Battle of the AIs: EP2 A man in a café, smiling

We're back with the Battle of the AIs. The aim of this series is to bring you a comparison of the most diverse image AIs in the world. We'll use the same prompt for all the images, generating 8 results and choosing the 4 best to share in this article.

How do the evaluation categories work?

[one_half animation="fade-in" delay=""]

[toggles accordion="false"] [toggle title="Visual Quality" color="Accent-Color" id="b1″] Evaluate AI's ability to generate quality images, with improved strokes, accurate colors and low levels of unwanted artifacts. [/toggle] [/toggles]

[toggles accordion="false"] [toggle title="Image Details" color="Accent-Color" id="b1″] Check if the AI is able to detail well the scenery, clothes and everything that surrounds the main character of the prompt[/toggle] [/toggles]

[/one_half]

[one_half_last animation="fade-in" delay=""]

[toggles accordion="false"] [toggle title="Contextual Coherence" color="Accent-Color" id="b1″] Check if the AI is able to generate images that fit the context provided or that have relevance and continuity within the requested theme[/toggle] [/toggles]

[toggles accordion="false"] [toggle title="Safe for Work (SFW)" color="Accent-Color" id="b1″] Evaluates the AI's ability to generate images of non-sensualized people (among other categories), i.e. Safe for Work[/toggle] [/toggles]

[/one_half_last]

Prompt: A guy in a cafe, smiling (A man in a cafe, smiling)
Complexity: 3 (1 point for character. 1 point for location. 1 point for expression)
Format: 1:1
Location: All AIs were generated at https://tess.pareto.io

Let's get to the results!

MidJourney v4

Midjourney is an Artificial Intelligence that allows users to generate high-quality images from textual descriptions. Midjourney uses a large language model to generate images that are accurate and consistent with the user's instructions.

Currently the most popular image AI in the world, with just over 15M users. The tool has an average price of $30 per month, with a limitation on generation speed after a certain period of time using the tool.

Integrated with Tess AI: [icon color="accent-color" size="tiny" icon_size="" image="fa-check"] Yes. You can generate images with MidJourney within Tess AI

[one_fourth boxed="true" animation="fade-in" delay=""]Visual Quality: Good [/one_fourth]
[one_fourth boxed="true" animation="fade-in" delay=""]Image Details: Good [/one_fourth]
[one_fourth boxed="true" animation="fade-in" delay=""]Contextual Coherence: Amazing [/one_fourth]
[one_fourth_last boxed="true" animation="none" delay=""]Safe for Work (SFW): Incredible [/one_fourth_last]
[milestone symbol_position="after" color="accent-color" symbol_alignment="default" number="80″ subject="Final Score" symbol="%" number_font_size="" symbol_font_size="36″]

[icon color="accent-color" size="tiny" icon_size="" image="fa-comment"]Comments: Although these 4 photos were good in quality, the rest have quite a few deformities. Even in these 4 images, you can see some deformities and missing details. One example is the fingers of the hand in image 4. In addition, photo 3 shows the body relatively small in front of the head. The hands in picture 2 are also deformed. Another element we noticed was the duplicate presence of cups.

[divider line_type="small" custom_height="24″]

Stable Diffusion

With 5.3M visits a month, Stable Diffusion is one of the most popular image AIs on the planet and one of the forerunners of all this technology.

Integrated with Tess AI: [icon color="accent-color" size="tiny" icon_size="" image="fa-check"] Yes. You can generate images with Stable Diffusion within Tess AI

[one_fourth boxed="true" animation="fade-in" delay=""]Visual Quality: Good [/one_fourth]
[one_fourth boxed="true" animation="fade-in" delay=""]Image Detail: Average [/one_fourth]
[one_fourth boxed="true" animation="fade-in" delay=""]Contextual Coherence: Incredible [/one_fourth]
[one_fourth_last boxed="true" animation="none" delay=""]Safe for Work (SFW): Incredible [/one_fourth_last]
[milestone symbol_position="after" color="accent-color" symbol_alignment="default" number="75″ subject="Final Score" symbol="%" number_font_size="" symbol_font_size="36″]

[icon color="accent-color" size="tiny" icon_size="" image="fa-comment"]Comments: The images show more apparent deformities, especially in the arms, eyes and mouths. We also noticed repeated items, such as cups.

[divider line_type="small" custom_height="24″]

DALL-E 2

DALL-E 2 is an AI tool that can generate realistic images from text prompts. For example, you can ask DALL-E 2 to generate an image of a cat sitting on a piano, and it will generate an image of a cat sitting on a piano.

DALL-E 2 is still in development, but it has the potential to be a powerful tool for artists, designers and creatives. This is the image-generating AI from Open AI, the largest AI company on the planet.

Its average price ranges from $30/m to $60/m, allowing the use of the most different prompts.

Integrated with Tess AI: [icon color="accent-color" size="tiny" icon_size="" image="fa-check"] Yes. You can generate images with DALL-E 2 inside Tess AI

[one_fourth boxed="true" animation="fade-in" delay=""]Visual Quality: Average [/one_fourth]
[one_fourth boxed="true" animation="fade-in" delay=""]Image Detail: Fair [/one_fourth]
[one_fourth boxed="true" animation="fade-in" delay=""]Contextual Coherence: Fair [/one_fourth]
[one_fourth_last boxed="true" animation="none" delay=""]Safe for Work (SFW): Incredible [/one_fourth_last]
[milestone symbol_position="after" color="accent-color" symbol_alignment="default" number="45″ subject="Final Score" symbol="%" number_font_size="" symbol_font_size="36″]

[icon color="accent-color" size="tiny" icon_size="" image="fa-comment"]Comments: The AI definitely didn't manage to build the café scene. However, it managed to understand the facial expression requested very well. A positive point is that there are no deformities.

[divider line_type="small" custom_height="24″]

OpenJourney

OpenJourney is an AI-generated image development platform that helps you create high-quality images quickly and easily.

Our simple yet powerful API lets you control every aspect of the image generation process, from text input to output style and resolution.

With 26.2k visits per month, OpenJourney has become one of the most widely used AI APIs. The average cost of the API ranges from $50/m to $100/m.

Integrated with Tess AI: [icon color="accent-color" size="tiny" icon_size="" image="fa-check"] Yes. You can generate images with OpenJourney within Tess AI

[one_fourth boxed="true" animation="fade-in" delay=""]Visual Quality: Good [/one_fourth]
[one_fourth boxed="true" animation="fade-in" delay=""]Image Detail: Fair [/one_fourth]
[one_fourth boxed="true" animation="fade-in" delay=""]Contextual Coherence: Incredible [/one_fourth]
[one_fourth_last boxed="true" animation="none" delay=""]Safe for Work (SFW): Incredible [/one_fourth_last]
[milestone symbol_position="after" color="accent-color" symbol_alignment="default" number="70″ subject="Final Score" symbol="%" number_font_size="" symbol_font_size="36″]

[icon color="accent-color" size="tiny" icon_size="" image="fa-comment"]Comments: Some points were lost in the "Details" category due to the constant presence of small deformities and duplicated items. The AI also had some proportion errors.

[divider line_type="small" custom_height="24″]

Tess AI Dream Pro V2

[one_fourth boxed="true" animation="fade-in" delay=""]Visual Quality: Good [/one_fourth]
[one_fourth boxed="true" animation="fade-in" delay=""]Image Details: Good [/one_fourth]
[one_fourth boxed="true" animation="fade-in" delay=""]Contextual Coherence: Amazing [/one_fourth]
[one_fourth_last boxed="true" animation="none" delay=""]Safe for Work (SFW): Incredible [/one_fourth_last]
[milestone symbol_position="after" color="accent-color" symbol_alignment="default" number="80″ subject="Final Score" symbol="%" number_font_size="" symbol_font_size="36″]

[icon color="accent-color" size="tiny" icon_size="" image="fa-comment"]Comments: This AI has a very interesting versatility - something very useful in AIs. It's common for AIs, for one prompt, to have 4 very similar versions - which typically isn't desirable. Ideally, the AI should be versatile and able to present even different traits - so that the user can define the one they like best and eventually work on image-to-image prompts, i.e. working on top of the image they like best. Another positive point was the fact that it didn't link the Café establishment with a coffee in the hands.

[divider line_type="small" custom_height="24″]

Tess AI Dream Pro V1

[one_fourth boxed="true" animation="fade-in" delay=""]Visual Quality: Average [/one_fourth]
[one_fourth boxed="true" animation="fade-in" delay=""]Image Detail: Fair [/one_fourth]
[one_fourth boxed="true" animation="fade-in" delay=""]Contextual Coherence: Incredible [/one_fourth]
[one_fourth_last boxed="true" animation="none" delay=""]Safe for Work (SFW): Incredible [/one_fourth_last]
[milestone symbol_position="after" color="accent-color" symbol_alignment="default" number="65″ subject="Final Score" symbol="%" number_font_size="" symbol_font_size="36″]

[icon color="accent-color" size="tiny" icon_size="" image="fa-comment"]Comments: Some points were lost in the "Details" category due to the constant presence of small deformities and proportion errors.

[divider line_type="small" custom_height="24″]

Tess AI Dream V1

[one_fourth boxed="true" animation="fade-in" delay=""]Visual Quality: Good [/one_fourth]
[one_fourth boxed="true" animation="fade-in" delay=""]Image Detail: Average [/one_fourth]
[one_fourth boxed="true" animation="fade-in" delay=""]Contextual Coherence: Incredible [/one_fourth]
[one_fourth_last boxed="true" animation="none" delay=""]Safe for Work (SFW): Incredible [/one_fourth_last]
[milestone symbol_position="after" color="accent-color" symbol_alignment="default" number="75″ subject="Final Score" symbol="%" number_font_size="" symbol_font_size="36″]

[icon color="accent-color" size="tiny" icon_size="" image="fa-comment"]Comments: Some points were lost in the "Details" category due to the duplicate formation of teeth in some photos. Overall, the photos generated were very good. Surely with a few more attempts we could achieve incredible results.

[divider line_type="small" custom_height="24″]

Tess AI Dream V2

[one_fourth boxed="true" animation="fade-in" delay=""]Visual Quality: Incredible [/one_fourth]
[one_fourth boxed="true" animation="fade-in" delay=""]Image Detail: Good [/one_fourth]
[one_fourth boxed="true" animation="fade-in" delay=""]Contextual Coherence: Amazing [/one_fourth]
[one_fourth_last boxed="true" animation="none" delay=""]Safe for Work (SFW): Incredible [/one_fourth_last]
[milestone symbol_position="after" color="accent-color" symbol_alignment="default" number="90″ subject="Final Score" symbol="%" number_font_size="" symbol_font_size="36″]

[icon color="accent-color" size="tiny" icon_size="" image="fa-comment"]Comments: The composition of the location lacked a bit of detail to really classify it as incredible.

[divider line_type="small" custom_height="24″]

Tess AI Dream Realistic Pro

[one_fourth boxed="true" animation="fade-in" delay=""]Visual Quality: Incredible [/one_fourth]
[one_fourth boxed="true" animation="fade-in" delay=""]Image Detail: Incredible [/one_fourth]
[one_fourth boxed="true" animation="fade-in" delay=""]Contextual Coherence: Amazing [/one_fourth]
[one_fourth_last boxed="true" animation="none" delay=""]Safe for Work (SFW): Incredible [/one_fourth_last]
[milestone symbol_position="after" color="accent-color" symbol_alignment="default" number="100″ subject="Final Score" symbol="%" number_font_size="" symbol_font_size="36″]

[icon color="accent-color" size="tiny" icon_size="" image="fa-comment"]Comments: In addition to incredible results, this AI was even able to vary the people in the photo, which definitely made it the champion of this battle!

[divider line_type="small" custom_height="24″]

Result of the Battle of the AIs