Home Image AI Create Your Image AI with Tess AI

Create Your Image AI with Tess AI

0

We recommend that you start your creation journey by exploring the tutorial Create your Text AI with Tess AIbut if you're already familiar with it, let's learn how to build an image AI with your own style.

Welcome to the fascinating world of Tess AI, the leading AI platform in Latin America. Here, users can create and publish their own AIs in seconds! All connected to the biggest AI platforms, such as ChatGPT, LLaMA (from Meta), Bard (from Google), Dall-E and MidJourney.

There are endless possibilities. Creating logos, realistic images, sales emails, advertising campaigns and, above all, what we're going to cover in this article: the possibility of creating your own image AI! Read on to find out more about Tess AI and its fascinating creation capabilities.

 

Quick Navigation

 

Creating an Idea

Creating an Image Template

1 - Detailing the Model

2 - Defining the Inputs

3 - Inserting Steps

4 - Ending the Prompt

Review

 

Creating an Idea

The command prompt is the central part of your Artificial Intelligence. It will dictate what is created. So let's start with it.

Let's say you have the idea of creating images using a "Steampunk" style.

To do this, we'll make a simple command for the AI. As a test, we'll try to create a dog, so the prompt will look like this:

"a dog Steampunk style and high detail".

For best results with image prompts, always choose to create the prompts in English.

 

Test Your Prompt with Tess AI

With your initial prompt in hand, simply test your idea with the help of Tess AI by selecting "For Image" from the "AI Playground" menu.

Then select the Tess image template you want to test and enter the prompt you developed.

Check that the images Tess brought to your prompt were satisfactory, otherwise you'll need to refine them. Repeat this step as often as necessary.

The Prompt in this case was satisfactory, so we'll continue with it. So the prompt will initially be:

"**idea** Steampunk style and high detail"

 

Creating an Image Model with Tess AI

Now that the prompt is functional, it's time to bring a model to life . The first step is to access your templates area in the "My AIs" menu.

These initial steps are identical for both text and image templates. But let's recap here.

Click on "Add template" and start creating your personalized template.

 

1 - Detailing the Model

In this step you should create the initial details of the template, the name of the template, a short description and a long description to make it easier to understand.

Next, define whether your template will be public, unlisted or private. This will define who will have access: all users of the platform, only those who have the link or just you.

Set the template type to "Image" and choose which template you want to use. Remember that the template must be the same as the one you selected during the tests.

All the image models will soon be detailed here.

Finally, add details such as a cover, links to tutorials if you have created one, and categories. 

The specifications indicated for the cover are 3840 x 768 px, it is worth remembering that the platform has a margin that adjusts according to the type of screen. 

It is therefore advisable not to place text elements on the cover. For example, take a look at this image created to insert as the cover of a template and its display on the template:

Cover

Exhibition

If you leave the cover off, the template will display an automatic template instead. It's worth remembering that the cover is also an attractive element for differentiating your template through the thumbnails of the listing, as it appears when you click on "Home".

In the case of the categories, you should choose the ones that best suit the function of your model, just choose one or more of the ones available on the platform.

2 - Defining the Inputs

It's at this stage that we create the fields that users have to fill in. In the case of this prompt, it's the users' "Ideas" that will be transformed into art.

Remember that you can test other types of input in your template, just select the one that best suits your project.

See the options:

Input Field: By selecting this type, you enable the user to enter short texts, for more objective answers.

Textarea field: With Textarea active, you enable the possibility for the user to insert large blocks of text, if your template asks for a lot of information.

Single checkbox: if you want to limit the user's response to just one from a list of options, simply enter each of them separated by a comma in the entry description.

Multiple selection box: Now, if you don't want to limit the user's response, create a list of options, inserting each one separated by a comma in the entry description. The user will be able to choose more than one option.

Upload File: this type of input works very well for inserting audio files, try creating transcription templates with advanced AI steps.

 

3 - Inserting Steps - Advanced

If you want to create complex templates with more than one step, you can use Advanced Steps for this. Now, if this is your first time creating a template in Tess, skip to the next item.

You can stipulate the type of stage, choosing from the many options available:

Get Google Sheets Values: Gets data from a Google Sheets matrix defined by you.

Amazon Products: searches Amazon and returns the products to the template.

Google Sheets to Google Sheets: uses data from a Google Sheets spreadsheet defined by you and triggers a command for Tess to generate a result for each row.

Search Related Questions: performs a Google search and brings up data on related questions.

OpenAI: a new step for obtaining the result of a prompt. It can be used, for example, to translate input groups.

Google Trends: makes a query for a specific term in Google Trends. It can bring up Geolocation data, Temporal data and Weekly Average, for example.

Search Location Google Maps: performs a search on Google Maps and obtains data on businesses in the region.

Find Product Sellers: searches Google Shopping and obtains data from sellers of a specific product

Google Search Shopping: performs a search on Google Shopping and obtains data from the first players located.

Google Search Sports: brings up data and a specific team with match information.

Google Organic: performs an organic search on Google.

Google Autocomplete: uses Google's intelligence to obtain larger searches that are normally made from a smaller term.

Google Jobs: does a search for jobs on Google.

Google Travel Planner: searches for destinations and price lists based on a city of origin.

Google Available On: does a Google search for a movie, series or song to get data on where the content is available.

Audio Transcription: Analyzes an audio file to transcribe its content.

Pareto is bringing more and more connections so that the sky is the limit when building your automations. All these steps will be elaborated in another article.

But for the creation of this template it is important to note that your audience will probably fill in the Input Fields in Portuguese, we will use an Advanced AI Step to translate from Portuguese to English. In this case, we'll call it "idea".

Use the connection to GPT 3.5 to force a translation of the input field, note that the name between ** must be identical to the name of the input you defined for the user to fill in. 

The name of the step has been set to "Translate", it is this field that will be used in your final prompt.

Notice that after requesting the translation via the prompt, we insert the "Answer:" field, so that the AI can insert the direct answer into the template command.

 

4 - Ending the Prompt

This is the final stage in the creation of your AI model, where you'll put in the command that the AI should carry out.

The Created Entries are the elements you entered in step 2. Entry Groups. If you used item 3. Advanced Steps, they will also appear here.

This way, all you have to do is insert the tested Prompt and use the Entries created for customization.

In this template we have inserted an advanced step for the translation, it is this information that we want to insert in the prompt.

Therefore, to insert the translation into your prompt written in English, you should only enter the field that has been set to "translate" to avoid repeating data:

Note that if you don't use the Created Entries inside the Prompt, what the user types in the Input Fields won't be used. So make sure it is filled in exactly as in the "Input Fields" box, including the **asterisks**.

 

Review

Once the template has been created, it will be reviewed by the Pareto team who, if they find no discrepancies, will approve it for use.

But you can use it and test it while it's being approved. Just click on the link provided by the Tess AI platform. The example template for this article looks like this:

 

For more details on how to create prompts to generate images, we recommend watching the webinar "Creating Incredible Images with Tess AI", led by Rica Barros, CEO of Pareto. Don't miss this opportunity to deepen your knowledge!

 

Try Creating Your Own AIs

Congratulations on taking the first step on this exciting journey with Tess AI! You now have the skills to design your own artificial intelligences and automations, connecting to leading platforms such as ChatGPT, Lllama, Bard, Dall-E and MidJourney.

Keep exploring, experimenting and collaborating with our growing community of over 100,000 users. Your creations have the potential to stand out, and soon, you'll be able to monetize every time someone uses your AIs.

Thank you for choosing Tess AI as your partner on this exciting journey! Be sure to follow our updates and resources as we continue to expand the possibilities of artificial intelligence.

Don't have an account? Try Tess AI for free. Discover the unlimited potential of the world's greatest artificial intelligences and take your experience to new heights! Enjoy up to 150 free images to try out.

Want some image template inspiration? Go to: 36 Prompts to Create Amazing Images with Tess AI, the Pareto AI

Exit mobile version