brand-image-generator's Introduction

Vercel AI SDK, Next.js, and OpenAI Chat Example

This example shows how to use the Vercel AI SDK with Next.js and OpenAI to create a ChatGPT-like AI-powered streaming chat bot.

Deploy your own

Deploy the example using Vercel:

How to use

Execute create-next-app with npm, Yarn, or pnpm to bootstrap the example:

npx create-next-app --example https://github.com/vercel-labs/ai/tree/main/examples/next-openai next-openai-app

yarn create next-app --example https://github.com/vercel-labs/ai/tree/main/examples/next-openai next-openai-app

pnpm create next-app --example https://github.com/vercel-labs/ai/tree/main/examples/next-openai next-openai-app

To run the example locally you need to:

Sign up at OpenAI's Developer Platform.
Go to OpenAI's dashboard and create an API KEY.
Set the required OpenAI environment variable as the token value as shown the example env file but in a new file called .env.local
pnpm install to install the required dependencies.
pnpm dev to launch the development server.

Learn More

To learn more about OpenAI, Next.js, and the Vercel AI SDK take a look at the following resources:

Vercel AI SDK docs
Vercel AI Playground
OpenAI Documentation - learn about OpenAI features and API.
Next.js Documentation - learn about Next.js features and API.

brand-image-generator's People

Contributors

Watchers

brand-image-generator's Issues

Get images from Brand Folder and render them in the app

https://brandfolder.com/hubspot/photo-library contains the branded images we need
read in the images and render them in a thumbnail gallery
there are many images, so pagination may be required

Acceptance Criteria

the page displays a thubmnail gallery of images from the brand folder
the images can be selected, from 1 to 5 (max) by clicking them
clicking selected images should de-select them

Replace ChatGPT with Dall-e

Currently the template projects comes with a chat GTP prompt input, we need to replace this with Dall-e

The api/chat contains the call to ChatGPT currently.

Acceptance Criteria:

Selecting an image from the gallery and clicking on a button will generate a Dall-E variation of that image

Spike - Investigate prompting Dall-e with existing images

we need to test if Dall-e API can support prompts that mix images and text

For example, selecting one or more existing images and passing them along with a prompt in order to generate a new image based of the prompt, but in the same style as the existing images

If this is not possible, the backup plan is to make the app a brand image editor instead of generating new images

Acceptance Criteria

test if the prompt for creating a new image with Dall-e can include existing images
if yes, try a prompt with some of the brand folder images
if not, try a prompt editing one of the brand folder images instead

Recommend Projects