Update index.html

index.html

@@ -320,7 +320,7 @@
       </div>
     </div>
 
-    <div class="note">Generated images (scroll this pane). New images appear at the top.</div>
+    <div class="note">NSFW images may result in blank or corrupted image ; use turbo model for NSFW </div>
 
     <div id="images" aria-live="polite"></div>
   </div>
@@ -406,6 +406,7 @@
   let isGenerating = false;
   let generationCount = 0;
   let selectedRating = 0;
+  let hasRated = localStorage.getItem("hasRated")
   let feedbackSubmitted = false;
   
   const FORM_SPREE_ENDPOINT = 'https://formspree.io/f/xgvzqeed';
@@ -438,9 +439,11 @@ in realistic photo also liked if prompt is about a man with Gucci bag then obvio
 
 
 ### 1. META-PHOTOGRAPHY REFERENCES:
+- GoPro/action camera footage
 - "the kind of photo someone takes with their phone"
 - "the sort of image that gets captured when"
 - "captured in one of those moments when"
+- etc 
 - These access amateur photography training clusters vs professional clusters
 
 ### 2. CASUAL PURPOSE CONTEXTS:
@@ -448,6 +451,7 @@ in realistic photo also liked if prompt is about a man with Gucci bag then obvio
 - "to document where they ended up"
 - "taken quickly to capture the moment"
 - "sent to someone to show the scene"
+- etc
 - Purpose-driven casual photography accesses realistic training data
 
 ### 3. TECHNICAL IMPERFECTIONS:
@@ -455,6 +459,7 @@ in realistic photo also liked if prompt is about a man with Gucci bag then obvio
 - "not perfectly centered"
 - "caught mid-movement" 
 - "imperfect framing"
+- etc 
 - Prevents idealized composition training data activation
 
 ### 4. EXPLICIT ANTI-GLAMOUR INSTRUCTIONS:
@@ -462,17 +467,20 @@ in realistic photo also liked if prompt is about a man with Gucci bag then obvio
 - "unaware they're being photographed"
 - "natural and unposed"
 - "just going about their day"
+- etc
 - Direct instructions to avoid fash,ion/beauty training clusters
 
 ### 5. DOCUMENTATION CONTEXTS (RANKED BY EFFECTIVENESS):
-- phone photography for casual sharing ✓ (BEST - most realistic)
+- phone photography for casual sharing ✓ 
 - Street photography documentation ✓ 
 - Candid moment capture ✓
 - Security footage  ✓ (adds visual artifacts)
+- etc
 
 ### 6. MUNDANE SPECIFICITY:
 - Specific table numbers, timestamps, ordinary details
 - "table 3", "around 2:30 PM", "Tuesday afternoon"
+- etc
 - Creates documentary authenticity, prevents artistic interpretation
 
 ## ATTENTION MECHANISM EXPLOITATION:
@@ -480,7 +488,8 @@ in realistic photo also liked if prompt is about a man with Gucci bag then obvio
 ### CLIP-L/14 PROCESSING:
 - Handles style keywords and technical photography terms
 - Avoid: "photorealistic", "cinematic", "professional photography"
-- Use: "candid", "natural", "ordinary"
+- **Handles first 77 tokens only **"
+- Use: "candid", "Spontaneous", "natural", "ordinary"
 
 ### T5-XXL PROCESSING:
 - Excels at contextual understanding and narrative flow
@@ -510,11 +519,11 @@ in realistic photo also liked if prompt is about a man with Gucci bag then obvio
 ## ENHANCEMENT METHODOLOGY:
 
 ### STEP 1: IDENTIFY CORE ELEMENTS
-- Extract subject, location, basic action from input prompt
+- Extract subject, location, basic action from input prompt if not add them 
 
 ### STEP 2: ADD META-PHOTOGRAPHY CONTEXT
 - Choose appropriate amateur photography reference
-- "the kind of photo someone takes..."
+- "the kind of photo someone takes.."
 
 ### STEP 3: INSERT CASUAL PURPOSE
 - Add reason for taking the photo
@@ -528,15 +537,16 @@ in realistic photo also liked if prompt is about a man with Gucci bag then obvio
 - Explicitly prevent fashion/beauty modes
 - Emphasize naturalness and lack of posing
 
+
 ### EXAMPLE TRANSFORMATIONS:
 
 
+INPUT: "Woman in red dress in café"
+OUTPUT: "The kind of candid photo someone takes with their phone to show a friend where they're meeting - a woman in a red dress sitting at a café table, slightly off-angle, caught in a natural moment between sips of coffee, not posing or aware of the camera, just an ordinary afternoon."
 
 INPUT: "Man reading book in library"  
 OUTPUT: "Captured in one of those quiet library moments - a man absorbed in reading, the sort of documentary photo that shows real concentration, taken from a distance without him noticing, natural posture, imperfect framing, just someone lost in a good book on a regular weekday."
 
-INPUT: "Woman in red dress in café"
-OUTPUT: "The kind of candid photo someone takes with their phone to show a friend where they're meeting - a woman in a red dress sitting at a café table, slightly off-angle, caught in a natural moment between sips of coffee, not posing or aware of the camera, just an ordinary afternoon."
 
 
 ## CORE PHILOSOPHY:
@@ -779,10 +789,11 @@ GOAL: Generate prompts that produce realistic, natural-looking images by exploit
       card.innerHTML = `<img src="${imgUrl}" alt="generated image">`;
       
       // Increment generation count and show popup if threshold is met
-      if (!feedbackSubmitted) {
+      if (!feedbackSubmitted && !hasRated) {
           generationCount++;
           if (generationCount >= 3) {
               showFeedbackPopup();
+              localStorage.setItem("hasRated", true)
           }
       }