Update app.py

app.py

@@ -1,96 +1,130 @@
 #!/usr/bin/env python3
 import os
+import glob
 import base64
 import time
+import shutil
+import streamlit as st
+import pandas as pd
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
-import numpy as np
-from PIL import Image
-import gradio as gr
-import torchvision.transforms as transforms
-from transformers import AutoModel, AutoTokenizer
+from transformers import AutoModelForCausalLM, AutoTokenizer, AutoModel
 from diffusers import StableDiffusionPipeline
 from torch.utils.data import Dataset, DataLoader
-import asyncio
-import aiofiles
-import fitz  # PyMuPDF
+import csv
+import fitz
 import requests
+from PIL import Image
+import cv2
+import numpy as np
 import logging
+import asyncio
+import aiofiles
 from io import BytesIO
 from dataclasses import dataclass
-from typing import Optional
+from typing import Optional, Tuple
+import zipfile
+import math
+import random
+import re
 
-# Logging setup
 logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
 logger = logging.getLogger(__name__)
+log_records = []
+
+class LogCaptureHandler(logging.Handler):
+    def emit(self, record):
+        log_records.append(record)
+
+logger.addHandler(LogCaptureHandler())
+
+st.set_page_config(
+    page_title="AI Vision & SFT Titans 🚀",
+    page_icon="🤖",
+    layout="wide",
+    initial_sidebar_state="expanded",
+    menu_items={
+        'Get Help': 'https://huggingface.co/awacke1',
+        'Report a Bug': 'https://huggingface.co/spaces/awacke1',
+        'About': "AI Vision & SFT Titans: PDFs, OCR, Image Gen, Line Drawings, Custom Diffusion, and SFT on CPU! 🌌"
+    }
+)
+
+if 'history' not in st.session_state:
+    st.session_state['history'] = []
+if 'builder' not in st.session_state:
+    st.session_state['builder'] = None
+if 'model_loaded' not in st.session_state:
+    st.session_state['model_loaded'] = False
+if 'processing' not in st.session_state:
+    st.session_state['processing'] = {}
+if 'asset_checkboxes' not in st.session_state:
+    st.session_state['asset_checkboxes'] = {}
+if 'downloaded_pdfs' not in st.session_state:
+    st.session_state['downloaded_pdfs'] = {}
+if 'unique_counter' not in st.session_state:
+    st.session_state['unique_counter'] = 0  # For generating unique keys
+
+@dataclass
+class ModelConfig:
+    name: str
+    base_model: str
+    size: str
+    domain: Optional[str] = None
+    model_type: str = "causal_lm"
+    @property
+    def model_path(self):
+        return f"models/{self.name}"
+
+@dataclass
+class DiffusionConfig:
+    name: str
+    base_model: str
+    size: str
+    domain: Optional[str] = None
+    @property
+    def model_path(self):
+        return f"diffusion_models/{self.name}"
+
+class SFTDataset(Dataset):
+    def __init__(self, data, tokenizer, max_length=128):
+        self.data = data
+        self.tokenizer = tokenizer
+        self.max_length = max_length
+    def __len__(self):
+        return len(self.data)
+    def __getitem__(self, idx):
+        prompt = self.data[idx]["prompt"]
+        response = self.data[idx]["response"]
+        full_text = f"{prompt} {response}"
+        full_encoding = self.tokenizer(full_text, max_length=self.max_length, padding="max_length", truncation=True, return_tensors="pt")
+        prompt_encoding = self.tokenizer(prompt, max_length=self.max_length, padding=False, truncation=True, return_tensors="pt")
+        input_ids = full_encoding["input_ids"].squeeze()
+        attention_mask = full_encoding["attention_mask"].squeeze()
+        labels = input_ids.clone()
+        prompt_len = prompt_encoding["input_ids"].shape[1]
+        if prompt_len < self.max_length:
+            labels[:prompt_len] = -100
+        return {"input_ids": input_ids, "attention_mask": attention_mask, "labels": labels}
+
+class DiffusionDataset(Dataset):
+    def __init__(self, images, texts):
+        self.images = images
+        self.texts = texts
+    def __len__(self):
+        return len(self.images)
+    def __getitem__(self, idx):
+        return {"image": self.images[idx], "text": self.texts[idx]}
+
+class TinyDiffusionDataset(Dataset):
+    def __init__(self, images):
+        self.images = [torch.tensor(np.array(img.convert("RGB")).transpose(2, 0, 1), dtype=torch.float32) / 255.0 for img in images]
+    def __len__(self):
+        return len(self.images)
+    def __getitem__(self, idx):
+        return self.images[idx]
 
-# Neural network layers for line drawing
-norm_layer = nn.InstanceNorm2d
-
-# Residual Block for Generator
-class ResidualBlock(nn.Module):
-    def __init__(self, in_features):
-        super(ResidualBlock, self).__init__()
-        conv_block = [
-            nn.ReflectionPad2d(1),
-            nn.Conv2d(in_features, in_features, 3),
-            norm_layer(in_features),
-            nn.ReLU(inplace=True),
-            nn.ReflectionPad2d(1),
-            nn.Conv2d(in_features, in_features, 3),
-            norm_layer(in_features)
-        ]
-        self.conv_block = nn.Sequential(*conv_block)
-
-    def forward(self, x):
-        return x + self.conv_block(x)
-
-# Generator for Line Drawings
-class Generator(nn.Module):
-    def __init__(self, input_nc, output_nc, n_residual_blocks=9, sigmoid=True):
-        super(Generator, self).__init__()
-        model0 = [nn.ReflectionPad2d(3), nn.Conv2d(input_nc, 64, 7), norm_layer(64), nn.ReLU(inplace=True)]
-        self.model0 = nn.Sequential(*model0)
-        model1 = []
-        in_features, out_features = 64, 128
-        for _ in range(2):
-            model1 += [nn.Conv2d(in_features, out_features, 3, stride=2, padding=1), norm_layer(out_features), nn.ReLU(inplace=True)]
-            in_features, out_features = out_features, out_features * 2
-        self.model1 = nn.Sequential(*model1)
-        model2 = [ResidualBlock(in_features) for _ in range(n_residual_blocks)]
-        self.model2 = nn.Sequential(*model2)
-        model3 = []
-        out_features = in_features // 2
-        for _ in range(2):
-            model3 += [nn.ConvTranspose2d(in_features, out_features, 3, stride=2, padding=1, output_padding=1), norm_layer(out_features), nn.ReLU(inplace=True)]
-            in_features, out_features = out_features, out_features // 2
-        self.model3 = nn.Sequential(*model3)
-        model4 = [nn.ReflectionPad2d(3), nn.Conv2d(64, output_nc, 7)]
-        if sigmoid:
-            model4 += [nn.Sigmoid()]
-        self.model4 = nn.Sequential(*model4)
-
-    def forward(self, x, cond=None):
-        out = self.model0(x)
-        out = self.model1(out)
-        out = self.model2(out)
-        out = self.model3(out)
-        out = self.model4(out)
-        return out
-
-# Load Line Drawing Models
-model1 = Generator(3, 1, 3)
-model2 = Generator(3, 1, 3)
-try:
-    model1.load_state_dict(torch.load('model.pth', map_location='cpu', weights_only=True))
-    model2.load_state_dict(torch.load('model2.pth', map_location='cpu', weights_only=True))
-except FileNotFoundError:
-    logger.warning("Model files not found. Please ensure 'model.pth' and 'model2.pth' are available.")
-model1.eval()
-model2.eval()
-
-# Tiny Diffusion Model
 class TinyUNet(nn.Module):
     def __init__(self, in_channels=3, out_channels=3):
         super(TinyUNet, self).__init__()
@@ -103,7 +137,9 @@ class TinyUNet(nn.Module):
         self.time_embed = nn.Linear(1, 64)
 
     def forward(self, x, t):
-        t_embed = F.relu(self.time_embed(t.unsqueeze(-1))).view(t_embed.size(0), t_embed.size(1), 1, 1)
+        t_embed = F.relu(self.time_embed(t.unsqueeze(-1)))
+        t_embed = t_embed.view(t_embed.size(0), t_embed.size(1), 1, 1)
+        
         x1 = F.relu(self.down1(x))
         x2 = F.relu(self.down2(x1))
         x_mid = F.relu(self.mid(x2)) + t_embed
@@ -119,8 +155,8 @@ class TinyDiffusion:
         self.alpha = 1 - self.beta
         self.alpha_cumprod = torch.cumprod(self.alpha, dim=0)
 
-    def train(self, images, epochs=10):
-        dataset = [torch.tensor(np.array(img.convert("RGB")).transpose(2, 0, 1), dtype=torch.float32) / 255.0 for img in images]
+    def train(self, images, epochs=50):
+        dataset = TinyDiffusionDataset(images)
         dataloader = DataLoader(dataset, batch_size=1, shuffle=True)
         optimizer = torch.optim.Adam(self.model.parameters(), lr=1e-4)
         device = torch.device("cpu")
@@ -155,126 +191,744 @@ class TinyDiffusion:
         x = torch.clamp(x * 255, 0, 255).byte()
         return Image.fromarray(x.squeeze(0).permute(1, 2, 0).cpu().numpy())
 
-# Utility Functions
+    def upscale(self, image, scale_factor=2):
+        img_tensor = torch.tensor(np.array(image.convert("RGB")).transpose(2, 0, 1), dtype=torch.float32).unsqueeze(0) / 255.0
+        upscaled = F.interpolate(img_tensor, scale_factor=scale_factor, mode='bilinear', align_corners=False)
+        upscaled = torch.clamp(upscaled * 255, 0, 255).byte()
+        return Image.fromarray(upscaled.squeeze(0).permute(1, 2, 0).cpu().numpy())
+
+class ModelBuilder:
+    def __init__(self):
+        self.config = None
+        self.model = None
+        self.tokenizer = None
+        self.sft_data = None
+        self.jokes = ["Why did the AI go to therapy? Too many layers to unpack! 😂", "Training complete! Time for a binary coffee break. ☕"]
+    def load_model(self, model_path: str, config: Optional[ModelConfig] = None):
+        with st.spinner(f"Loading {model_path}... ⏳"):
+            self.model = AutoModelForCausalLM.from_pretrained(model_path)
+            self.tokenizer = AutoTokenizer.from_pretrained(model_path)
+            if self.tokenizer.pad_token is None:
+                self.tokenizer.pad_token = self.tokenizer.eos_token
+            if config:
+                self.config = config
+            self.model.to("cuda" if torch.cuda.is_available() else "cpu")
+        st.success(f"Model loaded! 🎉 {random.choice(self.jokes)}")
+        return self
+    def fine_tune_sft(self, csv_path: str, epochs: int = 3, batch_size: int = 4):
+        self.sft_data = []
+        with open(csv_path, "r") as f:
+            reader = csv.DictReader(f)
+            for row in reader:
+                self.sft_data.append({"prompt": row["prompt"], "response": row["response"]})
+        dataset = SFTDataset(self.sft_data, self.tokenizer)
+        dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=True)
+        optimizer = torch.optim.AdamW(self.model.parameters(), lr=2e-5)
+        self.model.train()
+        device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        self.model.to(device)
+        for epoch in range(epochs):
+            with st.spinner(f"Training epoch {epoch + 1}/{epochs}... ⚙️"):
+                total_loss = 0
+                for batch in dataloader:
+                    optimizer.zero_grad()
+                    input_ids = batch["input_ids"].to(device)
+                    attention_mask = batch["attention_mask"].to(device)
+                    labels = batch["labels"].to(device)
+                    outputs = self.model(input_ids=input_ids, attention_mask=attention_mask, labels=labels)
+                    loss = outputs.loss
+                    loss.backward()
+                    optimizer.step()
+                    total_loss += loss.item()
+                st.write(f"Epoch {epoch + 1} completed. Average loss: {total_loss / len(dataloader):.4f}")
+        st.success(f"SFT Fine-tuning completed! 🎉 {random.choice(self.jokes)}")
+        return self
+    def save_model(self, path: str):
+        with st.spinner("Saving model... 💾"):
+            os.makedirs(os.path.dirname(path), exist_ok=True)
+            self.model.save_pretrained(path)
+            self.tokenizer.save_pretrained(path)
+        st.success(f"Model saved at {path}! ✅")
+    def evaluate(self, prompt: str, status_container=None):
+        self.model.eval()
+        if status_container:
+            status_container.write("Preparing to evaluate... 🧠")
+        try:
+            with torch.no_grad():
+                inputs = self.tokenizer(prompt, return_tensors="pt", max_length=128, truncation=True).to(self.model.device)
+                outputs = self.model.generate(**inputs, max_new_tokens=50, do_sample=True, top_p=0.95, temperature=0.7)
+                return self.tokenizer.decode(outputs[0], skip_special_tokens=True)
+        except Exception as e:
+            if status_container:
+                status_container.error(f"Oops! Something broke: {str(e)} 💥")
+            return f"Error: {str(e)}"
+
+class DiffusionBuilder:
+    def __init__(self):
+        self.config = None
+        self.pipeline = None
+    def load_model(self, model_path: str, config: Optional[DiffusionConfig] = None):
+        with st.spinner(f"Loading diffusion model {model_path}... ⏳"):
+            self.pipeline = StableDiffusionPipeline.from_pretrained(model_path, torch_dtype=torch.float32).to("cpu")
+            if config:
+                self.config = config
+        st.success(f"Diffusion model loaded! 🎨")
+        return self
+    def fine_tune_sft(self, images, texts, epochs=3):
+        dataset = DiffusionDataset(images, texts)
+        dataloader = DataLoader(dataset, batch_size=1, shuffle=True)
+        optimizer = torch.optim.AdamW(self.pipeline.unet.parameters(), lr=1e-5)
+        self.pipeline.unet.train()
+        for epoch in range(epochs):
+            with st.spinner(f"Training diffusion epoch {epoch + 1}/{epochs}... ⚙️"):
+                total_loss = 0
+                for batch in dataloader:
+                    optimizer.zero_grad()
+                    image = batch["image"][0].to(self.pipeline.device)
+                    text = batch["text"][0]
+                    latents = self.pipeline.vae.encode(torch.tensor(np.array(image)).permute(2, 0, 1).unsqueeze(0).float().to(self.pipeline.device)).latent_dist.sample()
+                    noise = torch.randn_like(latents)
+                    timesteps = torch.randint(0, self.pipeline.scheduler.num_train_timesteps, (latents.shape[0],), device=latents.device)
+                    noisy_latents = self.pipeline.scheduler.add_noise(latents, noise, timesteps)
+                    text_embeddings = self.pipeline.text_encoder(self.pipeline.tokenizer(text, return_tensors="pt").input_ids.to(self.pipeline.device))[0]
+                    pred_noise = self.pipeline.unet(noisy_latents, timesteps, encoder_hidden_states=text_embeddings).sample
+                    loss = torch.nn.functional.mse_loss(pred_noise, noise)
+                    loss.backward()
+                    optimizer.step()
+                    total_loss += loss.item()
+                st.write(f"Epoch {epoch + 1} completed. Average loss: {total_loss / len(dataloader):.4f}")
+        st.success("Diffusion SFT Fine-tuning completed! 🎨")
+        return self
+    def save_model(self, path: str):
+        with st.spinner("Saving diffusion model... 💾"):
+            os.makedirs(os.path.dirname(path), exist_ok=True)
+            self.pipeline.save_pretrained(path)
+        st.success(f"Diffusion model saved at {path}! ✅")
+    def generate(self, prompt: str):
+        return self.pipeline(prompt, num_inference_steps=20).images[0]
+
 def generate_filename(sequence, ext="png"):
     timestamp = time.strftime("%d%m%Y%H%M%S")
     return f"{sequence}_{timestamp}.{ext}"
 
-def predict_line_drawing(input_img, ver):
-    original_img = Image.open(input_img) if isinstance(input_img, str) else input_img
-    original_size = original_img.size
-    transform = transforms.Compose([
-        transforms.Resize(256, Image.BICUBIC),
-        transforms.ToTensor(),
-        transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
-    ])
-    input_tensor = transform(original_img).unsqueeze(0)
-    with torch.no_grad():
-        output = model2(input_tensor) if ver == 'Simple Lines' else model1(input_tensor)
-    output_img = transforms.ToPILImage()(output.squeeze().cpu().clamp(0, 1))
-    return output_img.resize(original_size, Image.BICUBIC)
-
-async def process_ocr(image):
+def pdf_url_to_filename(url):
+    safe_name = re.sub(r'[<>:"/\\|?*]', '_', url)
+    return f"{safe_name}.pdf"
+
+def get_download_link(file_path, mime_type="application/pdf", label="Download"):
+    with open(file_path, 'rb') as f:
+        data = f.read()
+    b64 = base64.b64encode(data).decode()
+    return f'<a href="data:{mime_type};base64,{b64}" download="{os.path.basename(file_path)}">{label}</a>'
+
+def zip_directory(directory_path, zip_path):
+    with zipfile.ZipFile(zip_path, 'w', zipfile.ZIP_DEFLATED) as zipf:
+        for root, _, files in os.walk(directory_path):
+            for file in files:
+                zipf.write(os.path.join(root, file), os.path.relpath(os.path.join(root, file), os.path.dirname(directory_path)))
+
+def get_model_files(model_type="causal_lm"):
+    path = "models/*" if model_type == "causal_lm" else "diffusion_models/*"
+    return [d for d in glob.glob(path) if os.path.isdir(d)]
+
+def get_gallery_files(file_types=["png", "pdf"]):
+    return sorted(list(set([f for ext in file_types for f in glob.glob(f"*.{ext}")])))  # Deduplicate files
+
+def get_pdf_files():
+    return sorted(glob.glob("*.pdf"))
+
+def download_pdf(url, output_path):
+    try:
+        response = requests.get(url, stream=True, timeout=10)
+        if response.status_code == 200:
+            with open(output_path, "wb") as f:
+                for chunk in response.iter_content(chunk_size=8192):
+                    f.write(chunk)
+            return True
+    except requests.RequestException as e:
+        logger.error(f"Failed to download {url}: {e}")
+    return False
+
+async def process_pdf_snapshot(pdf_path, mode="single"):
+    start_time = time.time()
+    status = st.empty()
+    status.text(f"Processing PDF Snapshot ({mode})... (0s)")
+    try:
+        doc = fitz.open(pdf_path)
+        output_files = []
+        if mode == "single":
+            page = doc[0]
+            pix = page.get_pixmap(matrix=fitz.Matrix(2.0, 2.0))
+            output_file = generate_filename("single", "png")
+            pix.save(output_file)
+            output_files.append(output_file)
+        elif mode == "twopage":
+            for i in range(min(2, len(doc))):
+                page = doc[i]
+                pix = page.get_pixmap(matrix=fitz.Matrix(2.0, 2.0))
+                output_file = generate_filename(f"twopage_{i}", "png")
+                pix.save(output_file)
+                output_files.append(output_file)
+        elif mode == "allpages":
+            for i in range(len(doc)):
+                page = doc[i]
+                pix = page.get_pixmap(matrix=fitz.Matrix(2.0, 2.0))
+                output_file = generate_filename(f"page_{i}", "png")
+                pix.save(output_file)
+                output_files.append(output_file)
+        doc.close()
+        elapsed = int(time.time() - start_time)
+        status.text(f"PDF Snapshot ({mode}) completed in {elapsed}s!")
+        update_gallery()
+        return output_files
+    except Exception as e:
+        status.error(f"Failed to process PDF: {str(e)}")
+        return []
+
+async def process_ocr(image, output_file):
+    start_time = time.time()
+    status = st.empty()
+    status.text("Processing GOT-OCR2_0... (0s)")
     tokenizer = AutoTokenizer.from_pretrained("ucaslcl/GOT-OCR2_0", trust_remote_code=True)
     model = AutoModel.from_pretrained("ucaslcl/GOT-OCR2_0", trust_remote_code=True, torch_dtype=torch.float32).to("cpu").eval()
     result = model.chat(tokenizer, image, ocr_type='ocr')
-    output_file = generate_filename("ocr_output", "txt")
+    elapsed = int(time.time() - start_time)
+    status.text(f"GOT-OCR2_0 completed in {elapsed}s!")
     async with aiofiles.open(output_file, "w") as f:
         await f.write(result)
-    return result, output_file
+    update_gallery()
+    return result
 
-async def process_diffusion(images):
+async def process_image_gen(prompt, output_file):
+    start_time = time.time()
+    status = st.empty()
+    status.text("Processing Image Gen... (0s)")
+    pipeline = StableDiffusionPipeline.from_pretrained("OFA-Sys/small-stable-diffusion-v0", torch_dtype=torch.float32).to("cpu")
+    gen_image = pipeline(prompt, num_inference_steps=20).images[0]
+    elapsed = int(time.time() - start_time)
+    status.text(f"Image Gen completed in {elapsed}s!")
+    gen_image.save(output_file)
+    update_gallery()
+    return gen_image
+
+async def process_custom_diffusion(images, output_file, model_name):
+    start_time = time.time()
+    status = st.empty()
+    status.text(f"Training {model_name}... (0s)")
     unet = TinyUNet()
     diffusion = TinyDiffusion(unet)
     diffusion.train(images)
     gen_image = diffusion.generate()
-    output_file = generate_filename("diffusion_output", "png")
-    gen_image.save(output_file)
-    return gen_image, output_file
-
-def download_pdf(url):
-    output_path = f"pdf_{int(time.time())}.pdf"
-    response = requests.get(url, stream=True, timeout=10)
-    if response.status_code == 200:
-        with open(output_path, "wb") as f:
-            for chunk in response.iter_content(chunk_size=8192):
-                f.write(chunk)
-        return output_path
-    return None
-
-# Gradio Blocks UI
-with gr.Blocks(title="Mystical AI Vision Studio 🌌", css="""
-    .gr-button {background-color: #4CAF50; color: white;}
-    .gr-tab {border: 2px solid #2196F3; border-radius: 5px;}
-    #gallery img {border: 1px solid #ddd; border-radius: 4px;}
-""") as demo:
-    gr.Markdown("<h1 style='text-align: center; color: #2196F3;'>Mystical AI Vision Studio 🌌</h1>")
-    gr.Markdown("<p style='text-align: center;'>Transform images into line drawings, extract text with OCR, and craft unique art with diffusion!</p>")
-
-    with gr.Tab("Image to Line Drawings 🎨"):
-        with gr.Row():
-            with gr.Column():
-                img_input = gr.Image(type="pil", label="Upload Image")
-                version = gr.Radio(['Complex Lines', 'Simple Lines'], label='Style', value='Simple Lines')
-                submit_btn = gr.Button("Generate Line Drawing")
-            with gr.Column():
-                line_output = gr.Image(type="pil", label="Line Drawing")
-                download_btn = gr.Button("Download Output")
-        submit_btn.click(predict_line_drawing, inputs=[img_input, version], outputs=line_output)
-        download_btn.click(lambda x: gr.File(x, label="Download Line Drawing"), inputs=line_output, outputs=None)
-
-    with gr.Tab("OCR Vision 🔍"):
-        with gr.Row():
-            with gr.Column():
-                ocr_input = gr.Image(type="pil", label="Upload Image or PDF Snapshot")
-                ocr_btn = gr.Button("Extract Text")
-            with gr.Column():
-                ocr_text = gr.Textbox(label="Extracted Text", interactive=False)
-                ocr_file = gr.File(label="Download OCR Result")
-        async def run_ocr(img):
-            result, file_path = await process_ocr(img)
-            return result, file_path
-        ocr_btn.click(run_ocr, inputs=ocr_input, outputs=[ocr_text, ocr_file])
-
-    with gr.Tab("Custom Diffusion 🎨🤓"):
-        with gr.Row():
-            with gr.Column():
-                diffusion_input = gr.File(label="Upload Images for Training", multiple=True)
-                diffusion_btn = gr.Button("Train & Generate")
-            with gr.Column():
-                diffusion_output = gr.Image(type="pil", label="Generated Art")
-                diffusion_file = gr.File(label="Download Art")
-        async def run_diffusion(files):
-            images = [Image.open(BytesIO(f.read())) for f in files]
-            img, file_path = await process_diffusion(images)
-            return img, file_path
-        diffusion_btn.click(run_diffusion, inputs=diffusion_input, outputs=[diffusion_output, diffusion_file])
-
-    with gr.Tab("PDF Downloader 📥"):
-        with gr.Row():
-            pdf_url = gr.Textbox(label="Enter PDF URL")
-            pdf_btn = gr.Button("Download PDF")
-            pdf_output = gr.File(label="Downloaded PDF")
-        pdf_btn.click(download_pdf, inputs=pdf_url, outputs=pdf_output)
-
-    with gr.Tab("Gallery 📸"):
-        gallery = gr.Gallery(label="Processed Outputs", elem_id="gallery")
-        def update_gallery():
-            files = [f for f in os.listdir('.') if f.endswith(('.png', '.txt', '.pdf'))]
-            return [f for f in files]
-        gr.Button("Refresh Gallery").click(update_gallery, outputs=gallery)
-
-    # JavaScript for dynamic UI enhancements
-    gr.HTML("""
-    <script>
-        document.addEventListener('DOMContentLoaded', () => {
-            const buttons = document.querySelectorAll('.gr-button');
-            buttons.forEach(btn => {
-                btn.addEventListener('mouseover', () => btn.style.backgroundColor = '#45a049');
-                btn.addEventListener('mouseout', () => btn.style.backgroundColor = '#4CAF50');
-            });
-        });
-    </script>
-    """)
-
-demo.launch()
+    upscaled_image = diffusion.upscale(gen_image, scale_factor=2)
+    elapsed = int(time.time() - start_time)
+    status.text(f"{model_name} completed in {elapsed}s!")
+    upscaled_image.save(output_file)
+    update_gallery()
+    return upscaled_image
+
+def mock_search(query: str) -> str:
+    if "superhero" in query.lower():
+        return "Latest trends: Gold-plated Batman statues, VR superhero battles."
+    return "No relevant results found."
+
+def mock_duckduckgo_search(query: str) -> str:
+    if "superhero party trends" in query.lower():
+        return """
+        Latest trends for 2025: 
+        - Luxury decorations: Gold-plated Batman statues, holographic Avengers displays.
+        - Entertainment: Live stunt shows with Iron Man suits, VR superhero battles.
+        - Catering: Gourmet kryptonite-green cocktails, Thor’s hammer-shaped appetizers.
+        """
+    return "No relevant results found."
+
+class PartyPlannerAgent:
+    def __init__(self, model, tokenizer):
+        self.model = model
+        self.tokenizer = tokenizer
+        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        self.model.to(self.device)
+    def generate(self, prompt: str) -> str:
+        self.model.eval()
+        with torch.no_grad():
+            inputs = self.tokenizer(prompt, return_tensors="pt", max_length=128, truncation=True).to(self.device)
+            outputs = self.model.generate(**inputs, max_new_tokens=100, do_sample=True, top_p=0.95, temperature=0.7)
+            return self.tokenizer.decode(outputs[0], skip_special_tokens=True)
+    def plan_party(self, task: str) -> pd.DataFrame:
+        search_result = mock_duckduckgo_search("latest superhero party trends")
+        prompt = f"Given this context: '{search_result}'\n{task}"
+        plan_text = self.generate(prompt)
+        locations = {
+            "Wayne Manor": (42.3601, -71.0589),
+            "New York": (40.7128, -74.0060),
+            "Los Angeles": (34.0522, -118.2437),
+            "London": (51.5074, -0.1278)
+        }
+        wayne_coords = locations["Wayne Manor"]
+        travel_times = {loc: calculate_cargo_travel_time(coords, wayne_coords) for loc, coords in locations.items() if loc != "Wayne Manor"}
+        catchphrases = ["To the Batmobile!", "Avengers, assemble!", "I am Iron Man!", "By the power of Grayskull!"]
+        data = [
+            {"Location": "New York", "Travel Time (hrs)": travel_times["New York"], "Luxury Idea": "Gold-plated Batman statues", "Catchphrase": random.choice(catchphrases)},
+            {"Location": "Los Angeles", "Travel Time (hrs)": travel_times["Los Angeles"], "Luxury Idea": "Holographic Avengers displays", "Catchphrase": random.choice(catchphrases)},
+            {"Location": "London", "Travel Time (hrs)": travel_times["London"], "Luxury Idea": "Live stunt shows with Iron Man suits", "Catchphrase": random.choice(catchphrases)},
+            {"Location": "Wayne Manor", "Travel Time (hrs)": 0.0, "Luxury Idea": "VR superhero battles", "Catchphrase": random.choice(catchphrases)},
+            {"Location": "New York", "Travel Time (hrs)": travel_times["New York"], "Luxury Idea": "Gourmet kryptonite-green cocktails", "Catchphrase": random.choice(catchphrases)},
+            {"Location": "Los Angeles", "Travel Time (hrs)": travel_times["Los Angeles"], "Luxury Idea": "Thor’s hammer-shaped appetizers", "Catchphrase": random.choice(catchphrases)},
+        ]
+        return pd.DataFrame(data)
+
+class CVPartyPlannerAgent:
+    def __init__(self, pipeline):
+        self.pipeline = pipeline
+    def generate(self, prompt: str) -> Image.Image:
+        return self.pipeline(prompt, num_inference_steps=20).images[0]
+    def plan_party(self, task: str) -> pd.DataFrame:
+        search_result = mock_search("superhero party trends")
+        prompt = f"Given this context: '{search_result}'\n{task}"
+        data = [
+            {"Theme": "Batman", "Image Idea": "Gold-plated Batman statue"},
+            {"Theme": "Avengers", "Image Idea": "VR superhero battle scene"}
+        ]
+        return pd.DataFrame(data)
+
+def calculate_cargo_travel_time(origin_coords: Tuple[float, float], destination_coords: Tuple[float, float], cruising_speed_kmh: float = 750.0) -> float:
+    def to_radians(degrees: float) -> float:
+        return degrees * (math.pi / 180)
+    lat1, lon1 = map(to_radians, origin_coords)
+    lat2, lon2 = map(to_radians, destination_coords)
+    EARTH_RADIUS_KM = 6371.0
+    dlon = lon2 - lon1
+    dlat = lat2 - lat1
+    a = (math.sin(dlat / 2) ** 2 + math.cos(lat1) * math.cos(lat2) * math.sin(dlon / 2) ** 2)
+    c = 2 * math.asin(math.sqrt(a))
+    distance = EARTH_RADIUS_KM * c
+    actual_distance = distance * 1.1
+    flight_time = (actual_distance / cruising_speed_kmh) + 1.0
+    return round(flight_time, 2)
+
+st.title("AI Vision & SFT Titans 🚀")
+
+st.sidebar.header("Captured Files 📜")
+cols = st.sidebar.columns(2)
+with cols[0]:
+    if st.button("Zip All 🤐"):
+        zip_path = f"all_assets_{int(time.time())}.zip"
+        with zipfile.ZipFile(zip_path, 'w', zipfile.ZIP_DEFLATED) as zipf:
+            for file in get_gallery_files():
+                zipf.write(file, os.path.basename(file))
+        st.sidebar.markdown(get_download_link(zip_path, "application/zip", "Download All Assets"), unsafe_allow_html=True)
+with cols[1]:
+    if st.button("Zap All! 🗑️"):
+        for file in get_gallery_files():
+            os.remove(file)
+        st.session_state['asset_checkboxes'].clear()
+        st.session_state['downloaded_pdfs'].clear()
+        st.sidebar.success("All assets vaporized! 💨")
+        st.rerun()
+
+gallery_size = st.sidebar.slider("Gallery Size", 1, 10, 2)
+def update_gallery():
+    all_files = get_gallery_files()
+    if all_files:
+        st.sidebar.subheader("Asset Gallery 📸📖")
+        cols = st.sidebar.columns(2)
+        for idx, file in enumerate(all_files[:gallery_size * 2]):
+            with cols[idx % 2]:
+                st.session_state['unique_counter'] += 1  # Increment counter for uniqueness
+                unique_id = st.session_state['unique_counter']
+                if file.endswith('.png'):
+                    st.image(Image.open(file), caption=os.path.basename(file), use_container_width=True)
+                else:
+                    doc = fitz.open(file)
+                    pix = doc[0].get_pixmap(matrix=fitz.Matrix(0.5, 0.5))
+                    img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
+                    st.image(img, caption=os.path.basename(file), use_container_width=True)
+                    doc.close()
+                checkbox_key = f"asset_{file}_{unique_id}"  # Unique key with counter
+                st.session_state['asset_checkboxes'][file] = st.checkbox(
+                    "Use for SFT/Input", 
+                    value=st.session_state['asset_checkboxes'].get(file, False), 
+                    key=checkbox_key
+                )
+                mime_type = "image/png" if file.endswith('.png') else "application/pdf"
+                st.markdown(get_download_link(file, mime_type, "Snag It! 📥"), unsafe_allow_html=True)
+                if st.button("Zap It! 🗑️", key=f"delete_{file}_{unique_id}"):  # Unique key with counter
+                    os.remove(file)
+                    if file in st.session_state['asset_checkboxes']:
+                        del st.session_state['asset_checkboxes'][file]
+                    if file.endswith('.pdf'):
+                        url_key = next((k for k, v in st.session_state['downloaded_pdfs'].items() if v == file), None)
+                        if url_key:
+                            del st.session_state['downloaded_pdfs'][url_key]
+                    st.sidebar.success(f"Asset {os.path.basename(file)} vaporized! 💨")
+                    st.rerun()
+update_gallery()
+
+st.sidebar.subheader("Model Management 🗂️")
+model_type = st.sidebar.selectbox("Model Type", ["Causal LM", "Diffusion"], key="sidebar_model_type")
+model_dirs = get_model_files(model_type)
+selected_model = st.sidebar.selectbox("Select Saved Model", ["None"] + model_dirs, key="sidebar_model_select")
+if selected_model != "None" and st.sidebar.button("Load Model 📂"):
+    builder = ModelBuilder() if model_type == "Causal LM" else DiffusionBuilder()
+    config = (ModelConfig if model_type == "Causal LM" else DiffusionConfig)(name=os.path.basename(selected_model), base_model="unknown", size="small")
+    builder.load_model(selected_model, config)
+    st.session_state['builder'] = builder
+    st.session_state['model_loaded'] = True
+    st.rerun()
+
+st.sidebar.subheader("Action Logs 📜")
+log_container = st.sidebar.empty()
+with log_container:
+    for record in log_records:
+        st.write(f"{record.asctime} - {record.levelname} - {record.message}")
+
+st.sidebar.subheader("History 📜")
+history_container = st.sidebar.empty()
+with history_container:
+    for entry in st.session_state['history'][-gallery_size * 2:]:
+        st.write(entry)
+
+tab1, tab2, tab3, tab4, tab5, tab6, tab7, tab8, tab9 = st.tabs([
+    "Camera Snap 📷", "Download PDFs 📥", "Build Titan 🌱", "Fine-Tune Titan 🔧", 
+    "Test Titan 🧪", "Agentic RAG Party 🌐", "Test OCR 🔍", "Test Image Gen 🎨", "Custom Diffusion 🎨🤓"
+])
+
+with tab1:
+    st.header("Camera Snap 📷")
+    st.subheader("Single Capture")
+    cols = st.columns(2)
+    with cols[0]:
+        cam0_img = st.camera_input("Take a picture - Cam 0", key="cam0")
+        if cam0_img:
+            filename = generate_filename("cam0")
+            with open(filename, "wb") as f:
+                f.write(cam0_img.getvalue())
+            entry = f"Snapshot from Cam 0: {filename}"
+            if entry not in st.session_state['history']:
+                st.session_state['history'] = [e for e in st.session_state['history'] if not e.startswith("Snapshot from Cam 0:")] + [entry]
+            st.image(Image.open(filename), caption="Camera 0", use_container_width=True)
+            logger.info(f"Saved snapshot from Camera 0: {filename}")
+            update_gallery()
+    with cols[1]:
+        cam1_img = st.camera_input("Take a picture - Cam 1", key="cam1")
+        if cam1_img:
+            filename = generate_filename("cam1")
+            with open(filename, "wb") as f:
+                f.write(cam1_img.getvalue())
+            entry = f"Snapshot from Cam 1: {filename}"
+            if entry not in st.session_state['history']:
+                st.session_state['history'] = [e for e in st.session_state['history'] if not e.startswith("Snapshot from Cam 1:")] + [entry]
+            st.image(Image.open(filename), caption="Camera 1", use_container_width=True)
+            logger.info(f"Saved snapshot from Camera 1: {filename}")
+            update_gallery()
+
+with tab2:
+    st.header("Download PDFs 📥")
+    if st.button("Examples 📚"):
+        example_urls = [
+            "https://arxiv.org/pdf/2308.03892",
+            "https://arxiv.org/pdf/1912.01703",
+            "https://arxiv.org/pdf/2408.11039",
+            "https://arxiv.org/pdf/2109.10282",
+            "https://arxiv.org/pdf/2112.10752",
+            "https://arxiv.org/pdf/2308.11236",
+            "https://arxiv.org/pdf/1706.03762",
+            "https://arxiv.org/pdf/2006.11239",
+            "https://arxiv.org/pdf/2305.11207",
+            "https://arxiv.org/pdf/2106.09685",
+            "https://arxiv.org/pdf/2005.11401",
+            "https://arxiv.org/pdf/2106.10504"
+        ]
+        st.session_state['pdf_urls'] = "\n".join(example_urls)
+    
+    url_input = st.text_area("Enter PDF URLs (one per line)", value=st.session_state.get('pdf_urls', ""), height=200)
+    if st.button("Robo-Download 🤖"):
+        urls = url_input.strip().split("\n")
+        progress_bar = st.progress(0)
+        status_text = st.empty()
+        total_urls = len(urls)
+        existing_pdfs = get_pdf_files()
+        for idx, url in enumerate(urls):
+            if url:
+                output_path = pdf_url_to_filename(url)
+                status_text.text(f"Fetching {idx + 1}/{total_urls}: {os.path.basename(output_path)}...")
+                if output_path not in existing_pdfs:
+                    if download_pdf(url, output_path):
+                        st.session_state['downloaded_pdfs'][url] = output_path
+                        logger.info(f"Downloaded PDF from {url} to {output_path}")
+                        entry = f"Downloaded PDF: {output_path}"
+                        if entry not in st.session_state['history']:
+                            st.session_state['history'].append(entry)
+                    else:
+                        st.error(f"Failed to nab {url} 😿")
+                else:
+                    st.info(f"Already got {os.path.basename(output_path)}! Skipping... 🐾")
+                    st.session_state['downloaded_pdfs'][url] = output_path
+                progress_bar.progress((idx + 1) / total_urls)
+        status_text.text("Robo-Download complete! 🚀")
+        update_gallery()
+
+    mode = st.selectbox("Snapshot Mode", ["Single Page (High-Res)", "Two Pages (High-Res)", "All Pages (High-Res)"], key="download_mode")
+    if st.button("Snapshot Selected 📸"):
+        selected_pdfs = [path for path in get_gallery_files() if path.endswith('.pdf') and st.session_state['asset_checkboxes'].get(path, False)]
+        if selected_pdfs:
+            for pdf_path in selected_pdfs:
+                mode_key = {"Single Page (High-Res)": "single", "Two Pages (High-Res)": "twopage", "All Pages (High-Res)": "allpages"}[mode]
+                snapshots = asyncio.run(process_pdf_snapshot(pdf_path, mode_key))
+                for snapshot in snapshots:
+                    st.image(Image.open(snapshot), caption=snapshot, use_container_width=True)
+        else:
+            st.warning("No PDFs selected for snapshotting! Check some boxes in the sidebar gallery.")
+
+with tab3:
+    st.header("Build Titan 🌱")
+    model_type = st.selectbox("Model Type", ["Causal LM", "Diffusion"], key="build_type")
+    base_model = st.selectbox("Select Tiny Model", 
+        ["HuggingFaceTB/SmolLM-135M", "Qwen/Qwen1.5-0.5B-Chat"] if model_type == "Causal LM" else 
+        ["OFA-Sys/small-stable-diffusion-v0", "stabilityai/stable-diffusion-2-base"])
+    model_name = st.text_input("Model Name", f"tiny-titan-{int(time.time())}")
+    domain = st.text_input("Target Domain", "general")
+    if st.button("Download Model ⬇️"):
+        config = (ModelConfig if model_type == "Causal LM" else DiffusionConfig)(name=model_name, base_model=base_model, size="small", domain=domain)
+        builder = ModelBuilder() if model_type == "Causal LM" else DiffusionBuilder()
+        builder.load_model(base_model, config)
+        builder.save_model(config.model_path)
+        st.session_state['builder'] = builder
+        st.session_state['model_loaded'] = True
+        entry = f"Built {model_type} model: {model_name}"
+        if entry not in st.session_state['history']:
+            st.session_state['history'].append(entry)
+        st.success(f"Model downloaded and saved to {config.model_path}! 🎉")
+        st.rerun()
+
+with tab4:
+    st.header("Fine-Tune Titan 🔧")
+    if 'builder' not in st.session_state or not st.session_state.get('model_loaded', False):
+        st.warning("Please build or load a Titan first! ⚠️")
+    else:
+        if isinstance(st.session_state['builder'], ModelBuilder):
+            if st.button("Generate Sample CSV 📝"):
+                sample_data = [
+                    {"prompt": "What is AI?", "response": "AI is artificial intelligence, simulating human smarts in machines."},
+                    {"prompt": "Explain machine learning", "response": "Machine learning is AI’s gym where models bulk up on data."},
+                ]
+                csv_path = f"sft_data_{int(time.time())}.csv"
+                with open(csv_path, "w", newline="") as f:
+                    writer = csv.DictWriter(f, fieldnames=["prompt", "response"])
+                    writer.writeheader()
+                    writer.writerows(sample_data)
+                st.markdown(get_download_link(csv_path, "text/csv", "Download Sample CSV"), unsafe_allow_html=True)
+                st.success(f"Sample CSV generated as {csv_path}! ✅")
+
+            uploaded_csv = st.file_uploader("Upload CSV for SFT", type="csv")
+            if uploaded_csv and st.button("Fine-Tune with Uploaded CSV 🔄"):
+                csv_path = f"uploaded_sft_data_{int(time.time())}.csv"
+                with open(csv_path, "wb") as f:
+                    f.write(uploaded_csv.read())
+                new_model_name = f"{st.session_state['builder'].config.name}-sft-{int(time.time())}"
+                new_config = ModelConfig(name=new_model_name, base_model=st.session_state['builder'].config.base_model, size="small", domain=st.session_state['builder'].config.domain)
+                st.session_state['builder'].config = new_config
+                st.session_state['builder'].fine_tune_sft(csv_path)
+                st.session_state['builder'].save_model(new_config.model_path)
+                zip_path = f"{new_config.model_path}.zip"
+                zip_directory(new_config.model_path, zip_path)
+                entry = f"Fine-tuned Causal LM: {new_model_name}"
+                if entry not in st.session_state['history']:
+                    st.session_state['history'].append(entry)
+                st.markdown(get_download_link(zip_path, "application/zip", "Download Fine-Tuned Titan"), unsafe_allow_html=True)
+                st.rerun()
+        elif isinstance(st.session_state['builder'], DiffusionBuilder):
+            selected_files = [path for path in get_gallery_files() if st.session_state['asset_checkboxes'].get(path, False)]
+            if len(selected_files) >= 2:
+                demo_data = [{"image": file, "text": f"Asset {os.path.basename(file).split('.')[0]}"} for file in selected_files]
+                edited_data = st.data_editor(pd.DataFrame(demo_data), num_rows="dynamic")
+                if st.button("Fine-Tune with Dataset 🔄"):
+                    images = [Image.open(row["image"]) if row["image"].endswith('.png') else Image.frombytes("RGB", fitz.open(row["image"])[0].get_pixmap(matrix=fitz.Matrix(2.0, 2.0)).size, fitz.open(row["image"])[0].get_pixmap(matrix=fitz.Matrix(2.0, 2.0)).samples) for _, row in edited_data.iterrows()]
+                    texts = [row["text"] for _, row in edited_data.iterrows()]
+                    new_model_name = f"{st.session_state['builder'].config.name}-sft-{int(time.time())}"
+                    new_config = DiffusionConfig(name=new_model_name, base_model=st.session_state['builder'].config.base_model, size="small", domain=st.session_state['builder'].config.domain)
+                    st.session_state['builder'].config = new_config
+                    st.session_state['builder'].fine_tune_sft(images, texts)
+                    st.session_state['builder'].save_model(new_config.model_path)
+                    zip_path = f"{new_config.model_path}.zip"
+                    zip_directory(new_config.model_path, zip_path)
+                    entry = f"Fine-tuned Diffusion: {new_model_name}"
+                    if entry not in st.session_state['history']:
+                        st.session_state['history'].append(entry)
+                    st.markdown(get_download_link(zip_path, "application/zip", "Download Fine-Tuned Diffusion Model"), unsafe_allow_html=True)
+                csv_path = f"sft_dataset_{int(time.time())}.csv"
+                with open(csv_path, "w", newline="") as f:
+                    writer = csv.writer(f)
+                    writer.writerow(["image", "text"])
+                    for _, row in edited_data.iterrows():
+                        writer.writerow([row["image"], row["text"]])
+                st.markdown(get_download_link(csv_path, "text/csv", "Download SFT Dataset CSV"), unsafe_allow_html=True)
+
+with tab5:
+    st.header("Test Titan 🧪")
+    if 'builder' not in st.session_state or not st.session_state.get('model_loaded', False):
+        st.warning("Please build or load a Titan first! ⚠️")
+    else:
+        if isinstance(st.session_state['builder'], ModelBuilder):
+            if st.session_state['builder'].sft_data:
+                st.write("Testing with SFT Data:")
+                for item in st.session_state['builder'].sft_data[:3]:
+                    prompt = item["prompt"]
+                    expected = item["response"]
+                    status_container = st.empty()
+                    generated = st.session_state['builder'].evaluate(prompt, status_container)
+                    st.write(f"**Prompt**: {prompt}")
+                    st.write(f"**Expected**: {expected}")
+                    st.write(f"**Generated**: {generated}")
+                    st.write("---")
+                    status_container.empty()
+            test_prompt = st.text_area("Enter Test Prompt", "What is AI?")
+            if st.button("Run Test ▶️"):
+                status_container = st.empty()
+                result = st.session_state['builder'].evaluate(test_prompt, status_container)
+                entry = f"Causal LM Test: {test_prompt} -> {result}"
+                if entry not in st.session_state['history']:
+                    st.session_state['history'].append(entry)
+                st.write(f"**Generated Response**: {result}")
+                status_container.empty()
+        elif isinstance(st.session_state['builder'], DiffusionBuilder):
+            test_prompt = st.text_area("Enter Test Prompt", "Neon Batman")
+            if st.button("Run Test ▶️"):
+                image = st.session_state['builder'].generate(test_prompt)
+                output_file = generate_filename("diffusion_test", "png")
+                image.save(output_file)
+                entry = f"Diffusion Test: {test_prompt} -> {output_file}"
+                if entry not in st.session_state['history']:
+                    st.session_state['history'].append(entry)
+                st.image(image, caption="Generated Image")
+                update_gallery()
+
+with tab6:
+    st.header("Agentic RAG Party 🌐")
+    if 'builder' not in st.session_state or not st.session_state.get('model_loaded', False):
+        st.warning("Please build or load a Titan first! ⚠️")
+    else:
+        if isinstance(st.session_state['builder'], ModelBuilder):
+            if st.button("Run NLP RAG Demo 🎉"):
+                agent = PartyPlannerAgent(st.session_state['builder'].model, st.session_state['builder'].tokenizer)
+                task = "Plan a luxury superhero-themed party at Wayne Manor."
+                plan_df = agent.plan_party(task)
+                entry = f"NLP RAG Demo: Planned party at Wayne Manor"
+                if entry not in st.session_state['history']:
+                    st.session_state['history'].append(entry)
+                st.dataframe(plan_df)
+        elif isinstance(st.session_state['builder'], DiffusionBuilder):
+            if st.button("Run CV RAG Demo 🎉"):
+                agent = CVPartyPlannerAgent(st.session_state['builder'].pipeline)
+                task = "Generate images for a luxury superhero-themed party."
+                plan_df = agent.plan_party(task)
+                entry = f"CV RAG Demo: Generated party images"
+                if entry not in st.session_state['history']:
+                    st.session_state['history'].append(entry)
+                st.dataframe(plan_df)
+                for _, row in plan_df.iterrows():
+                    image = agent.generate(row["Image Idea"])
+                    output_file = generate_filename(f"cv_rag_{row['Theme'].lower()}", "png")
+                    image.save(output_file)
+                    st.image(image, caption=f"{row['Theme']} - {row['Image Idea']}")
+                update_gallery()
+
+with tab7:
+    st.header("Test OCR 🔍")
+    all_files = [path for path in get_gallery_files() if st.session_state['asset_checkboxes'].get(path, False)]
+    if all_files:
+        selected_file = st.selectbox("Select Image or PDF", all_files, key="ocr_select")
+        if selected_file:
+            if selected_file.endswith('.png'):
+                image = Image.open(selected_file)
+            else:
+                doc = fitz.open(selected_file)
+                pix = doc[0].get_pixmap(matrix=fitz.Matrix(2.0, 2.0))
+                image = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
+                doc.close()
+            st.image(image, caption="Input Image", use_container_width=True)
+            if st.button("Run OCR 🚀", key="ocr_run"):
+                output_file = generate_filename("ocr_output", "txt")
+                st.session_state['processing']['ocr'] = True
+                result = asyncio.run(process_ocr(image, output_file))
+                entry = f"OCR Test: {selected_file} -> {output_file}"
+                if entry not in st.session_state['history']:
+                    st.session_state['history'].append(entry)
+                st.text_area("OCR Result", result, height=200, key="ocr_result")
+                st.success(f"OCR output saved to {output_file}")
+                st.session_state['processing']['ocr'] = False
+    else:
+        st.warning("No images or PDFs selected yet. Check some boxes in the sidebar gallery!")
+
+with tab8:
+    st.header("Test Image Gen 🎨")
+    all_files = [path for path in get_gallery_files() if st.session_state['asset_checkboxes'].get(path, False)]
+    if all_files:
+        selected_file = st.selectbox("Select Image or PDF", all_files, key="gen_select")
+        if selected_file:
+            if selected_file.endswith('.png'):
+                image = Image.open(selected_file)
+            else:
+                doc = fitz.open(selected_file)
+                pix = doc[0].get_pixmap(matrix=fitz.Matrix(2.0, 2.0))
+                image = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
+                doc.close()
+            st.image(image, caption="Reference Image", use_container_width=True)
+            prompt = st.text_area("Prompt", "Generate a similar superhero image", key="gen_prompt")
+            if st.button("Run Image Gen 🚀", key="gen_run"):
+                output_file = generate_filename("gen_output", "png")
+                st.session_state['processing']['gen'] = True
+                result = asyncio.run(process_image_gen(prompt, output_file))
+                entry = f"Image Gen Test: {prompt} -> {output_file}"
+                if entry not in st.session_state['history']:
+                    st.session_state['history'].append(entry)
+                st.image(result, caption="Generated Image", use_container_width=True)
+                st.success(f"Image saved to {output_file}")
+                st.session_state['processing']['gen'] = False
+    else:
+        st.warning("No images or PDFs selected yet. Check some boxes in the sidebar gallery!")
+
+with tab9:
+    st.header("Custom Diffusion 🎨🤓")
+    st.write("Unleash your inner artist with our tiny diffusion models!")
+    all_files = [path for path in get_gallery_files() if st.session_state['asset_checkboxes'].get(path, False)]
+    if all_files:
+        st.subheader("Select Images or PDFs to Train")
+        selected_files = st.multiselect("Pick Images or PDFs", all_files, key="diffusion_select")
+        images = []
+        for file in selected_files:
+            if file.endswith('.png'):
+                images.append(Image.open(file))
+            else:
+                doc = fitz.open(file)
+                pix = doc[0].get_pixmap(matrix=fitz.Matrix(2.0, 2.0))
+                images.append(Image.frombytes("RGB", [pix.width, pix.height], pix.samples))
+                doc.close()
+        
+        model_options = [
+            ("PixelTickler 🎨✨", "OFA-Sys/small-stable-diffusion-v0"),
+            ("DreamWeaver 🌙🖌️", "stabilityai/stable-diffusion-2-base"),
+            ("TinyArtBot 🤖🖼️", "custom")
+        ]
+        model_choice = st.selectbox("Choose Your Diffusion Dynamo", [opt[0] for opt in model_options], key="diffusion_model")
+        model_name = next(opt[1] for opt in model_options if opt[0] == model_choice)
+
+        if st.button("Train & Generate 🚀", key="diffusion_run"):
+            output_file = generate_filename("custom_diffusion", "png")
+            st.session_state['processing']['diffusion'] = True
+            if model_name == "custom":
+                result = asyncio.run(process_custom_diffusion(images, output_file, model_choice))
+            else:
+                builder = DiffusionBuilder()
+                builder.load_model(model_name)
+                result = builder.generate("A superhero scene inspired by captured images")
+                result.save(output_file)
+            entry = f"Custom Diffusion: {model_choice} -> {output_file}"
+            if entry not in st.session_state['history']:
+                st.session_state['history'].append(entry)
+            st.image(result, caption=f"{model_choice} Masterpiece", use_container_width=True)
+            st.success(f"Image saved to {output_file}")
+            st.session_state['processing']['diffusion'] = False
+    else:
+        st.warning("No images or PDFs selected yet. Check some boxes in the sidebar gallery!")
+
+update_gallery()