
The OpenAI Generator extension uses the OpenAI Image Generation API — colloquially known as DALL·E 2 — and the Text Completion API to generate results from a text-based prompt.
This extension provides 4 commands:
In order to use OpenAI's APIs, you have to create an account and create a new API key. Once you have a key, paste it into the extension's settings.
Please make sure to familiarize yourself with the API's limits. While it's super fun to just start immediately generating images, the Create Image API is heavily rate-limited (you'll be limited to 10 images per minute, and 25 per 5 minutes) and even the Text Completion API can run up a bill if you push it hard enough.
When you create a free account, you're granted $18 worth of credits for 12 months. Once you blow through your free credits, you'll be blocked from making more requests until you enter billing information.
The DALL·E Create Image API is priced based on image dimensions:
| Size | Price |
|---|---|
| 1024×1024 | $0.020 / image |
| 512×512 | $0.018 / image |
| 256×256 | $0.016 / image |
The GPT-3 Text Completion API is priced based on token usage:
| AI Model | Price |
|---|---|
| Ada (Fastest) | $0.0004 / 1K tokens |
| Babbage | $0.0005 / 1K tokens |
| Curie | $0.0020 / 1K tokens |
| Davinci (Most powerful) | $0.0200 / 1K tokens |
Generate images using OpenAI's DALL·E 2, an AI system that can create realistic images and art from a description in natural language
Generate a variation of an existing image using OpenAI's DALL·E 2
Generate an edited or extended image given an original image and a prompt using OpenAI's DALL·E 2
Input some text as a prompt, and generate a text completion that attempts to match whatever context or pattern you gave it
__proto__ key in mergeConfigtext-davinci-003 version