pipeline in Baseline-Experimental.ipynb

Experiments/Baseline-Experimental.ipynb

@@ -8,7 +8,45 @@
     "collapsed": true
    },
    "outputs": [],
-   "source": []
+   "source": [
+    "# Utilize the Google Cloud Vision API to recognize text in the input images (diary images), https://cloud.google.com/vision.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "# Utilize the PaLM 2 Bison for Text model to conduct NLP tasks such as text summarization and condensing on the diary text, https://ai.google.dev/palm_docs/palm.\n"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "204930c13fd1e579"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "# Utilize the Gemini 1.0 Pro Vision to input an image of the diary writer, and output a textual description of the image, https://ai.google.dev/gemini-api/docs/models/gemini.\n"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "7f0c7d788b8de177"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "# Now that you have text from the diary and text describing the diary writer, you can utilize the SDXL-Turbo stable diffusion model to generate images https://huggingface.co/stabilityai/sdxl-turbo. You can try to output several images for a diary entry. Analyze how accurate the results, and think about what could be improved.\n"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "c475ca58dea760da"
   }
  ],
  "metadata": {