
+story_text = st.text_area(
+    "Paste a short story (3–15 paragraphs works best):",
+    value=default_story,
+    height=260
+)
+
+if st.button("🎬 Generate Scenes"):
+    if not story_text.strip():
+        st.error("Please paste a story first.")
+    else:
+        with st.spinner("Breaking story into scenes..."):
+            scenes = story_to_scenes(story_text)
+
+        st.success(f"Generated {len(scenes)} scene(s).")
+
+        st.markdown("---")
+        st.subheader("📚 Generated Scenes")
+
+        for scene in scenes:
+            scene_id = scene.get("scene_id", "?")
+            title = scene.get("title", f"Scene {scene_id}")
+            with st.expander(f"Scene {scene_id}: {title}", expanded=True):
+                st.markdown(f"**Setting:** {scene.get('setting', '')}")
+                st.markdown(f"**Mood:** {scene.get('mood', '')}")
+                st.markdown(f"**Characters:** {', '.join(scene.get('characters', [])) or 'N/A'}")
+
+                st.markdown("**Summary:**")
+                st.write(scene.get("summary", ""))
+
+                st.markdown("**Visual Prompt (for future image generation):**")
+                st.code(textwrap.fill(scene.get("visual_prompt", ""), width=90), language="text")
+
+        st.info("✅ Phase 1 complete: story → structured scenes.\n\nNext phases will turn these visual prompts into images and then a video.")
+else:
+    st.info("Paste a story and click **Generate Scenes** to begin.")