Initial commit of DALL-E and Segment Anything notebook (#406)

* Initial commit of DALL-E and Segment Anything notebook

* Add example images and changed wording of the notebook

* Updated comments and added base images

* minor text amendments

* fix typo

* makes bullets more consistent

* converts title DALLE to DALL·E

* converts DALL-E to DALL·E

* update original DALL-E notebook title

* makes time of writing explicit

* makes intro bullets more consistent

* clarifies which version of Pytorch is appropriate

* moves setup instructions into setup section (to help clarify that they do not need to be done separately from the notebook)

* explains size of model checkpoint file

* code linting

* added more background info in the introduction for folks unfamiliar with segment anything

* adds period to sentence

* updates table of contents with new DALL·E guide

---------

Co-authored-by: Ted Sanders <ted@openai.com>

README.md

@@ -10,6 +10,7 @@ Most code examples are written in Python, though the concepts can be applied in
 
 ## Recently added or updated 🆕 ✨
 
+- [How to create dynamic masks with DALL·E and Segment Anything](examples/dalle/How_to_create_dynamic_masks_with_DALL-E_and_Segment_Anything.ipynb) [May 19th, 2021]
 - [Question answering using embeddings](examples/Question_answering_using_embeddings.ipynb) [Apr 14th, 2023]
 - [Using vector databases for embeddings search](examples/vector_databases/) [various dates]
 - [Powering your products with ChatGPT and your own data](apps/chatbot-kickstarter/powering_your_products_with_chatgpt_and_your_data.ipynb) [Mar 10th, 2023]
@@ -44,7 +45,8 @@ Most code examples are written in Python, though the concepts can be applied in
   - [Guide: best practices for fine-tuning GPT-3 to classify text](https://docs.google.com/document/d/1rqj7dkuvl7Byd5KQPUJRxc19BJt8wo0yHNwK84KfU3Q/edit)
   - [Fine-tuned classification](examples/Fine-tuned_classification.ipynb)
 - DALL-E
-  - [How to generate and edit images with DALL-E](examples/dalle/Image_generations_edits_and_variations_with_DALL-E.ipynb)
+  - [How to generate and edit images with DALL·E](examples/dalle/Image_generations_edits_and_variations_with_DALL-E.ipynb)
+  - [How to create dynamic masks with DALL·E and Segment Anything](examples/dalle/How_to_create_dynamic_masks_with_DALL-E_and_Segment_Anything.ipynb)
 - Azure OpenAI (alternative API from Microsoft Azure)
   - [How to use ChatGPT with Azure OpenAI](examples/azure/chat.ipynb)
   - [How to get completions from Azure OpenAI](examples/azure/completions.ipynb)

examples/dalle/Image_generations_edits_and_variations_with_DALL-E.ipynb

@@ -1,12 +1,13 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# DALL-E\n",
+    "# How to use the DALL·E API\n",
     "\n",
-    "This notebook shows how to use OpenAI's DALL-E image API endpoints.\n",
+    "This notebook shows how to use OpenAI's DALL·E image API endpoints.\n",
     "\n",
     "There are three API endpoints:\n",
     "- **Generations:** generates an image or images based on an input caption\n",
@@ -55,7 +56,7 @@
     }
    ],
    "source": [
-    "# set a directory to save DALL-E images to\n",
+    "# set a directory to save DALL·E images to\n",
     "image_dir_name = \"images\"\n",
     "image_dir = os.path.join(os.curdir, image_dir_name)\n",
     "\n",
@@ -318,12 +319,13 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "## Edits\n",
     "\n",
-    "The edit endpoint uses DALL-E to generate a specified portion of an existing image. Three inputs are needed: the image to edit, a mask specifying the portion to be regenerated, and a prompt describing the desired image.\n",
+    "The edit endpoint uses DALL·E to generate a specified portion of an existing image. Three inputs are needed: the image to edit, a mask specifying the portion to be regenerated, and a prompt describing the desired image.\n",
     "\n",
     "**Required inputs:** \n",
     "- image (str): The image to edit. Must be a valid PNG file, less than 4MB, and square.\n",