This page is dedicated to collecting information and Links for Text AI and Graphics

The playground that leads to the ChatGPT site.  Playground is free to start with. Great area to experiment.
Allows bots to be built to do regular tasks right form the chrome browser.  Caution, it seems it may cause pop-ups on chrome, however, since it is free that is what pays for it.  
A local web UI for stable diffusion.  check system requirements.
ChatGPT's answer to a question about OpenAI:

what sites are connected to openaiOpenAI is an independent research organization that is not directly connected to any specific websites. However, OpenAI has developed a number of technologies that have been integrated into a variety of websites and applications. Some examples include:
  1. GPT (Generative Pre-trained Transformer): This is a machine learning model that can generate human-like text. It has been used to power chatbots, language translation tools, and content recommendation systems on various websites and apps.
  2. DALL-E: This is an artificial intelligence system that can generate images from text descriptions. It has been used to create a range of images, including paintings, photographs, and even logos.
  3. GPT-3: This is a large-scale language model that can generate human-like text and perform a variety of language tasks. It has been used to power chatbots, content generation tools, and other applications.
It is likely that there are many other websites and apps that are using technologies developed by OpenAI, but it is not possible to provide a comprehensive list.
The image site associated with OpenAI. Text to image.
Deep Dream is an AI system developed by Google that can generate images based on input provided by the user.

​ It works by analyzing the content of an image and generating a new image that is similar in style to the original image but with added elements or features based on the user's input.

​Has a brief free period.

To use Deep Dream, you will need to follow these steps:
  1. Visit the Deep Dream website (https://deepdream.net/) and click on the "Start Now" button.
  2. Select the type of image you want to generate from the available options (e.g., animals, plants, patterns, etc.).
  3. Upload an image to use as a reference or starting point for the generated image. You can also use one of the sample images provided by Deep Dream.
  4. Enter a description or keyword to specify the elements or features you want to include in the generated image.
  5. Click on the "Generate" button to start the image generation process.
  6. Wait for the image to be generated, which may take a few minutes depending on the complexity of the input.
  7. Once the image has been generated, you can view it and download it to your computer if you wish.
Generate response to directions or questions.  remembers what user said in earlier conversations so can build on previous discussion.  Uses the GPT engine.  
Are you into AI image generation? You can try these tools:
--Use caution as I have not checked each of these sites --

Do AI to music
​https://vocalremover.org/
A fun graphic site that allows experimenting with shapes in 3D.
3d model DreamFusion: Text-to-3D using 2D Diffusion ​


A 3d CAD program that at some point seems to link into AI.  More later after I experiment. 
Stable Diffusion is a machine learning, text-to-image model developed by StabilityAI, in collaboration with EleutherAI and LAION, to generate digital images from natural language descriptions. The model can be used for other tasks too, like generating image-to-image translations guided by a text prompt.

​free alternative to DALL-E and Midjourney.
Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input, cultivates autonomous freedom to produce incredible imagery, empowers billions of people to create stunning art within seconds.
Create beautiful art using stable diffusion ONLINE for free.
Just enter your prompt and click the generate button.
No code required to generate your image!
References
This creates an amazing photorealistic set of pictures from a text input.  after free then $$

Midjourney Prompt Tool
​Futuretools.io
​

Discussion and links for Midjourney ai

midjourney home page

Text to image parameters

This is a text area to collelct parameters that seem to work well with the various text to image sites.  No particular order yet.  A collection point at present.  Some of this can be derived from the various wiki sites associated with the above AI engines.
​
​

Notes on results and some sample outputs

Here is an interesting example of a question to openai and the answer I will try one of the suggestions and post the results on this page.

how do I get open ai to draw a picture?There are a few ways you can get OpenAI to generate a picture:
  1. Use OpenAI's DALL-E API: DALL-E is a neural network that generates images from text descriptions, using a combination of deep learning and evolutionary techniques. You can use the DALL-E API to generate a picture by sending a text description of the image you want to generate.
  2. Use OpenAI's GPT-3 API: GPT-3 is a language generation model that can be used to generate text, including descriptions of images. You can use the GPT-3 API to generate a text description of the image you want to generate, and then use that description to create the image using another tool or service.
  3. Use OpenAI's GANs: Generative adversarial networks (GANs) are neural networks that can be trained to generate new, synthetic data that is similar to a training dataset. You can use GANs to generate images by training a GAN on a dataset of images and then using the GAN to generate new images. OpenAI has released several GAN models that you can use for this purpose, including BigGAN and StyleGAN.
I hope this helps! Let me know if you have any other questions.

how do i use DALL-E API:
To use the DALL-E API, you will first need to register for an API key. Once you have your key, you can begin making requests to the API using the provided client library in your preferred programming language. You can then specify the type of image you are looking for (such as a landscape or a portrait) and the desired output format (such as a JPEG or PNG). The API will then return a list of images that match your criteria. You can then use these images as you wish.

how do I register for a dall-e api key?To register for a DALL-E API key, you will need to sign up for an OpenAI account. Here's a step-by-step guide on how to do that:
  1. Go to the OpenAI website (https://openai.com/) and click on the "Sign In" button in the top right corner of the page.
  2. Click on the "Sign up" link.
  3. Enter your email address and create a password. Click on the "Sign up" button.
  4. Check your email for a message from OpenAI with a verification link. Click on the link to verify your email address.
  5. Log in to your OpenAI account.
  6. Once you are logged in, click on the "APIs" tab at the top of the page.
  7. Scroll down to the "DALL-E" section and click on the "Get started" button.
  8. Follow the prompts to create a new API key for the DALL-E API.
I hope this helps! Let me know if you have any other questions.

generate the text to build a picture of a cabin deep in the woods, surrounded by flowers, with the warm glow of a fireplace showing through the windows. a small trail leads to the cabin.

Using the DALL-E API, you can generate an image of a cabin deep in the woods, surrounded by flowers, with the warm glow of a fireplace showing through the windows. A small trail can be seen leading to the cabin, giving it a sense of peace and tranquility. The scene is illuminated by a bright and inviting light, with a hint of smoke coming from the chimney. The perfect place for a peaceful getaway!

>> After getting an api key, and getting to dall-e I gave it a try with the above text:
I got 4 images.  you may have to be signed in to get these to link
I made public these shared links, then clicked on variations and got 4 more pictures.
All the photos were saved to a collection, which I assume is now public.
>I will try to figure out what this cost...
>think more about the next picture to generate
From Site:  
​Image generation Beta
Learn how to generate or manipulate images with our DALL·E models
IntroductionThe Images API provides three methods for interacting with images:
  1. Creating images from scratch based on a text prompt
  2. Creating edits of an existing image based on a new text prompt
  3. Creating variations of an existing image
This guide covers the basics of using these three API endpoints with useful code samples. To see them in action, check out our DALL·E preview app.
The Images API is in beta. During this time the API and models will evolve based on your feedback. To ensure all users can prototype comfortably, the default rate limit is 20 images per minute, 50 per 5 minutes. If you would like to increase your rate limit, please review this help center article. We will increase the default rate limit as we learn more about usage and capacity requirements.

Cabin in the woods using stable diffusion and dust bunny using Dall-E

Caverns on Harmony using stable diffusion