Why spotting AI images still matters

I would like to give you tips how to recognize AI generated images. They are getting more realistic, but they still tend to “cheat” on details, physics and text, especially in emotionally charged viral posts. If you know where to look, you can spot many of them in a few seconds and you can avoid sharing fake nostalgia photos, miracle stories or political information that seems true.

Note: all of the images below are AI generated.

1. Start with a quick vibe check

Before you zoom into pixels, ask a simple question: does the overall scene make sense in the real world?

• Is the story almost too perfect, dramatic or heartwarming to be true?
• Does the image hit your emotions first and only later your critical thinking?

AI images shared on social media often target nostalgia, religion or empathy, because these themes lower our guard and trigger cognitive biases like confirmation bias and familiarity.

2. Count fingers, teeth and limbs

The second way to recognize AI generated images is looking at anatomy. Anatomy is still a weak spot for many models, especially in busy scenes.

Look for:

• extra or missing fingers, fused fingers, or fingers bending in physically impossible ways
• strange hands: too big, too small, wrong angle, fingers going through objects
• teeth that form a continuous “white wall” instead of individual teeth
• too regular a row of teeth / the people in the picture have almost the same row of teeth

These errors are more common in group photos, dynamic poses or images with many overlapping limbs.

3. Inspect faces and symmetry

AI can generate beautiful faces, but they often become slightly unnatural when you look closer.

Check for:

• Eyes looking in slightly different directions, different eye sizes, off‑center pupils
• Ears that are distorted, missing, blurred into hair, or have no clear structure
• Hairlines that look painted on or impossible curls and braids

Another tell: faces that look too symmetrical and flawless, almost like a beauty filter turned to maximum.

4. Look for background and object glitches

AI tends to “give up” on background details, especially when the foreground is complex.

Look for:

• objects that float, merge, or intersect in impossible ways (a mug melting into the table, a chair leg disappearing, faces are distorted etc.)
• reflections in windows, mirrors or water that don’t match reality
• background people with melted faces, broken glasses or missing limbs

These anomalies often hide at the edges of the frame. Zooming or mentally walking through the scene helps.

5. Study textures and materials

Many models still struggle with realistic surfaces, especially when patterns or fine details are involved.

Suspicious signs:

• skin that is too smooth, plastic‑like or uniformly perfect, with no pores or subtle imperfections
• clothing with chaotic folds or fabric that doesn’t follow gravity, or patterns that bend in impossible ways
• repeating textures where there should be variation (tiles, grass, bricks, crowd clothing)

6. Check text, logos and signatures

Even that image models are more and more precise, text is a classic weak point: AI often produces spelling errors, warped letters or meaningless symbols.

Watch out for:

• street signs, shop names, T‑shirt prints, posters and book covers with garbled or unreadable text
• signatures on the corner of an artwork that look smeared, inconsistent or unreadable
• logos that are almost right, but with wrong font, missing elements, mirrored details

Even with newer models, small text in the background is still a good place to look for glitches.

7. Test the physics: light, shadows, gravity

Reality has rules. AI sometimes ignores them.

Look for:

• shadows going in different directions or not matching the visible light sources
• liquids that look solid or frozen in an unnatural way (coffee that doesn’t move, water that behaves like gel)
• objects that seem to float or rest in unstable positions without any support
• the creases in the clothes are strange

If the lighting feels movie‑perfect everywhere:

• every face perfectly lit,
• no harsh contrast,
• no real imperfections

that can also be a subtle sign.

8. Look at crowds, pets and complex scenes

AI is much better at single portraits than at big, messy situations.

Potential tells in crowds:

• background people with distorted faces, extra limbs or missing body parts
• animals with strange anatomy: too many legs, missing tails, weird eyes
• repeated clones of the same person or dog in different parts of the image

Group scenes with many interactions (hugs, handshakes, sports) are still a frequent source of glitches.

9. Watch for over‑polished, style‑averaged art

In illustrations and digital paintings, AI often produces beautiful, but generic look.

Typical signs:

• many different stylistic influences mashed together without a strong personal style
• lighting and rendering that are extremely glossy and perfect, with no sign of brushwork or consistent technique
• backgrounds that feel less carefully designed than the main character

If an artwork looks like ArtStation, Pinterest and Instagram blended into one, but you can’t feel an individual artist’s hand, it might be AI.

You can notice on AI digital paintings also similar signs which I mentioned above (like distorted text, distorted faces).

10. Combine visual clues with context

Finally, don’t stop at the pixels. Context still matters.

Ask:

• Where is the image posted? Does the account frequently share AI art or sensational content?
• Does the caption mention an AI tool, or use hashtags like #aiart, #midjourney, #aigenerated?
• Is there any source, photographer name, place or date – or is everything vague?

If you are still unsure, you can look at metadata or use reverse image search, but even without tools, these simple questions often reveal that something is off.

Summary

We know that genAI models are constantly evolving. Sometimes it’s almost impossible now to make a difference between real and fake art or photo.

I hope this guide helps you to notice the differences. You can train your eye, you can create AI images yourself and see the difference between photo and generated visual content.

You can also search for “fake or photo quiz” or “AI or Photo” and you can take quizzes – this is fun and also a good training opportunity.

The post How to recognize AI generated images without special tools? appeared first on AI Art Blog.

This AI animation short film has gone viral extremely fast, reaching more than 6 million views since May 8. This is maybe the longest AI-made 3D-style animated short film.

What makes the video impressive is the consistency of the characters and the surprisingly high visual quality. This animation have a strong sense of humor throughout the film. The comedic timing also feels natural – something that is especially important in 3D animation.

Check out the full video on x.

According to the creator, the movie was produced in just a few hours using AI tools. In traditional 3D production pipelines, modeling, rigging, animation, lighting, and rendering can take days or even weeks. As someone who previously worked as a 3D graphic artist, I can confirm how time-consuming that workflow usually is.

AI video generation is changing the animation industry rapidly. This makes it possible for creators to produce cinematic content much faster and with fewer resources.

Do you want to learn how to start creating AI videos yourself? Check out my new article about the best video generators.

The post This AI Animation Short Film Goes Viral appeared first on AI Art Blog.

Ready to connect with fellow AI artists and creators? Our Discord server is a fresh, growing space where we’re building something special together – and we’d love you to be part of it from the ground up!

Why Join?

This is a brand-new community where AI artists, traditional creators, and every curious adventurer come together to share, learn and grow. We’re just getting started, so you’ll help shape what this space becomes!

Join now to Share, Learn and Grow!

Why join our Discord community:

• Real-time discussions about the latest AI tools and techniques
• Honest feedback from fellow creators
• A judgment-free zone where all questions are welcome
• Notification about new blog articles

What’s Happening?

Weekly Challenges

Almost every week, we drop fresh creative challenges:

• AI Image Challenge – Push your prompting skills
• AI Video Challenge – Experiment with video generation
• NOAI Challenge – Digital painting and drawing

Jump in, get inspired, and grow!

Topic Channels

Dedicated spaces for every creative flavor:

• AI Image – Nano Banana, chatGPT Image, Flux, Midjourney, Stable Diffusion, and more
• AI Video – Kling, Veo, Sora, Runway, Pika, and the evolving video world
• AI General – Broader generative AI conversations
• NOAI – Traditional digital art and drawing

Prompt Sharing & Ideas

Share your best prompts in #prompt-sharing and help others unlock their abilities. Suggest article topics in #article-suggestions – your ideas could become our next blog post or YouTube video!

Growing Together

We’re building this community together! Content and features are being added regularly as we grow. Join now and help shape what this space becomes.

Join our Discord Now

See you on the server!

Discord logo from https://pngimg.com

The post Join Our Discord Community! 🎨✨ appeared first on AI Art Blog.

The goal of this article is to make a relative short summary of the best AI video generators which are available in 2026. In this case I can’t list so much free tools (like what I done with AI image generators), because most of the professional AI video generators are simply not free or they have very limited usage / credits / tokens to take a try.

However you can save tokens if you choose the right tool or the fast version of a model. This guide helps to make a good choice.

You can access many of them within an aggregate site like Leonardo.Ai. They continuously integrate the newest and most popular AI models into their app.

Prices and subscriptions

To test these tools I decided to subscribe to Canva Business. I explain why I made this decision.

I had two options:

Option #1: subscribe to the Leonardo.Ai Essential plan.

Option #2: subscribe to Canva Business, because it contains also the access to Leonardo.Ai Essential.

I chose the 2nd option because I already have a Canva Pro subscription and this upgrade is the most budget friendly option for me.

Here is a table with the approximate prices in case of monthly subscription in April 2026:

Canva Pro costs about $16 / month (so this is only a +$6 expense for me).

Tip: if you plan to use Leonardo or Canva for long time, then yearly subscription is a better deal.

If you have done everything correctly, than after Leonardo.Ai login with Canva Account you get this popup message:

And you see in the bottom left corner, that you have 8500 Fast Tokens:

The testing method

I used the same parameters and prompt for all AI video models (edit: if a specific AI video generator model is too sensitive, then some prompt refinement is needed). This uniform testing parameters allow for fair comparison.

The main parameters are:

• 16:9 aspect ratio
• 480p resolution
• generate audio – if this feature is available
• length: 8s – if possible (alternatively 5s)

The prompt

A young man in a dark wool overcoat and waistcoat walks alone through a narrow cobblestone street in Victorian London at dawn. Rain falls steadily, soaking the streets and forming rippling puddles that reflect the dim glow of gas lamps. Horse-drawn carriages pass in the distance, their wheels splashing through the wet road, while faint smoke drifts from nearby chimneys into the cool morning air. He pauses beside a small street-side tea stall, steam rising from a freshly poured cup, and turns to look over his shoulder with a calm, knowing expression. The camera slowly pushes in on his face. Cinematic lighting, shallow depth of field, shot on a vintage 50mm cinema lens, moody and atmospheric.

1. Seedance 2.0

This video generator is available on Leonardo.Ai.

A standard resolution (480p), 8 second video in Seedance 2.0 model costs 1124 tokens, but you have 150 free tokens per day.

Remark: you can save tokens if you use Seedance 2.0 fast model.

The user interface is easy-to-use:

The Result

First generation was failed due to the strict rules of Seedance. I altered the prompt slightly to this:

A lone figure in a dark wool overcoat and waistcoat walks through a narrow cobblestone street in Victorian London at dawn. Rain falls steadily, soaking the streets and forming rippling puddles that reflect the dim glow of gas lamps. Horse-drawn carriages pass in the distance, their wheels splashing through the wet road, while faint smoke drifts from nearby chimneys into the cool morning air. He pauses beside a small street-side tea stall, steam rising from a freshly poured cup, and turns slightly as if aware of something behind him. The camera slowly pushes forward, keeping his face partially obscured by shadow. Cinematic lighting, shallow depth of field, vintage film lens look, moody and atmospheric, slightly stylized.

The generation took about 460 seconds (almost 8 minutes).

My summary: Seedance in Leonardo.Ai is easy to use. This tool followed my instructions almost exactly. I like the overall mood, the music and sounds. I only miss the visible rain, but the cobblestone is wet and the wheel splashes are also visible.

2. Veo 3.1 Lite

Google’s AI video generator is available in Leonardo.Ai with various models. I selected the 3.1 Lite version, which is a fast, low-cost video generator.

I tried first the original prompt, not the fine-tuned “Seedance-version”.

Remark: the lowest resolution is 720p, not 480p, so I generated the video with that quality. The cost is only 400 tokens (standard Veo 3.1 model costs 3200 tokens!).

The video was completed in about 1 minute.

My opinion: you can clearly see, that the image quality is very good, it’s a cinematic video, but thanks to the lite version there are many inaccuracies: the floating cup, the character suddenly turning around, and the lamp appearing out of nowhere. Seedance video has a better vibe.

Maybe I try the accurate model later and update this article, but it’s very expensive (3200 tokens as I mentioned).

Veo 3.1 Lite is ideal for prototyping, but not for production-like movies.

Pros:

• good atmosphere
• visible rain
• veo accepted my first prompt

Cons:

• short generation time comes with inaccurate results and strange errors
• no background music

2. Veo 3.1 Standard

Update: I added a new test. This is the standard Veo 3.1 result (not the lite version).

The rendering time was about 2 minutes.

My short summary about Veo 3.1:

• this video is more accurate, but still has some problems:
  • in his right hand an umbrella appears first, but at the tea stall it turns to a cup
  • the Horse-drawn carriage emits smoke in the background, not a chimney

3. Runway

This test coming soon.

Unfortunately this video generator is not available in Leonardo.

4. Sora 2

Sora from OpenAI is also a popular video generator. Let’s test what it can do!

The only resolution for a 16:9 video is 1280 x 720 (HD) as you can see on the image above.

The cost of this generation is 800 tokens. (There is also a Sora 2 Pro model which costs 3x more, 2400 tokens, but we test the standard Sora 2 at this time.)

This video took about 2 minutes to generate.

The overall image quality is good, this is a moody, cinematic video with classical look. I like it. But Sora 2 does not follow the plot: just a very slight turn to the side, he does not stop at the tea stall.

And maybe I should refine the prompt, because I wanted the camera to follow the guy from behind, like in the Seedance video.

Pros:

• very good cinematic visual quality
• even footsteps have a sound

Cons:

• mid or low quality sound
• no music
• Sora did not followed the plot

5. Kling Video 3.0

I decided to use the standard Kling Video 3.0 model, because it is not so expensive and promises strong visual consistency.

The lowest resolution I can choose is HD.
This video costs 1008 tokens.

Kling needed 270 secs (about 4.5 minutes) to generate this video.

My evaluation: I like the overall mood, colors, the lens type and cinematic look. I also like the implementation of the plot. The “dramatic” pause before he turns back is perfect.

Pros:

• real cinematic look with realistic colors and depth of field
• very realistic result
• good sound quality

Cons:

• no music, but it is possible that you need to ask for this directly in the prompt

6. Hailuo 2.3

I chose the standard model, not the fast.

A big difference to other video generator models that Hailuo can use different visual styles. I tried to align the styles to the vibe of this theme.

See my image for the settings:

This video costed 224 tokens, so it’s very cost-friendly.

This 10 sec video was about 2 minutes to generate.

This video is a little bit scary, like a shot from a thriller movie. Unfortunately, the gas lamps are not lit. There is no option to generate sound.

Pros:

• a strong, thriller-like mood
• very good image quality

Cons:

• maybe the overall color is too blueish, but the reason can be the Foggy lighting style.
• the cobblestones look like artificial (computer-generated)
• no sound
  

Summary

My personal favorite is Seedance and Kling. They both gave me the result I wanted. Hailuo is also promising and cost-friendly.

AI video generators are very popular in 2026. You have the choice to select and test your favorite app. The decision is not always easy, because the quality, prompt adherence and token cost is depends on which model and parameters you choose. I hope, that this short article can help you to start with AI videos.

Later, I would like to write an article about the most popular AI video generators separately to give you prompting tips regarding camera movement for example.

I know that other AI video generators existing on the market of course, but I think that these above are way enough to experiment with.

Do you have experience with AI video generators? Share your thoughts in the comment section below.

The post The Best AI Video Generators – I tested them, here are the results appeared first on AI Art Blog.

I saw some probably fake videos on social media. They are strange videos about wild animals for example. They are interacting with people in an unusual way. A specific example: frozen animal coming back to life after a few hammer hits. This looks dramatic – and in many cases, they are fake. This AI generated content designed to trigger emotion and shares, not to show real events.

Why these videos are dangerous

• AI tools can now create very realistic videos. You believe that the animals, people in the video are real.​
• Content with strong emotions spreads faster, so fake rescues, miracles or disasters are perfect fuel for engagement and misinformation.​
• When we believe fabricated scenes, we may copy dangerous behavior in real life.
  Example: getting close to a real wild animal or spread harmful myths about nature and animals.

The internet is flooded with AI content

• Recent research by a SEO firm says that content creators write just over half of newly published online articles with the help of AI.​ (source)
• Another analysis reports that around 52% of all online written content is AI-generated. This shows that AI‑written text has quietly become the new normal. (source)
• I have no information on what percentage of images and videos are artificial.
• Experts often predict that AI may power the majority of online content, but these are forecasts, not measured reality.

How to stay skeptical

• You can question everything: people can generate text, images, and even videos with AI. (source)​
• Look for signals:
  • check sources,
  • read beyond the headline,
  • and see whether trusted entities or experts report the same story.
• Slow down: if a piece of content triggers a strong emotional reaction, take a breath before liking or sharing it.

AI slop is also a big problem in these times. Low quality and vast quantity of AI content can be harmful. It can significantly reduce the quality of Internet content.

Now you understand that more and more people create content with AI. This content can be very believable and realistic. Unfortunately, in many cases, people use it to misinform others. So it’s good to browse the internet with a healthy skepticism.

Cover image generated with Flextreme AI. For illustration purposes only.

The post Fake videos on social media appeared first on AI Art Blog.

Lot of AI image generators are still existing, but I tested Flextreme AI because it is free for personal use. Let’s see what capabilites this AI Art generator have.

Login to Flextreme AI

If you open the flextremeai.com site a Welcome page appears.
Scroll down and click on the Get Started button to open the login page.

You can use the app only with a Google account, but you don’t need to register.

After login, you see this simple and clean user interface and you can immediately start generating images:

Just type the prompt, select the aspect ratio and the number of images. Then click on Generate and Flextreme AI will do the rest for you.

Detailed, medium-length prompts also work. You don’t need to write the prompt in english. My experience is that Flextreme AI also understand german, italian and other languages. It’s worth to experiment with different languages.

Test #1 – Cinematic photo

Prompt: Cinematic photo of a red sportscar drifting in the sunset on Florida street. The sports car is taking a sharp turn. Low camera angle, full shot, motion blur, city lights, dust.

Test #2 – Landscape oil painting

Prompt: Oil painting of Swiss Alps in daylight.

Test #3 – Macro photo

Prompt: Extremely detailed photo of a beautiful blue tiger butterfly on a pink flower. Green background, shallow depth of field vivid colors, 4k fine art, sharp details.

Test #4 – Vector graphics

Prompt: Medium detailed and shaded vector illustration of a angry black cat warrior with shield and spear. He stands on his two back feets in the endless desert. Full shot, side view.

Test #5 – 3D Logo design

Prompt: A silver-cyan 3D gear logo on darkgray background with “COMPANY” written below the gear with silver sans serif font. A “YOUR SLOGAN HERE” text below the company text with serif font.

Test #6 – Using a complex prompt

My plan was to test the accuracy of the model and the prompt adherence. In fact, this is exactly the prompt from my Nano Banana Pro test:

Prompt: “Create a comic with the title: Getting started with Nano Banana Pro. Panel 1: A mobile interface on Gemini, rendered in a poetic watercolor-ink style with fine ink outlines and soft, bleeding washes. The interface is friendly and a hand painted with expressive brushwork taps a prominent button labeled “Create image”.

Above the button it should say “Choose your Model” then below there should be a checkbox that says “Thinking with 3 Pro” Muted greys and blues dominate the background. The button has a vivid yellow accent. “ Select the Thinking with 3 Pro model” and tap “Create image” to begin. Panel 2: A cheerful person is depicted adding their selfie from the phone’s camera. The user’s face is drawn with soft outlines and warm pastel colors, while the phone and UI maintain the delicate water-ink aesthetic. Visible paper grain adds to the texture.

Panel 3: The person thinks about what to create. In the background, different options are visualized to show what they’re thinking, including — them as a plushie, them with a mohawk hairstyle, and a figurine. These options are clearly rendered behind the person in the same style as the rest of the comic.

Panel 4: The person is shown adding a style prompt, with a speech bubble saying “Transform me into a watercolor painting”. The text is integrated into the panel’s watercolor-ink look, and the interaction feels natural and intuitive.

Panel 5: The person is seen editing the image by simply typing into Gemini. The scene captures the ease of this interaction, with the final edited image, now in a watercolor style, appearing on the screen. The overall tone is friendly, instructional, and inspiring. It feels like a mini tutorial comic, all conveyed through the specified delicate water-ink illustration style. Make the aspect ratio 16:9.”

Test #7 – 3D render

Prompt: 3D render of an enchanted treetop forest village with rope ladders on a summer evening with fireflies illuminating it during the blue hour

Test #8 – Pencil sketch

Prompt: A detailed pencil sketch of a flying dragon over the rocky mountains.

Troubleshooting

As I tested this app I experienced sometimes little but annoying bugs. If I have the solution, then I will share it here.

Issue #1 – Login service

Solution: just hit the refresh button or F5 key to reload the page. I’m sure that the Google login button should then appear immediately.

Issue # 2 – Strange results

Symptom: Strange text and irrelevant result.

Solution: Log out and log in again, refine your prompt.

Summary

Althrough the Flextreme AI art generator is still in alpha phase, it already works very good for basic tasks. In most cases the results are quite convincing. Below, I summarize my experiences in bullet points.

However, be aware that Flextreme AI does not save your generated images on their server.
Instead, they are storing them only in your browser session, as far as I understand. Therefore, I strongly recommend to download the images as soon as possible. Additionally, make sure you log in on the same computer or mobile device and use the same browser if you want to access them again.

Pros:

• easy to use interface
• fast image generating
• 15 images per day for free
• the minimum number of images is 1
• your generations are private

Cons:

• no pro plan / subscription
• images are for non-commercial use only
• minor application issues sometimes (eg. login)
• strange, irrelevant results sometimes
• no community gallery
• no extra features like:
  • negative prompt
  • AI art generation from reference image,
  • remove background,
  • inpainting,
  • selecting AI model
  • image enlargement

The post I tested Flextreme AI – Images and prompts are included appeared first on AI Art Blog.

Google’s Nano Banana was released in this year, August. I missed to write an article about it so now I tested Nano Banana Pro.

How to try it out?

Nano Banana Pro is available in Google Gemini. You will see this starting screen when you open the Gemini webpage:

I would like to note that if you click on the Try It link at the top of the page, then Banana will load a sample prompt and generates an image, which already counts towards your 3 image limit per day.

Click on the Create Image button to activate the Nano Banana Pro image model.

Note: You can create only 3 images / day for free.

Test #1 – The inbuilt sample prompt

The prompt is very detailed and long, so I pasted it with a small sized font:

“Create a comic with the title: Getting started with Nano Banana Pro. Panel 1: A mobile interface on Gemini, rendered in a poetic watercolor-ink style with fine ink outlines and soft, bleeding washes. The interface is friendly and a hand painted with expressive brushwork taps a prominent button labeled “Create image”. Above the button it should say “Choose your Model” then below there should be a checkbox that says “Thinking with 3 Pro” Muted greys and blues dominate the background. The button has a vivid yellow accent. “ Select the Thinking with 3 Pro model” and tap “Create image” to begin. Panel 2: A cheerful person is depicted adding their selfie from the phone’s camera. The user’s face is drawn with soft outlines and warm pastel colors, while the phone and UI maintain the delicate water-ink aesthetic. Visible paper grain adds to the texture. Panel 3: The person thinks about what to create. In the background, different options are visualized to show what they’re thinking, including — them as a plushie, them with a mohawk hairstyle, and a figurine. These options are clearly rendered behind the person in the same style as the rest of the comic. Panel 4: The person is shown adding a style prompt, with a speech bubble saying “Transform me into a watercolor painting”. The text is integrated into the panel’s watercolor-ink look, and the interaction feels natural and intuitive. Panel 5: The person is seen editing the image by simply typing into Gemini. The scene captures the ease of this interaction, with the final edited image, now in a watercolor style, appearing on the screen. The overall tone is friendly, instructional, and inspiring. It feels like a mini tutorial comic, all conveyed through the specified delicate water-ink illustration style. Make the aspect ratio 16:9.”

And this is the result:

Click on the image to enlarge

It’s pretty convincing. The typography is perfect. I don’t see any typos or other problems on the picture.

Remark: Gemini also included the banana emoji in the prompt, but I had to delete it to able to save the blogpost.

Update: I tried the same prompt with ChatGPT (GPT Image 1.5):

This results is impressive too. I think that Nano Banana Pro has a new rival.

Test #2 – Infographic

I used this prompt:

Create an infographic-like image of the most popular brushes in similar style as on the attached example picture, but with landscape aspect ratio (eg. 16:9). The brushes are from top to down: 2B Pencil, Ballpoint Pen, Soft Airbrush, Watercolor brush, Acryl brush, Oil paint, Calligraphic brush. Each row contains the stroke of the brush or tool with realistic and relevant color. Next to the stroke is the photorealistic illustration of the tool (for example it is clearly visible that the brush stroke was painted with the brush) and a sample image that was drawn with the tool. The image should also contain the name of every tool with a good readable darkbrown coloured font. There is also a darkbrown coloured victorian ornamental frame around the infographic.

The reference image was Krita’s first picture about brushes.

This is the generated image:

The result is impressive! Gemini precisely followed my instructions: text, tools, samples, structure, victorian border: everything is on the picture.

Using Banana in Leonardo.Ai

You can also try it in Leonardo.Ai, but in the free plan you have only 150 tokens. One image with Nano Banana Pro costs 140 tokens, so you can generate only 1 image.
Tokens are resetting in 12 hours, so you have a 2 image daily quota.

In Leonardo free plan you can use 1 reference image. I made a test with it.
This is the starting real estate interior photo:

This is a very simple prompt to replace some objects on this living room photo:

Replace the pictures on the wall with photos from Gobi desert. Replace the couch with a darkbrown leather couch. Change the wall colour to matching bluegreen, increase the density of the foliage.

And this is the final result:

I think it’s pretty good. Nano Banana also was able in August to make this kind of change on a picture – I think.

The best thing is, that it doesn’t change the alignment or form of the objects in the scene, it changes only what you define in the prompt.

Let’s summarize what are the new features of the 2nd version of Nano Banana.

Summary

Nano Banana Pro is a revolutionary model. It’s fantastic and a little bit scary at the same time. Images made with this new model are more realistic and hard to make a difference between real photo an AI generated image. In another article I will post images which compare the standard and pro version of Banana.

The main new features are:

• enhanced prompt adherence
• better consistency (you define what to change or replace, the other objects and forms remaining intact)
• ability to create complex text and image combinations on one picture, like:
  • infographics
  • comics
  • accurate scientific graphics
  • easily change the mood, like: lighting, season, camera angle etc.

The post I tested Nano Banana Pro – Check the Results appeared first on AI Art Blog.

Intro

Sometimes I’m really surprised by how quickly the years go by. It was just “yesterday” when I wrote the first Welcome post, in which I described why I created this site: I wanted a place where I could talk about the world of AI in a clear and honest way, where I could show how to use these tools well, and where I could also express my own curiosity. A small online place where anyone can come and learn more about where this is all going mostly from the perspective of visual art.

The Past

I’ve learned a lot in the past two years – not only about technology, but also about how to build a website from scratch. I did everything myself: from design to research to writing articles. Of course, this is often time-consuming, especially since I do it in my free time, but I always enjoy sitting down to write. This blog is not work for me, but creation, relaxation and continuous development.

The Present and the Future

There are currently about thirty posts on the site, and the best thing is that I haven’t run out of ideas at all. For example,

I’m already working on some topics like:

• a Prompting Guide,
• several articles about Leonardo AI,
• Gemini (incl. Nano Banana Pro),
• I’d like to test Flextreme AI, a new free AI image generator (flextremeai.com),
• I have articles planned on AI video production,
• and of course the NoAI topic, which seems particularly interesting to many of you.

I feel that the next two years will be at least as exciting as the last two.

I’m also thinking about creating an open, but of course structured community on Discord.
Update: the Discord Community is ready, feel free to join!

I continue to consider it important to use genAI consciously and moderately. I’ve already written about environmental and other impacts and risks in some articles.

How can you Support

Finally, an important but somewhat sensitive topic for me: maintaining a blog comes with costs, and I would like to keep the site free from advertisements – I don’t want intrusive ads that take away the focus. If you would like to support my work and contribute to the operation of the site, you can do so with a PayPal donation. I am sincerely grateful for all the support – and I promise to continue building this little AI island with the same enthusiasm.

Thank you for being with me!

Cover image created with Flextreme AI

The post AI Art Blog is 2 years old appeared first on AI Art Blog.

The brand new Affinity app has arrived.
You may know that Canva acquired Serif (the developer of Affinity products) some months ago. Now it seems that it is possible to use the Canva desktop app for free. This is the new Affinity.

What are the most important changes?

The new software includes the 3 previous ones in one app.

You know that up to and including Affinity v2, these 3 software can be used separately:
Affinity Photo – Photo editing and digital painting
Affinity Designer – Vector graphics
Affinity Publisher – Publication editing

The new Affinity includes these in one. Switching between the 3 (or even more) so-called Studios is possible in the upper left corner.

The new Affinity also includes Canva AI, but its use is completely optional.

In addition, the app has Slice, Retouch and Colour Grading studios.
You can also create your own Studio, which can be completely customized.

You can find the most frequently asked questions on the official website, here is an excerpt:

Can I still use the v1 and v2 software?
Yes, support will continue and the activation server will remain available, but new licenses for v1 or v2 can no longer be purchased.

Am I able to open and edit the files created with Affinity v1 and v2 in the new app?
Yes, the new desktop version can open them.

Can I re-download my previously purchased Affinity products?
Yes, you can download them by signing-in to your account.

New features in nutshell

• pigment blend – a different type of transition option for gradients
• mesh fill type – a mesh can be used to fill shapes with a gradient
• an adjustment brush has been added to Pixel studio
• live filter brush – live filters can be painted directly on the image with a brush
• new filters: glitch – aberration, distortion, pixelate and similar effects can be added to the image in a non-destructive way
• A big new feature in Layout studio is that you can vectorize pixel images (this is called tracing, which has existed in Corel Draw for a long time, for example)
• in general, it is easier to find the panels we need (panel search function)
• quick menu: right click on the pasteboard to show it

A brief overview of AI Studio:
general AI functions are available, such as:

• generative expand
• generative fill
• generative edit
• generate image
• select subject
• remove background
• portrait blur and lighting

AI studio is available with Canva Premium Plan.

No internet connection is required to use the new Affinity, only when logging in for the first time and downloading the app.

Personally, I still don’t fully understand how they made this great software free.
Which partly explains this decision, that it seems that the AI ​​studio will be a paid service.

In the first look video, further developments were also briefly introduced:

• live blend tool
• creating custom scripts (programming)

Conclusion

Overall, these new features are interesting and I definitely recommend trying the new Affinity.

The new app can be downloaded from https://www.affinity.studio/ for Windows and macOS users. We should wait a little for the iPad app.

For your information: when you first launch the app you should decide whether you want to share usage data (turned off by default):

I created the cover image with the new Affinity desktop app. (I used a custom font with glitch filter and one layer with motion blur, other layer with gaussian blur effect)

The post New Affinity is available for free appeared first on AI Art Blog.

This is a collection of so called NoAI Tools. NoAI means, that the software, application or service does not use artificial intelligence to produce the end result. You can use them in your daily creative work. I try to continuously verify and update this list.

I would like to list here the most useful and budget-friendly (possibly free) tools for graphic design.

3D Software

Blender – an open source creative software for modeling, sculpting, lighting, rendering of 3D images. Completely free. It has a long learning curve, but lot of free learning materials are available on the web.
It contains also a professional video editing tool.

Digital painting

Krita – Free and open source painting software. User friendly UI, huge set of brushes, ability to create tilable textures and patterns and a lot more.

Procreate – this software made for Mac users. Not free, but on low budget if you have an Apple product. The Procreate team clearly defines that they don’t plan to implement any generative AI functions to their apps, which can really support the real artists and creative, human made artwork. Read about this on their the official site.

Sketchbook – I really like this drawing software because of the good drawing tools like pencil, pens, brushes and much more. If you have a stylus then using this tool can be a very good drawing experience. Sketchbook is available for desktop and mobile devices (Mac and Android and even Windows). Free for iPhone, iPad and Android devices. It has a Pro Mac version which is not free.

Photo editing

Canva is an online, web-based graphic design and photo editing tool. Canva has a free version, but it has also premium plans. This software contains an inbuilt AI image generator (with limited usage in the free plan), so not clearly a “noAI” tool, but it has many traditional design features.

GIMP – free image editing and painting software. Similar to Adobe Photoshop and Affinity Photo. Adobe and Affinity products are more user-friendly, but GIMP is free and it doesn’t have AI features, just the classic selecting and painting tools and image filters.

Web design

Placeholder image generator – use this excellent free tool if you would like to create photos in different categories, in custom sizes for your website design or prototype. More image formats are available like jpeg, png and even webp.

Vector graphics design

Affinity Designer – not free, but relatively cheap and not subscription-based.

Inkscape – this is probably the most popular and free vector graphics editor for Windows, macOS and Linux

Video editing

Shotcut – free and open source video editor. Fast cutting, wide range of video and audio effects, 4k video editing and much more. I recommend to watch the tutorials on the official site to get familiar with the UI.

Do you have a great tool which is not on this list? Write a short sentence about it and send the link in the comment section below or send it to our mail address: hello at aiartblog.com.

The post Collection of NoAI Tools appeared first on AI Art Blog.