Upload sd_token_similarity_calculator.ipynb

sd_token_similarity_calculator.ipynb

@@ -123,7 +123,7 @@
       ],
       "metadata": {
         "id": "rUXQ73IbonHY",
-        "outputId": "aa0e25d1-f6b8-46ad-c1c1-0ccd70952cff",
+        "outputId": "5ce85c43-136a-49b5-f316-a74e70085e88",
         "colab": {
           "base_uri": "https://localhost:8080/"
         }
@@ -136,13 +136,13 @@
           "text": [
             "/content\n",
             "Cloning into 'text-to-image-prompts'...\n",
-            "remote: Enumerating objects: 478, done.\u001b[K\n",
-            "remote: Counting objects: 100% (475/475), done.\u001b[K\n",
-            "remote: Compressing objects: 100% (452/452), done.\u001b[K\n",
-            "remote: Total 478 (delta 82), reused 0 (delta 0), pack-reused 3 (from 1)\u001b[K\n",
-            "Receiving objects: 100% (478/478), 1.93 MiB | 6.96 MiB/s, done.\n",
-            "Resolving deltas: 100% (82/82), done.\n",
-            "Filtering content: 100% (95/95), 305.98 MiB | 59.56 MiB/s, done.\n"
+            "remote: Enumerating objects: 521, done.\u001b[K\n",
+            "remote: Counting objects: 100% (518/518), done.\u001b[K\n",
+            "remote: Compressing objects: 100% (492/492), done.\u001b[K\n",
+            "remote: Total 521 (delta 91), reused 0 (delta 0), pack-reused 3 (from 1)\u001b[K\n",
+            "Receiving objects: 100% (521/521), 2.51 MiB | 6.14 MiB/s, done.\n",
+            "Resolving deltas: 100% (91/91), done.\n",
+            "Filtering content: 100% (95/95), 305.98 MiB | 37.71 MiB/s, done.\n"
           ]
         }
       ]
@@ -223,258 +223,10 @@
         "NUM_VOCAB_ITEMS = nA\n"
       ],
       "metadata": {
-        "id": "ZMG4CThUAmwW",
-        "outputId": "029abb8c-ccb0-40af-b87c-df6e61d7548a",
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        }
+        "id": "ZMG4CThUAmwW"
       },
       "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "reading 🦜 fusion-t2i-prompt-features-23.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-9.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-4.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-2.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-25.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-6.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-19.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-33.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-18.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-22.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-31.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-3.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-8.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-7.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-13.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-34.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-14.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-12.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-17.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-21.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-24.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-32.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-5.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-20.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-16.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-28.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-10.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-15.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-26.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-27.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-1.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-29.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-30.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 🦜 fusion-t2i-prompt-features-11.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/green/text_encodings\n",
-            "reading 😃 fusion-t2i-emojis-2.json....\n",
-            "/content/text-to-image-prompts/tokens/emoji/text\n",
-            "/content/text-to-image-prompts/tokens/emoji/text_encodings\n",
-            "reading 🧿📘 fusion-t2i-civitai-0-20-chars-mix-2.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/blue/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/blue/text_encodings\n",
-            "reading 🧿📘 fusion-t2i-civitai-0-20-chars-mix-10.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/blue/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/blue/text_encodings\n",
-            "reading 🧿📘 fusion-t2i-civitai-0-20-chars-mix-6.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/blue/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/blue/text_encodings\n",
-            "reading 🧿📘 fusion-t2i-civitai-0-20-chars-mix-5.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/blue/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/blue/text_encodings\n",
-            "reading 🧿📘 fusion-t2i-civitai-0-20-chars-mix-4.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/blue/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/blue/text_encodings\n",
-            "reading 🧿📘 fusion-t2i-civitai-0-20-chars-mix-8.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/blue/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/blue/text_encodings\n",
-            "reading 🧿📘 fusion-t2i-civitai-0-20-chars-mix-1.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/blue/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/blue/text_encodings\n",
-            "reading 🧿📘 fusion-t2i-civitai-0-20-chars-mix-7.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/blue/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/blue/text_encodings\n",
-            "reading 🧿📘 fusion-t2i-civitai-0-20-chars-mix-3.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/blue/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/blue/text_encodings\n",
-            "reading 🧿📘 fusion-t2i-civitai-0-20-chars-mix-9.json....\n",
-            "/content/text-to-image-prompts/civitai-prompts/blue/text\n",
-            "/content/text-to-image-prompts/civitai-prompts/blue/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-common-suffix-5 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/common/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/common/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-common-suffix-2 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/common/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/common/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-common-suffix-3 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/common/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/common/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-common-suffix-4 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/common/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/common/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-common-suffix-1 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/common/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/common/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-common-suffix-6 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/common/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/common/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-average-suffix-5 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/average/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/average/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-average-suffix-1 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/average/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/average/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-average-suffix-6 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/average/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/average/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-average-suffix-2 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/average/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/average/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-average-suffix-3 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/average/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/average/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-average-suffix-7 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/average/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/average/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-average-suffix-4 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/average/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/average/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-rare-suffix-6 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/rare/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/rare/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-rare-suffix-1 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/rare/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/rare/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-rare-suffix-5 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/rare/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/rare/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-rare-suffix-2 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/rare/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/rare/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-rare-suffix-7 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/rare/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/rare/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-rare-suffix-3 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/rare/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/rare/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-rare-suffix-4 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/rare/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/rare/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-weird-suffix-6 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/weird/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/weird/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-weird-suffix-3 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/weird/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/weird/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-weird-suffix-5 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/weird/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/weird/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-weird-suffix-1 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/weird/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/weird/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-weird-suffix-4 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/weird/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/weird/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-weird-suffix-2 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/weird/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/weird/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-weird-suffix-7 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/weird/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/weird/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-exotic-suffix-4 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/exotic/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/exotic/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-exotic-suffix-2 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/exotic/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/exotic/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-exotic-suffix-3 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/exotic/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/exotic/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-exotic-suffix-1 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/exotic/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/exotic/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-exotic-suffix-7 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/exotic/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/exotic/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-exotic-suffix-6 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/exotic/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/exotic/text_encodings\n",
-            "reading 🔹 fusion-t2i-sd15-clip-tokens-exotic-suffix-5 Tokens.json....\n",
-            "/content/text-to-image-prompts/tokens/suffix/exotic/text\n",
-            "/content/text-to-image-prompts/tokens/suffix/exotic/text_encodings\n"
-          ]
-        }
-      ]
+      "outputs": []
     },
     {
       "cell_type": "code",
@@ -555,121 +307,10 @@
         "#-------#"
       ],
       "metadata": {
-        "id": "_vnVbxcFf7WV",
-        "outputId": "1c8953a9-6519-4b6a-cb45-127d34beaddf",
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        }
+        "id": "_vnVbxcFf7WV"
       },
       "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "{Sports Car|\n",
-            "beautiful car|\n",
-            "her car behind on the road|\n",
-            "the race car driver sits behind the wheel|\n",
-            "racing car in the background|\n",
-            "road nature|\n",
-            "running road|\n",
-            "sport car petite|\n",
-            "it's a gas gas|\n",
-            "The Road Not Taken|\n",
-            "cyber car looking_upscenery|\n",
-            "cyber car looking_upscenery|\n",
-            "road Horizon|\n",
-            "a beautiful|\n",
-            "a beautiful|\n",
-            "far away|\n",
-            "speed</w>|\n",
-            "roadtrip</w>|\n",
-            "driving</w>|\n",
-            "true to life|\n",
-            "street|\n",
-            "ontheroad</w>|\n",
-            "sharp image|\n",
-            "on a race track|\n",
-            "road construction|\n",
-            "with a soft|\n",
-            "on the crowded streets|\n",
-            "a picture|\n",
-            "faster</w>|\n",
-            "Fantastic|\n",
-            "loving|\n",
-            "the image should have|\n",
-            "takes off down the track|\n",
-            "road architecture|\n",
-            "and you can't help but feel|\n",
-            "day scenery|\n",
-            "wonderful|\n",
-            "but now seems to exude|\n",
-            "is appropriate for the time period|\n",
-            "head back|\n",
-            "photographic style|\n",
-            "very sweet|\n",
-            "alright</w>|\n",
-            "thats</w>|\n",
-            "awesome inspiring|\n",
-            "Know the past|\n",
-            "seems</w>|\n",
-            "as style|\n",
-            "inspired|\n",
-            "should have an attentive|\n",
-            "the image should be one|\n",
-            "lovely|\n",
-            "well</w>|\n",
-            "reminds</w>|\n",
-            "looking pass the came|\n",
-            "looking pass the came|\n",
-            "beautiful amazing|\n",
-            "highway</w>|\n",
-            "appears timeless|\n",
-            "emphasizing the sense|\n",
-            "that</w>|\n",
-            "beautiful gorgeous|\n",
-            "highway  setting|\n",
-            "science fiction|\n",
-            "Science fiction|\n",
-            "speeding</w>|\n",
-            "an engine or the clanking|\n",
-            "in a mountain land|\n",
-            "inspiration|\n",
-            "day time|\n",
-            "beautiful_|\n",
-            "busy highway|\n",
-            "really</w>|\n",
-            "sitting in the driver seat|\n",
-            "bright the image should convey|\n",
-            "Phenomenal|\n",
-            "girl trembling|\n",
-            "inspired by the last|\n",
-            "beauty|\n",
-            "advanced technology in|\n",
-            "baby|\n",
-            "adding to the overall sense|\n",
-            "top quality|\n",
-            "motorcycle freeway|\n",
-            "very beautiful|\n",
-            "beautiful beautiful|\n",
-            "cute beautiful|\n",
-            "Beautiful|\n",
-            "beautiful|\n",
-            "beautiful|\n",
-            "best highest quallity|\n",
-            "meticulous attention to|\n",
-            "meticulous attention to|\n",
-            "tweeted</w>|\n",
-            "street in city|\n",
-            "a gorgeous|\n",
-            "exciting|\n",
-            "a beautiful ravishing|\n",
-            "fire flames|\n",
-            "police car in background}\n"
-          ]
-        }
-      ]
+      "outputs": []
     },
     {
       "cell_type": "markdown",
@@ -825,121 +466,10 @@
         "#-------#"
       ],
       "metadata": {
-        "id": "JkzncP8SgKtS",
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "outputId": "2271de2f-6885-4f72-bcd0-3c39a9cfaada"
+        "id": "JkzncP8SgKtS"
       },
       "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "{reimagined</w>|\n",
-            "movie</w>|\n",
-            "4k vivid colors|\n",
-            "movie still|\n",
-            "Movie still|\n",
-            "heroine</w>|\n",
-            "amazon</w>|\n",
-            "taun-|\n",
-            "alliance</w>|\n",
-            "reminis-|\n",
-            "premiere</w>|\n",
-            "honor-|\n",
-            "artemis</w>|\n",
-            "blue archive|\n",
-            "guarding</w>|\n",
-            "purple-|\n",
-            "protectors</w>|\n",
-            "Concept art|\n",
-            "concept art|\n",
-            "mags</w>|\n",
-            "cinematic still|\n",
-            "Cinematic still|\n",
-            "epic fantasy|\n",
-            "athena</w>|\n",
-            "ragnarok</w>|\n",
-            "bloo-|\n",
-            "special effects|\n",
-            "rained</w>|\n",
-            "vibrant arthouse|\n",
-            "clones</w>|\n",
-            "cinema art|\n",
-            "elves</w>|\n",
-            "movie texture|\n",
-            "anarch-|\n",
-            "oxi-|\n",
-            "sura-|\n",
-            "widow</w>|\n",
-            "vibrant Concept art|\n",
-            "goddess</w>|\n",
-            "Masterpiece Sci-Fi|\n",
-            "recruited</w>|\n",
-            "terra</w>|\n",
-            "sirens</w>|\n",
-            "defiance</w>|\n",
-            "sprite</w>|\n",
-            "soaked</w>|\n",
-            "kavan-|\n",
-            "holocau-|\n",
-            "soldiers</w>|\n",
-            "artstation|\n",
-            "valor</w>|\n",
-            "etty</w>|\n",
-            "marshals</w>|\n",
-            "clint</w>|\n",
-            "hd 8k masterpiece|\n",
-            "bluec-|\n",
-            "poppins</w>|\n",
-            "deeps darks|\n",
-            "hera</w>|\n",
-            "marvel 1girl|\n",
-            "guardian</w>|\n",
-            "references</w>|\n",
-            "woman solo|\n",
-            "4K 2girl|\n",
-            "characters</w>|\n",
-            "resolve</w>|\n",
-            "hail</w>|\n",
-            "sarmy</w>|\n",
-            "watched</w>|\n",
-            "drow-|\n",
-            "absurdres highres|\n",
-            "ogue</w>|\n",
-            "eq-|\n",
-            "snapped</w>|\n",
-            "atrix</w>|\n",
-            "navis</w>|\n",
-            "bodypaint|\n",
-            "striking</w>|\n",
-            "in that scene|\n",
-            "legion-|\n",
-            "hue-|\n",
-            "empowered</w>|\n",
-            "faction</w>|\n",
-            "widows</w>|\n",
-            "1girl vast|\n",
-            "destiny</w>|\n",
-            "visually</w>|\n",
-            "aspirations</w>|\n",
-            "tson</w>|\n",
-            "highres ultrares|\n",
-            "tali-|\n",
-            "swoon</w>|\n",
-            "aroo</w>|\n",
-            "oxi</w>|\n",
-            "blue filter|\n",
-            "blue theme|\n",
-            "women</w>|\n",
-            "orah</w>|\n",
-            "backlash</w>|\n",
-            "legendof-}\n"
-          ]
-        }
-      ]
+      "outputs": []
     },
     {
       "cell_type": "code",
@@ -992,19 +522,7 @@
     {
       "cell_type": "code",
       "source": [
-        "%cd /content/\n",
-        "!git clone https://huggingface.co/datasets/codeShare/text-to-image-prompts"
-      ],
-      "metadata": {
-        "id": "GPAUFxZgPfrY"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "# @title Make your own text_encodings .pt file for later use (using GPU is recommended to speed things up)\n",
+        "# @title Make your own text_encodings .safetensor file for later use (using GPU is recommended to speed things up)\n",
         "\n",
         "import json\n",
         "import pandas as pd\n",
@@ -1013,9 +531,16 @@
         "import torch\n",
         "from safetensors.torch import save_file\n",
         "\n",
+        "using_Kaggle = False #Use https://www.kaggle.com/ if Google Colab GPU is busy\n",
+        "\n",
+        "home_directory = '/content/'\n",
+        "if using_Kaggle : home_directory = '/kaggle/working/'\n",
+        "output_folder = home_directory + 'text_encodings/'\n",
+        "target = home_directory + 'text-to-image-prompts/names/celebs/mixed/text'\n",
+        "\n",
         "def my_mkdirs(folder):\n",
-        "  if os.path.exists(folder)==False:\n",
-        "    os.makedirs(folder)\n",
+        "    if os.path.exists(folder)==False:\n",
+        "        os.makedirs(folder)\n",
         "\n",
         "device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n",
         "from transformers import AutoTokenizer\n",
@@ -1024,52 +549,53 @@
         "processor = CLIPProcessor.from_pretrained(\"openai/clip-vit-large-patch14\" , clean_up_tokenization_spaces = True)\n",
         "model = CLIPModel.from_pretrained(\"openai/clip-vit-large-patch14\").to(device)\n",
         "\n",
-        "%cd /content/\n",
-        "\n",
-        "my_mkdirs('/content/text_encodings/')\n",
-        "filename = ''\n",
-        "\n",
-        "NUM_FILES = 9\n",
+        "%cd {home_directory}\n",
         "\n",
         "\n",
-        "filename = '🆔👩_🦰 fusion-t2i-girl-firstname-1'\n",
-        "%cd /content/text-to-image-prompts/names/firstnames/text\n",
-        "with open(filename + '.json', 'r') as f:\n",
-        "    data = json.load(f)\n",
-        "_df = pd.DataFrame({'count': data})['count']\n",
-        "firstname = {\n",
-        "    key : value for key, value in _df.items()\n",
-        "}\n",
+        "my_mkdirs(home_directory +'text_encodings/')\n",
+        "filename = ''\n",
         "\n",
-        "NUM_FIRSTNAME = 100901\n",
         "\n",
+        "NUM_FILES = 1\n",
         "for  file_index in range(NUM_FILES + 1):\n",
-        "  if file_index <1: continue\n",
-        "  #if file_index >4: break\n",
-        "  filename = f'👱_♀️ fusion-t2i-lastnames-1 plugin-{file_index}'\n",
-        "  #🦜 fusion-t2i-prompt-features-1.json\n",
+        "    if (file_index < 1): continue\n",
+        "    filename = f'🆔👨 fusion-t2i-v2-celeb-{file_index}'\n",
         "\n",
         "  # Read suffix.json\n",
-        "  %cd /content/text-to-image-prompts/names/lastnames/text\n",
-        "  with open(filename + '.json', 'r') as f:\n",
-        "      data = json.load(f)\n",
-        "  _df = pd.DataFrame({'count': data})['count']\n",
-        "  names = {\n",
-        "      key : firstname[f'{random.randint(2,NUM_FIRSTNAME)}'] + f'{value}' for key, value in _df.items()\n",
-        "  }\n",
-        "  NUM_ITEMS = int(prompts[\"0\"])\n",
-        "  #------#\n",
+        "    %cd {target}\n",
+        "    with open(filename + '.json', 'r') as f:\n",
+        "        data = json.load(f)\n",
+        "    _df = pd.DataFrame({'count': data})['count']\n",
+        "    prompts = {\n",
+        "        key : value.replace(\"</w>\",\" \") for key, value in _df.items()\n",
+        "    }\n",
+        "    NUM_ITEMS = int(prompts[\"0\"])\n",
+        "    #------#\n",
         "\n",
         "  # Calculate text_encoding for .json file contents and results as .db file\n",
         "\n",
-        "  %cd /content/text_encodings/\n",
-        "  text_encoding_dict = {}\n",
-        "  for index in range(NUM_ITEMS + 1):\n",
-        "    inputs = tokenizer(text = '' + prompts[f'{index}'], padding=True, return_tensors=\"pt\").to(device)\n",
-        "    text_features = model.get_text_features(**inputs).to(device)\n",
-        "    text_features =  text_features/text_features.norm(p=2, dim=-1, keepdim=True).to(device)\n",
-        "    text_encoding_dict[f'{index}'] = text_features.to('cpu')\n",
+        "    %cd {output_folder}\n",
+        "    text_encoding_dict = {}\n",
+        "    offset = 0;\n",
+        "    index = 0;\n",
+        "    subby = 1;\n",
+        "    for _index in range(NUM_ITEMS):\n",
+        "      index = _index - offset\n",
+        "      inputs = tokenizer(text = '' + prompts[f'{index}'], padding=True, return_tensors=\"pt\").to(device)\n",
+        "      text_features = model.get_text_features(**inputs).to(device)\n",
+        "      text_features =  text_features/text_features.norm(p=2, dim=-1, keepdim=True)\n",
+        "      text_encoding_dict[f'{index}'] = text_features.to(torch.device('cpu'))\n",
+        "      if (index % 100 == 0) :\n",
+        "        print(index)\n",
+        "      if (index % 1000 == 0) :\n",
+        "        save_file(text_encoding_dict, f'{filename}-{subby}.safetensors')\n",
+        "        offset = offset + index\n",
+        "        subby = subby + 1\n",
+        "        text_encoding_dict = {}\n",
+        "      continue\n",
         "    save_file(text_encoding_dict, f'{filename}.safetensors')\n",
+        "    #-----#\n",
+        "\n",
         "  #----#\n",
         "\n",
         "#from safetensors.torch import load_file\n",
@@ -1086,9 +612,9 @@
     {
       "cell_type": "code",
       "source": [
-        "# @title Download the created JSON as .zip file\n",
+        "# @title Download the text_encodings as .zip\n",
         "%cd /content/\n",
-        "!zip -r /content/blue.zip /content/text-to-image-prompts/civitai-prompts/blue/text"
+        "!zip -r /content/text_encodings.zip /content/text_encodings/"
       ],
       "metadata": {
         "id": "gX-sHZPWj4Lt"
@@ -1099,315 +625,50 @@
     {
       "cell_type": "code",
       "source": [
-        "# @title ⚡+🖼️ -> 📝 Token-Sampling Image interrogator (work in progress)\n",
-        "#-----#\n",
-        "NUM_TOKENS = 49407\n",
+        "# @title Merge text_encodings\n",
+        "\n",
+        "import json\n",
+        "import pandas as pd\n",
+        "import os\n",
         "import shelve\n",
-        "db_vocab = shelve.open(VOCAB_FILENAME)\n",
-        "print(f'using the tokens found in {VOCAB_FILENAME}.db as the vocab')\n",
-        "# @markdown # What do you want to to mimic?\n",
-        "use = '🖼️image_encoding from image' # @param ['📝text_encoding from prompt', '🖼️image_encoding from image']\n",
-        "# @markdown --------------------------\n",
-        "use_token_padding = True # param {type:\"boolean\"} <---- Enabled by default\n",
-        "prompt = \"photo of a banana\" # @param {\"type\":\"string\",\"placeholder\":\"Write a prompt\"}\n",
-        "#-----#\n",
-        "prompt_A = prompt\n",
-        "if(image_path != \"\") : image_A = cv2.imread(\"/content/sd_tokens/\" + image_path)\n",
-        "#-----#\n",
+        "import torch\n",
+        "from safetensors.torch import save_file , load_file\n",
         "\n",
-        "from transformers import AutoTokenizer\n",
-        "tokenizer = AutoTokenizer.from_pretrained(\"openai/clip-vit-large-patch14\", clean_up_tokenization_spaces = False)\n",
-        "from transformers import  CLIPProcessor, CLIPModel\n",
-        "processor = CLIPProcessor.from_pretrained(\"openai/clip-vit-large-patch14\" , clean_up_tokenization_spaces = True)\n",
-        "model = CLIPModel.from_pretrained(\"openai/clip-vit-large-patch14\")\n",
-        "#-----#\n",
-        "if(use == '🖼️image_encoding from image'):\n",
-        "  # Get image features\n",
-        "  inputs = processor(images=image_A, return_tensors=\"pt\")\n",
-        "  image_features = model.get_image_features(**inputs)\n",
-        "  image_features = image_features / image_features.norm(p=2, dim=-1, keepdim=True)\n",
-        "  name_A = \"the image\"\n",
-        "#-----#\n",
-        "if(use == '📝text_encoding from prompt'):\n",
-        "  # Get text features\n",
-        "  inputs = tokenizer(text = prompt, padding=True, return_tensors=\"pt\")\n",
-        "  text_features_A = model.get_text_features(**inputs)\n",
-        "  name_A = prompt\n",
-        "#-----#\n",
-        "# @markdown # The output...\n",
-        "must_start_with = \"\" # @param {\"type\":\"string\",\"placeholder\":\"write a text\"}\n",
-        "must_contain = \"\" # @param {\"type\":\"string\",\"placeholder\":\"write a text\"}\n",
-        "must_end_with = \"\" # @param {\"type\":\"string\",\"placeholder\":\"write a text\"}\n",
-        "# @markdown -----\n",
-        "# @markdown # Use a range of tokens from the vocab.json (slow method)\n",
-        "start_search_at_index = 0 # @param {type:\"slider\", min:0, max: 49407, step:100}\n",
-        "# @markdown The lower the start_index, the more similiar the sampled tokens will be to the target token assigned in the '⚡ Get similiar tokens' cell\". If the cell was not run, then it will use tokens ordered by similarity to the \"girl\\</w>\" token\n",
-        "start_search_at_ID = start_search_at_index\n",
-        "search_range = 1000 # @param {type:\"slider\", min:100, max:49407, step:100}\n",
+        "def my_mkdirs(folder):\n",
+        "    if os.path.exists(folder)==False:\n",
+        "        os.makedirs(folder)\n",
         "\n",
-        "samples_per_iter = 10 # @param {type:\"slider\", min:10, max: 100, step:10}\n",
         "\n",
-        "iterations = 5 # @param {type:\"slider\", min:1, max: 20, step:0}\n",
-        "restrictions = 'None' # @param [\"None\", \"Suffix only\", \"Prefix only\"]\n",
-        "#markdown Limit char size of included token <----- Disabled\n",
-        "min_char_size = 0 #param {type:\"slider\", min:0, max: 20, step:1}\n",
-        "char_range = 50 #param {type:\"slider\", min:0, max: 20, step:1}\n",
-        "# markdown # ...or paste prompt items\n",
-        "# markdown Format must be {item1|item2|...}. You can aquire prompt items using the Randomizer in the fusion gen: https://perchance.org/fusion-ai-image-generator\n",
-        "_enable = False # param {\"type\":\"boolean\"}\n",
-        "prompt_items = \"\" # param {\"type\":\"string\",\"placeholder\":\"{item1|item2|...}\"}\n",
-        "#-----#\n",
-        "#-----#\n",
-        "START = start_search_at_ID\n",
-        "RANGE =  min(search_range , max(1,NUM_TOKENS - start_search_at_ID))\n",
-        "#-----#\n",
-        "import math, random\n",
-        "NUM_PERMUTATIONS = 6\n",
-        "ITERS = iterations\n",
-        "#-----#\n",
-        "#LOOP START\n",
-        "#-----#\n",
-        "# Check if original solution is best\n",
-        "best_sim = 0\n",
-        "name = must_start_with + must_contain + must_end_with\n",
-        "ids = processor.tokenizer(text=name, padding=use_token_padding, return_tensors=\"pt\")\n",
-        "text_features = model.get_text_features(**ids)\n",
-        "text_features = text_features / text_features.norm(p=2, dim=-1, keepdim=True)\n",
-        "#------#\n",
-        "sim = 0\n",
-        "if(use == '🖼️image_encoding from image'):\n",
-        "  logit_scale = model.logit_scale.exp()\n",
-        "  torch.matmul(text_features, image_features.t()) * logit_scale\n",
-        "  sim = torch.nn.functional.cosine_similarity(text_features, image_features) * logit_scale\n",
-        "#-----#\n",
-        "if(use == '📝text_encoding from prompt'):\n",
-        "  sim = torch.nn.functional.cosine_similarity(text_features, text_features_A)\n",
-        "#-----#\n",
-        "best_sim = sim\n",
-        "best_name = name\n",
-        "name_B = must_contain\n",
+        "using_Kaggle = False #Use https://www.kaggle.com/ if Google Colab GPU is busy\n",
+        "\n",
+        "home_directory = '/content/'\n",
+        "if using_Kaggle : home_directory = '/kaggle/working/'\n",
+        "output_folder = home_directory +'merged_text_encodings/'\n",
+        "my_mkdirs(f'{output_folder}')\n",
+        "\n",
+        "target = home_directory + 'text_encodings'\n",
+        "_filename = f'🆔👨 fusion-t2i-v2-celeb-1'\n",
+        "result = {}\n",
         "#------#\n",
-        "results_sim = torch.zeros(ITERS*NUM_PERMUTATIONS)\n",
-        "results_name_B = {}\n",
-        "results_name = {}\n",
-        "#-----#\n",
-        "for iter in range(ITERS):\n",
-        "  dots = torch.zeros(min(list_size,RANGE))\n",
-        "  is_trail = torch.zeros(min(list_size,RANGE))\n",
+        "%cd {target}\n",
+        "for _index in range(5):\n",
+        "  if _index <1:continue\n",
+        "  filename = _filename + f'-{_index}'\n",
+        "  prompts = load_file(filename + '.safetensors')\n",
+        "  for key in prompts:\n",
+        "    index = _index*1000  + int(key)\n",
+        "    result[f'{index}'] = prompts[key]\n",
+        "  #------#\n",
+        "#--------3\n",
         "\n",
-        "  #-----#\n",
+        "%cd {output_folder}\n",
+        "save_file(result, f'{_filename}.safetensors')\n",
         "\n",
-        "  for index in range(samples_per_iter):\n",
-        "    _start = START\n",
-        "    id_C = random.randint(_start , _start + RANGE)\n",
-        "    name_C = db_vocab[f'{id_C}']\n",
-        "    is_Prefix = 0\n",
-        "    #Skip if non-AZ characters are found\n",
-        "    #???\n",
-        "    #-----#\n",
-        "    # Decide if we should process prefix/suffix tokens\n",
-        "    if name_C.find('</w>')<=-1:\n",
-        "      is_Prefix = 1\n",
-        "      if restrictions != \"Prefix only\":\n",
-        "        continue\n",
-        "    else:\n",
-        "      if restrictions == \"Prefix only\":\n",
-        "        continue\n",
-        "    #-----#\n",
-        "    # Decide if char-size is within range\n",
-        "    if len(name_C) < min_char_size:\n",
-        "      continue\n",
-        "    if len(name_C) > min_char_size + char_range:\n",
-        "      continue\n",
-        "    #-----#\n",
-        "    name_CB = must_start_with + name_C + name_B + must_end_with\n",
-        "    if is_Prefix>0:\n",
-        "      name_CB = must_start_with + ' ' + name_C + '-' + name_B + ' ' + must_end_with\n",
-        "    #-----#\n",
-        "    if(use == '🖼️image_encoding from image'):\n",
-        "      ids_CB = processor.tokenizer(text=name_CB, padding=use_token_padding, return_tensors=\"pt\")\n",
-        "      text_features = model.get_text_features(**ids_CB)\n",
-        "      text_features = text_features / text_features.norm(p=2, dim=-1, keepdim=True)\n",
-        "      logit_scale = model.logit_scale.exp()\n",
-        "      torch.matmul(text_features, image_features.t()) * logit_scale\n",
-        "      sim_CB = torch.nn.functional.cosine_similarity(text_features, image_features) * logit_scale\n",
-        "    #-----#\n",
-        "    if(use == '📝text_encoding from prompt'):\n",
-        "      ids_CB = processor.tokenizer(text=name_CB, padding=use_token_padding, return_tensors=\"pt\")\n",
-        "      text_features = model.get_text_features(**ids_CB)\n",
-        "      text_features = text_features / text_features.norm(p=2, dim=-1, keepdim=True)\n",
-        "      sim_CB = torch.nn.functional.cosine_similarity(text_features, text_features_A)\n",
-        "    #-----#\n",
-        "    #-----#\n",
-        "    if restrictions == \"Prefix only\":\n",
-        "      result = sim_CB\n",
-        "      result = result.item()\n",
-        "      dots[index] = result\n",
-        "      continue\n",
-        "    #-----#\n",
-        "    if(use == '🖼️image_encoding from image'):\n",
-        "      name_BC = must_start_with + name_B + name_C + must_end_with\n",
-        "      ids_BC = processor.tokenizer(text=name_BC, padding=use_token_padding, return_tensors=\"pt\")\n",
-        "      text_features = model.get_text_features(**ids_BC)\n",
-        "      text_features = text_features / text_features.norm(p=2, dim=-1, keepdim=True)\n",
-        "      logit_scale = model.logit_scale.exp()\n",
-        "      torch.matmul(text_features, image_features.t()) * logit_scale\n",
-        "      sim_BC = torch.nn.functional.cosine_similarity(text_features, image_features) * logit_scale\n",
-        "    #-----#\n",
-        "    if(use == '📝text_encoding from prompt'):\n",
-        "      name_BC = must_start_with + name_B + name_C + must_end_with\n",
-        "      ids_BC = processor.tokenizer(text=name_BC, padding=use_token_padding, return_tensors=\"pt\")\n",
-        "      text_features = model.get_text_features(**ids_BC)\n",
-        "      text_features = text_features / text_features.norm(p=2, dim=-1, keepdim=True)\n",
-        "      sim_BC = torch.nn.functional.cosine_similarity(text_features, text_features_A)\n",
-        "    #-----#\n",
-        "    result = sim_CB\n",
-        "    if(sim_BC > sim_CB):\n",
-        "      is_trail[index] = 1\n",
-        "      result = sim_BC\n",
-        "    #-----#\n",
-        "    #result = absolute_value(result.item())\n",
-        "    result = result.item()\n",
-        "    dots[index] = result\n",
-        "  #----#\n",
-        "  sorted, indices = torch.sort(dots,dim=0 , descending=True)\n",
-        "  # @markdown ----------\n",
-        "  # @markdown # Print options\n",
-        "  list_size = 100 # param {type:'number'}\n",
-        "  print_ID = False # @param {type:\"boolean\"}\n",
-        "  print_Similarity = True # @param {type:\"boolean\"}\n",
-        "  print_Name = True # @param {type:\"boolean\"}\n",
-        "  print_Divider = True # @param {type:\"boolean\"}\n",
-        "  print_Suggestions = False # @param {type:\"boolean\"}\n",
-        "  #----#\n",
-        "  if (print_Divider):\n",
-        "    print('//---//')\n",
-        "  #----#\n",
-        "  print('')\n",
-        "\n",
-        "  used_reference = f'the text_encoding for {prompt_A}'\n",
-        "  if(use == '🖼️image_encoding from image'):\n",
-        "    used_reference = 'the image input'\n",
-        "  print(f'These token pairings within the range ID = {_start} to ID = {_start + RANGE} most closely match {used_reference}: ')\n",
-        "  print('')\n",
-        "  #----#\n",
-        "  aheads = \"{\"\n",
-        "  trails = \"{\"\n",
-        "  tmp = \"\"\n",
-        "  #----#\n",
-        "  max_sim_ahead = 0\n",
-        "  max_sim_trail = 0\n",
-        "  sim = 0\n",
-        "  max_name_ahead = ''\n",
-        "  max_name_trail = ''\n",
-        "  #----#\n",
-        "  for index in range(min(list_size,RANGE)):\n",
-        "    id = _start + indices[index].item()\n",
-        "    name = db_vocab[f'{id}']\n",
-        "    #-----#\n",
-        "    if (name.find('</w>')<=-1):\n",
-        "      name = name + '-'\n",
-        "    if(is_trail[index]>0):\n",
-        "      trails = trails + name + \"|\"\n",
-        "    else:\n",
-        "      aheads = aheads + name + \"|\"\n",
-        "    #----#\n",
-        "    sim = sorted[index].item()\n",
-        "    #----#\n",
-        "    if(is_trail[index]>0):\n",
-        "      if sim>max_sim_trail:\n",
-        "        max_sim_trail = sim\n",
-        "        max_name_trail = name\n",
-        "        max_name_trail = max_name_trail.strip()\n",
-        "\n",
-        "    else:\n",
-        "      if sim>max_sim_ahead:\n",
-        "        max_sim_ahead = sim\n",
-        "        max_name_ahead = name\n",
-        "  #------#\n",
-        "  trails = (trails + \"&&&&\").replace(\"|&&&&\", \"}\").replace(\"</w>\", \" \").replace(\"{&&&&\", \"\")\n",
-        "  aheads = (aheads + \"&&&&\").replace(\"|&&&&\", \"}\").replace(\"</w>\", \" \").replace(\"{&&&&\", \"\")\n",
-        "  #-----#\n",
-        "\n",
-        "  if(print_Suggestions):\n",
-        "    print(f\"place these items ahead of prompt :  {aheads}\")\n",
-        "    print(\"\")\n",
-        "    print(f\"place these items behind the prompt : {trails}\")\n",
-        "    print(\"\")\n",
-        "\n",
-        "  tmp = must_start_with + ' ' + max_name_ahead + name_B + ' ' + must_end_with\n",
-        "  tmp = tmp.strip().replace('</w>', ' ')\n",
-        "  print(f\"max_similarity_ahead = {round(max_sim_ahead,2)} % when using '{tmp}' \")\n",
-        "  print(\"\")\n",
-        "  tmp = must_start_with + ' ' + name_B + max_name_trail + ' ' + must_end_with\n",
-        "  tmp = tmp.strip().replace('</w>', ' ')\n",
-        "  print(f\"max_similarity_trail = {round(max_sim_trail,2)} % when using '{tmp}' \")\n",
-        "  #-----#\n",
-        "  #STEP 2\n",
-        "  import random\n",
-        "  #-----#\n",
-        "  for index in range(NUM_PERMUTATIONS):\n",
-        "    name_inner = ''\n",
-        "    if index == 0 : name_inner = name_B\n",
-        "    if index == 1: name_inner = max_name_ahead\n",
-        "    if index == 2: name_inner = max_name_trail\n",
-        "    if index == 3: name_inner = name_B + max_name_trail\n",
-        "    if index == 4: name_inner = max_name_ahead + name_B\n",
-        "    if index == 5: name_inner = max_name_ahead + name_B + max_name_trail\n",
-        "    if name_inner == '': name_inner = max_name_ahead + name_B + max_name_trail\n",
-        "\n",
-        "    name = must_start_with  + name_inner + must_end_with\n",
-        "    #----#\n",
-        "    ids = processor.tokenizer(text=name, padding=use_token_padding, return_tensors=\"pt\")\n",
-        "    #----#\n",
-        "    sim = 0\n",
-        "    if(use == '🖼️image_encoding from image'):\n",
-        "      text_features = model.get_text_features(**ids)\n",
-        "      text_features = text_features / text_features.norm(p=2, dim=-1, keepdim=True)\n",
-        "      logit_scale = model.logit_scale.exp()\n",
-        "      torch.matmul(text_features, image_features.t()) * logit_scale\n",
-        "      sim = torch.nn.functional.cosine_similarity(text_features, image_features) * logit_scale\n",
-        "    #-----#\n",
-        "    if(use == '📝text_encoding from prompt'):\n",
-        "      text_features = model.get_text_features(**ids)\n",
-        "      text_features = text_features / text_features.norm(p=2, dim=-1, keepdim=True)\n",
-        "      sim = torch.nn.functional.cosine_similarity(text_features, text_features_A)\n",
-        "    #-----#\n",
-        "    results_name[iter*NUM_PERMUTATIONS + index] = name\n",
-        "    results_sim[iter*NUM_PERMUTATIONS + index] = sim\n",
-        "    results_name_B[iter*NUM_PERMUTATIONS + index] = name_inner.replace('</w>',' ')\n",
-        "  #------#\n",
-        "  #name_B  = results_name_B[iter*NUM_PERMUTATIONS + random.randint(0,3)]\n",
-        "  tmp = iter*NUM_PERMUTATIONS\n",
-        "  _name_B=''\n",
-        "  if results_sim[tmp+1]>results_sim[tmp+2]: _name_B = results_name_B[tmp + 3]\n",
-        "  if results_sim[tmp+2]>results_sim[tmp+1]: _name_B = results_name_B[tmp + 4]\n",
-        "\n",
-        "  if _name_B != name_B:\n",
-        "    name_B=_name_B\n",
-        "  else:\n",
-        "    name_B = results_name_B[tmp + 5]\n",
-        "\n",
-        "#--------#\n",
-        "print('')\n",
-        "if(use == '🖼️image_encoding from image'  and colab_image_path != \"\"):\n",
-        "  from google.colab.patches import cv2_imshow\n",
-        "  cv2_imshow(image_A)\n",
-        "#-----#\n",
-        "print('')\n",
-        "sorted, indices = torch.sort(results_sim,dim=0 , descending=True)\n",
         "\n",
-        "for index in range(ITERS*NUM_PERMUTATIONS):\n",
-        "  name_inner = results_name[indices[index].item()]\n",
-        "  print(must_start_with  + name_inner + must_end_with)\n",
-        "  print(f'similiarity = {round(sorted[index].item(),2)} %')\n",
-        "  print('------')\n",
-        "#------#\n",
-        "db_vocab.close() #close the file"
+        "\n"
       ],
       "metadata": {
-        "collapsed": true,
-        "id": "fi0jRruI0-tu"
+        "id": "DNb_iJtLiuOL"
       },
       "execution_count": null,
       "outputs": []
@@ -2043,14 +1304,19 @@
         "  for key in names:\n",
         "    index = index + 1\n",
         "  #-----#\n",
+        "  RANGE = min(index,1000)\n",
+        "  output = {}\n",
         "\n",
-        "  names[f'{1}'] = f'👱_♀️female_fullnames-{file_index}'\n",
-        "  names[f'{0}'] = f'{index}'\n",
-        "\n",
+        "  for index in range(RANGE):\n",
+        "    if index >1000: break\n",
+        "    output[f'{index}'] = names[f'{index}']\n",
+        "  #-----#\n",
+        "  output[f'{1}'] = f'👱_♀️female_fullnames-{file_index}'\n",
+        "  output[f'{0}'] = f'{RANGE}'\n",
         "  txt_filename = f'👱_♀️female_fullnames-{file_index}'\n",
         "  %cd /content/female_full_names/\n",
         "  with open(txt_filename + '.txt', 'w') as f:\n",
-        "    f.write(str(names))\n",
+        "    f.write(str(output))\n",
         "\n",
         "  #files.download(f'fullnames-{file_index}.txt')\n",
         "\n",
@@ -2074,7 +1340,346 @@
         "!zip -r /content/female_full_names.zip /content/female_full_names/"
       ],
       "metadata": {
-        "id": "IBenvYVrofil"
+        "id": "IBenvYVrofil",
+        "outputId": "9af94446-aa17-4784-93c1-a88ba53717af",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        }
+      },
+      "execution_count": 5,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "/content\n",
+            "  adding: content/female_full_names/ (stored 0%)\n",
+            "  adding: content/female_full_names/👱_♀️female_fullnames-3.txt (deflated 66%)\n",
+            "  adding: content/female_full_names/👱_♀️female_fullnames-8.txt (deflated 66%)\n",
+            "  adding: content/female_full_names/👱_♀️female_fullnames-1.txt (deflated 67%)\n",
+            "  adding: content/female_full_names/👱_♀️female_fullnames-9.txt (deflated 67%)\n",
+            "  adding: content/female_full_names/👱_♀️female_fullnames-2.txt (deflated 67%)\n",
+            "  adding: content/female_full_names/👱_♀️female_fullnames-6.txt (deflated 67%)\n",
+            "  adding: content/female_full_names/👱_♀️female_fullnames-5.txt (deflated 67%)\n",
+            "  adding: content/female_full_names/👱_♀️female_fullnames-4.txt (deflated 66%)\n",
+            "  adding: content/female_full_names/👱_♀️female_fullnames-7.txt (deflated 65%)\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# @title ⚡+🖼️ -> 📝 Token-Sampling Image interrogator (work in progress)\n",
+        "#-----#\n",
+        "NUM_TOKENS = 49407\n",
+        "import shelve\n",
+        "db_vocab = shelve.open(VOCAB_FILENAME)\n",
+        "print(f'using the tokens found in {VOCAB_FILENAME}.db as the vocab')\n",
+        "# @markdown # What do you want to to mimic?\n",
+        "use = '🖼️image_encoding from image' # @param ['📝text_encoding from prompt', '🖼️image_encoding from image']\n",
+        "# @markdown --------------------------\n",
+        "use_token_padding = True # param {type:\"boolean\"} <---- Enabled by default\n",
+        "prompt = \"photo of a banana\" # @param {\"type\":\"string\",\"placeholder\":\"Write a prompt\"}\n",
+        "#-----#\n",
+        "prompt_A = prompt\n",
+        "if(image_path != \"\") : image_A = cv2.imread(\"/content/sd_tokens/\" + image_path)\n",
+        "#-----#\n",
+        "\n",
+        "from transformers import AutoTokenizer\n",
+        "tokenizer = AutoTokenizer.from_pretrained(\"openai/clip-vit-large-patch14\", clean_up_tokenization_spaces = False)\n",
+        "from transformers import  CLIPProcessor, CLIPModel\n",
+        "processor = CLIPProcessor.from_pretrained(\"openai/clip-vit-large-patch14\" , clean_up_tokenization_spaces = True)\n",
+        "model = CLIPModel.from_pretrained(\"openai/clip-vit-large-patch14\")\n",
+        "#-----#\n",
+        "if(use == '🖼️image_encoding from image'):\n",
+        "  # Get image features\n",
+        "  inputs = processor(images=image_A, return_tensors=\"pt\")\n",
+        "  image_features = model.get_image_features(**inputs)\n",
+        "  image_features = image_features / image_features.norm(p=2, dim=-1, keepdim=True)\n",
+        "  name_A = \"the image\"\n",
+        "#-----#\n",
+        "if(use == '📝text_encoding from prompt'):\n",
+        "  # Get text features\n",
+        "  inputs = tokenizer(text = prompt, padding=True, return_tensors=\"pt\")\n",
+        "  text_features_A = model.get_text_features(**inputs)\n",
+        "  name_A = prompt\n",
+        "#-----#\n",
+        "# @markdown # The output...\n",
+        "must_start_with = \"\" # @param {\"type\":\"string\",\"placeholder\":\"write a text\"}\n",
+        "must_contain = \"\" # @param {\"type\":\"string\",\"placeholder\":\"write a text\"}\n",
+        "must_end_with = \"\" # @param {\"type\":\"string\",\"placeholder\":\"write a text\"}\n",
+        "# @markdown -----\n",
+        "# @markdown # Use a range of tokens from the vocab.json (slow method)\n",
+        "start_search_at_index = 0 # @param {type:\"slider\", min:0, max: 49407, step:100}\n",
+        "# @markdown The lower the start_index, the more similiar the sampled tokens will be to the target token assigned in the '⚡ Get similiar tokens' cell\". If the cell was not run, then it will use tokens ordered by similarity to the \"girl\\</w>\" token\n",
+        "start_search_at_ID = start_search_at_index\n",
+        "search_range = 1000 # @param {type:\"slider\", min:100, max:49407, step:100}\n",
+        "\n",
+        "samples_per_iter = 10 # @param {type:\"slider\", min:10, max: 100, step:10}\n",
+        "\n",
+        "iterations = 5 # @param {type:\"slider\", min:1, max: 20, step:0}\n",
+        "restrictions = 'None' # @param [\"None\", \"Suffix only\", \"Prefix only\"]\n",
+        "#markdown Limit char size of included token <----- Disabled\n",
+        "min_char_size = 0 #param {type:\"slider\", min:0, max: 20, step:1}\n",
+        "char_range = 50 #param {type:\"slider\", min:0, max: 20, step:1}\n",
+        "# markdown # ...or paste prompt items\n",
+        "# markdown Format must be {item1|item2|...}. You can aquire prompt items using the Randomizer in the fusion gen: https://perchance.org/fusion-ai-image-generator\n",
+        "_enable = False # param {\"type\":\"boolean\"}\n",
+        "prompt_items = \"\" # param {\"type\":\"string\",\"placeholder\":\"{item1|item2|...}\"}\n",
+        "#-----#\n",
+        "#-----#\n",
+        "START = start_search_at_ID\n",
+        "RANGE =  min(search_range , max(1,NUM_TOKENS - start_search_at_ID))\n",
+        "#-----#\n",
+        "import math, random\n",
+        "NUM_PERMUTATIONS = 6\n",
+        "ITERS = iterations\n",
+        "#-----#\n",
+        "#LOOP START\n",
+        "#-----#\n",
+        "# Check if original solution is best\n",
+        "best_sim = 0\n",
+        "name = must_start_with + must_contain + must_end_with\n",
+        "ids = processor.tokenizer(text=name, padding=use_token_padding, return_tensors=\"pt\")\n",
+        "text_features = model.get_text_features(**ids)\n",
+        "text_features = text_features / text_features.norm(p=2, dim=-1, keepdim=True)\n",
+        "#------#\n",
+        "sim = 0\n",
+        "if(use == '🖼️image_encoding from image'):\n",
+        "  logit_scale = model.logit_scale.exp()\n",
+        "  torch.matmul(text_features, image_features.t()) * logit_scale\n",
+        "  sim = torch.nn.functional.cosine_similarity(text_features, image_features) * logit_scale\n",
+        "#-----#\n",
+        "if(use == '📝text_encoding from prompt'):\n",
+        "  sim = torch.nn.functional.cosine_similarity(text_features, text_features_A)\n",
+        "#-----#\n",
+        "best_sim = sim\n",
+        "best_name = name\n",
+        "name_B = must_contain\n",
+        "#------#\n",
+        "results_sim = torch.zeros(ITERS*NUM_PERMUTATIONS)\n",
+        "results_name_B = {}\n",
+        "results_name = {}\n",
+        "#-----#\n",
+        "for iter in range(ITERS):\n",
+        "  dots = torch.zeros(min(list_size,RANGE))\n",
+        "  is_trail = torch.zeros(min(list_size,RANGE))\n",
+        "\n",
+        "  #-----#\n",
+        "\n",
+        "  for index in range(samples_per_iter):\n",
+        "    _start = START\n",
+        "    id_C = random.randint(_start , _start + RANGE)\n",
+        "    name_C = db_vocab[f'{id_C}']\n",
+        "    is_Prefix = 0\n",
+        "    #Skip if non-AZ characters are found\n",
+        "    #???\n",
+        "    #-----#\n",
+        "    # Decide if we should process prefix/suffix tokens\n",
+        "    if name_C.find('</w>')<=-1:\n",
+        "      is_Prefix = 1\n",
+        "      if restrictions != \"Prefix only\":\n",
+        "        continue\n",
+        "    else:\n",
+        "      if restrictions == \"Prefix only\":\n",
+        "        continue\n",
+        "    #-----#\n",
+        "    # Decide if char-size is within range\n",
+        "    if len(name_C) < min_char_size:\n",
+        "      continue\n",
+        "    if len(name_C) > min_char_size + char_range:\n",
+        "      continue\n",
+        "    #-----#\n",
+        "    name_CB = must_start_with + name_C + name_B + must_end_with\n",
+        "    if is_Prefix>0:\n",
+        "      name_CB = must_start_with + ' ' + name_C + '-' + name_B + ' ' + must_end_with\n",
+        "    #-----#\n",
+        "    if(use == '🖼️image_encoding from image'):\n",
+        "      ids_CB = processor.tokenizer(text=name_CB, padding=use_token_padding, return_tensors=\"pt\")\n",
+        "      text_features = model.get_text_features(**ids_CB)\n",
+        "      text_features = text_features / text_features.norm(p=2, dim=-1, keepdim=True)\n",
+        "      logit_scale = model.logit_scale.exp()\n",
+        "      torch.matmul(text_features, image_features.t()) * logit_scale\n",
+        "      sim_CB = torch.nn.functional.cosine_similarity(text_features, image_features) * logit_scale\n",
+        "    #-----#\n",
+        "    if(use == '📝text_encoding from prompt'):\n",
+        "      ids_CB = processor.tokenizer(text=name_CB, padding=use_token_padding, return_tensors=\"pt\")\n",
+        "      text_features = model.get_text_features(**ids_CB)\n",
+        "      text_features = text_features / text_features.norm(p=2, dim=-1, keepdim=True)\n",
+        "      sim_CB = torch.nn.functional.cosine_similarity(text_features, text_features_A)\n",
+        "    #-----#\n",
+        "    #-----#\n",
+        "    if restrictions == \"Prefix only\":\n",
+        "      result = sim_CB\n",
+        "      result = result.item()\n",
+        "      dots[index] = result\n",
+        "      continue\n",
+        "    #-----#\n",
+        "    if(use == '🖼️image_encoding from image'):\n",
+        "      name_BC = must_start_with + name_B + name_C + must_end_with\n",
+        "      ids_BC = processor.tokenizer(text=name_BC, padding=use_token_padding, return_tensors=\"pt\")\n",
+        "      text_features = model.get_text_features(**ids_BC)\n",
+        "      text_features = text_features / text_features.norm(p=2, dim=-1, keepdim=True)\n",
+        "      logit_scale = model.logit_scale.exp()\n",
+        "      torch.matmul(text_features, image_features.t()) * logit_scale\n",
+        "      sim_BC = torch.nn.functional.cosine_similarity(text_features, image_features) * logit_scale\n",
+        "    #-----#\n",
+        "    if(use == '📝text_encoding from prompt'):\n",
+        "      name_BC = must_start_with + name_B + name_C + must_end_with\n",
+        "      ids_BC = processor.tokenizer(text=name_BC, padding=use_token_padding, return_tensors=\"pt\")\n",
+        "      text_features = model.get_text_features(**ids_BC)\n",
+        "      text_features = text_features / text_features.norm(p=2, dim=-1, keepdim=True)\n",
+        "      sim_BC = torch.nn.functional.cosine_similarity(text_features, text_features_A)\n",
+        "    #-----#\n",
+        "    result = sim_CB\n",
+        "    if(sim_BC > sim_CB):\n",
+        "      is_trail[index] = 1\n",
+        "      result = sim_BC\n",
+        "    #-----#\n",
+        "    #result = absolute_value(result.item())\n",
+        "    result = result.item()\n",
+        "    dots[index] = result\n",
+        "  #----#\n",
+        "  sorted, indices = torch.sort(dots,dim=0 , descending=True)\n",
+        "  # @markdown ----------\n",
+        "  # @markdown # Print options\n",
+        "  list_size = 100 # param {type:'number'}\n",
+        "  print_ID = False # @param {type:\"boolean\"}\n",
+        "  print_Similarity = True # @param {type:\"boolean\"}\n",
+        "  print_Name = True # @param {type:\"boolean\"}\n",
+        "  print_Divider = True # @param {type:\"boolean\"}\n",
+        "  print_Suggestions = False # @param {type:\"boolean\"}\n",
+        "  #----#\n",
+        "  if (print_Divider):\n",
+        "    print('//---//')\n",
+        "  #----#\n",
+        "  print('')\n",
+        "\n",
+        "  used_reference = f'the text_encoding for {prompt_A}'\n",
+        "  if(use == '🖼️image_encoding from image'):\n",
+        "    used_reference = 'the image input'\n",
+        "  print(f'These token pairings within the range ID = {_start} to ID = {_start + RANGE} most closely match {used_reference}: ')\n",
+        "  print('')\n",
+        "  #----#\n",
+        "  aheads = \"{\"\n",
+        "  trails = \"{\"\n",
+        "  tmp = \"\"\n",
+        "  #----#\n",
+        "  max_sim_ahead = 0\n",
+        "  max_sim_trail = 0\n",
+        "  sim = 0\n",
+        "  max_name_ahead = ''\n",
+        "  max_name_trail = ''\n",
+        "  #----#\n",
+        "  for index in range(min(list_size,RANGE)):\n",
+        "    id = _start + indices[index].item()\n",
+        "    name = db_vocab[f'{id}']\n",
+        "    #-----#\n",
+        "    if (name.find('</w>')<=-1):\n",
+        "      name = name + '-'\n",
+        "    if(is_trail[index]>0):\n",
+        "      trails = trails + name + \"|\"\n",
+        "    else:\n",
+        "      aheads = aheads + name + \"|\"\n",
+        "    #----#\n",
+        "    sim = sorted[index].item()\n",
+        "    #----#\n",
+        "    if(is_trail[index]>0):\n",
+        "      if sim>max_sim_trail:\n",
+        "        max_sim_trail = sim\n",
+        "        max_name_trail = name\n",
+        "        max_name_trail = max_name_trail.strip()\n",
+        "\n",
+        "    else:\n",
+        "      if sim>max_sim_ahead:\n",
+        "        max_sim_ahead = sim\n",
+        "        max_name_ahead = name\n",
+        "  #------#\n",
+        "  trails = (trails + \"&&&&\").replace(\"|&&&&\", \"}\").replace(\"</w>\", \" \").replace(\"{&&&&\", \"\")\n",
+        "  aheads = (aheads + \"&&&&\").replace(\"|&&&&\", \"}\").replace(\"</w>\", \" \").replace(\"{&&&&\", \"\")\n",
+        "  #-----#\n",
+        "\n",
+        "  if(print_Suggestions):\n",
+        "    print(f\"place these items ahead of prompt :  {aheads}\")\n",
+        "    print(\"\")\n",
+        "    print(f\"place these items behind the prompt : {trails}\")\n",
+        "    print(\"\")\n",
+        "\n",
+        "  tmp = must_start_with + ' ' + max_name_ahead + name_B + ' ' + must_end_with\n",
+        "  tmp = tmp.strip().replace('</w>', ' ')\n",
+        "  print(f\"max_similarity_ahead = {round(max_sim_ahead,2)} % when using '{tmp}' \")\n",
+        "  print(\"\")\n",
+        "  tmp = must_start_with + ' ' + name_B + max_name_trail + ' ' + must_end_with\n",
+        "  tmp = tmp.strip().replace('</w>', ' ')\n",
+        "  print(f\"max_similarity_trail = {round(max_sim_trail,2)} % when using '{tmp}' \")\n",
+        "  #-----#\n",
+        "  #STEP 2\n",
+        "  import random\n",
+        "  #-----#\n",
+        "  for index in range(NUM_PERMUTATIONS):\n",
+        "    name_inner = ''\n",
+        "    if index == 0 : name_inner = name_B\n",
+        "    if index == 1: name_inner = max_name_ahead\n",
+        "    if index == 2: name_inner = max_name_trail\n",
+        "    if index == 3: name_inner = name_B + max_name_trail\n",
+        "    if index == 4: name_inner = max_name_ahead + name_B\n",
+        "    if index == 5: name_inner = max_name_ahead + name_B + max_name_trail\n",
+        "    if name_inner == '': name_inner = max_name_ahead + name_B + max_name_trail\n",
+        "\n",
+        "    name = must_start_with  + name_inner + must_end_with\n",
+        "    #----#\n",
+        "    ids = processor.tokenizer(text=name, padding=use_token_padding, return_tensors=\"pt\")\n",
+        "    #----#\n",
+        "    sim = 0\n",
+        "    if(use == '🖼️image_encoding from image'):\n",
+        "      text_features = model.get_text_features(**ids)\n",
+        "      text_features = text_features / text_features.norm(p=2, dim=-1, keepdim=True)\n",
+        "      logit_scale = model.logit_scale.exp()\n",
+        "      torch.matmul(text_features, image_features.t()) * logit_scale\n",
+        "      sim = torch.nn.functional.cosine_similarity(text_features, image_features) * logit_scale\n",
+        "    #-----#\n",
+        "    if(use == '📝text_encoding from prompt'):\n",
+        "      text_features = model.get_text_features(**ids)\n",
+        "      text_features = text_features / text_features.norm(p=2, dim=-1, keepdim=True)\n",
+        "      sim = torch.nn.functional.cosine_similarity(text_features, text_features_A)\n",
+        "    #-----#\n",
+        "    results_name[iter*NUM_PERMUTATIONS + index] = name\n",
+        "    results_sim[iter*NUM_PERMUTATIONS + index] = sim\n",
+        "    results_name_B[iter*NUM_PERMUTATIONS + index] = name_inner.replace('</w>',' ')\n",
+        "  #------#\n",
+        "  #name_B  = results_name_B[iter*NUM_PERMUTATIONS + random.randint(0,3)]\n",
+        "  tmp = iter*NUM_PERMUTATIONS\n",
+        "  _name_B=''\n",
+        "  if results_sim[tmp+1]>results_sim[tmp+2]: _name_B = results_name_B[tmp + 3]\n",
+        "  if results_sim[tmp+2]>results_sim[tmp+1]: _name_B = results_name_B[tmp + 4]\n",
+        "\n",
+        "  if _name_B != name_B:\n",
+        "    name_B=_name_B\n",
+        "  else:\n",
+        "    name_B = results_name_B[tmp + 5]\n",
+        "\n",
+        "#--------#\n",
+        "print('')\n",
+        "if(use == '🖼️image_encoding from image'  and colab_image_path != \"\"):\n",
+        "  from google.colab.patches import cv2_imshow\n",
+        "  cv2_imshow(image_A)\n",
+        "#-----#\n",
+        "print('')\n",
+        "sorted, indices = torch.sort(results_sim,dim=0 , descending=True)\n",
+        "\n",
+        "for index in range(ITERS*NUM_PERMUTATIONS):\n",
+        "  name_inner = results_name[indices[index].item()]\n",
+        "  print(must_start_with  + name_inner + must_end_with)\n",
+        "  print(f'similiarity = {round(sorted[index].item(),2)} %')\n",
+        "  print('------')\n",
+        "#------#\n",
+        "db_vocab.close() #close the file"
+      ],
+      "metadata": {
+        "collapsed": true,
+        "id": "fi0jRruI0-tu",
+        "cellView": "form"
       },
       "execution_count": null,
       "outputs": []