diff --git a/extract_tags.rb b/extract_tags.rb
index ba7b50b..2fb1fd0 100755
--- a/extract_tags.rb
+++ b/extract_tags.rb
@@ -11,7 +11,7 @@ require 'time'
 
 class TagExtractor
   OLLAMA_URL = 'http://localhost:11434/api/generate'
-  DEFAULT_MODELS = ['llava:7b']
+  DEFAULT_MODELS = ['llava:7b', 'qwen2.5vl:7b', 'bakllava:7b', 'minicpm-v:8b', 'llama3.2-vision:11b', 'llava:13b']
   VALID_EXTENSIONS = %w[.jpg .jpeg .png .gif .bmp .tiff .tif].freeze
 
   def initialize(options = {})
diff --git a/prompts/08-memory-search-optimizer.txt b/prompts/08-memory-search-optimizer.txt
new file mode 100644
index 0000000..74dca44
--- /dev/null
+++ b/prompts/08-memory-search-optimizer.txt
@@ -0,0 +1,13 @@
+Create detailed keywords for video diary search. Users might search for: "happy moments", "food experiences", "family time", "adventures", "quiet moments", "celebrations", "daily life", "travel memories". 
+
+Keyword everything visible including:
+- People: if present include 'people' with count descriptor (e.g. '3-people'), approximate ages, emotions on faces, what they're doing, how they're interacting
+- Scene type: where this is happening, indoor/outdoor, public/private space
+- Time: morning light, afternoon, golden hour, evening, night time
+- Mood: the feeling of the moment (joyful, peaceful, exciting, intimate, festive, contemplative)
+- Activities: eating, playing, working, relaxing, traveling, celebrating, exploring
+- Details: specific foods visible, drinks, decorations, clothing styles, weather, season
+- Colors: main colors that define the scene
+- Special moments: laughter, hugs, cheers, surprises, achievements
+
+Format: comma-separated keywords only, be specific rather than generic.
\ No newline at end of file
diff --git a/prompts/11-smart-scene-decoder.txt b/prompts/11-smart-scene-decoder.txt
new file mode 100644
index 0000000..17bd4a9
--- /dev/null
+++ b/prompts/11-smart-scene-decoder.txt
@@ -0,0 +1,13 @@
+You're analyzing frames for an AI-powered video diary search. Users search with natural language like "dinner with friends", "kids playing", "sunset at the beach", "birthday celebrations", "quiet morning coffee".
+
+Extract and keyword:
+HUMANS: if humans visible include 'people' and descriptive count (e.g. '4-people', 'couple', 'crowd'), estimated ages in decades (20s/30s/etc), primary emotion per person, body language, attire style. Skip if no humans present
+ACTIONS: primary action, secondary actions, interactions, gestures
+LOCATION: venue type, indoor/outdoor, architectural style, geographic region if evident
+TEMPORAL: exact time if visible, otherwise: dawn/morning/noon/afternoon/dusk/night, season indicators
+AMBIANCE: energy level 1-10, mood descriptors, lighting quality, color temperature
+OBJECTS: enumerate all significant objects, food with cuisine type, beverages, decorations
+CONTEXT: occasion type, relationship dynamics, cultural indicators
+TECHNICAL: image quality descriptors, composition style
+
+Output as comma-separated keywords. Prioritize specific over generic (e.g., "pepperoni pizza" not just "food").
\ No newline at end of file