Pixlr AI image generator gives you 20 free credits, which is enough for 20 image generations. Every time you hit the Generate button, 4 images will be generated. It costs 4 credits (1 credit per image).

I used some basic prompts. These prompts were based on those written in the Pixlr newsletter. Of course, I changed them a bit to make the end result varied.

Image properties:

• Aspect ratio: 1:1
• Image dimensions: 1024 x 1024 pixels
• File format: .png

I used the default settings (No Style, No Color, No Lighting, No Composition) and I gave only the prompts below and after that I clicked the Generate button.

You can view the full size test images on my Facebook page.

Test #1 – Dragon on the cliff

Prompt: A dragon sits on a rock and overlooks a huge medieval city. Use deep greens and yellows for the scales and make sure the city below reflects the past.

Result: Beautiful, detailed, 2D painting style dragon, rich in colors. Maybe he needs some color adjustment. Drawing a dragon is not an easy task because of its complexity.

The last image needs some retouch (separate castle at the bottom right corner)

Test #2 – White Wolf

Prompt: A white wolf with shiny iridescent fur standing in a mystical moonlit forest with millions of tiny stars shining in the sky.

Result: interesting, dreamlike, mystical wolf images. A little too much purple and pink in the generated images imho. I would like it better with a bluer color scheme. My favorite is the second creation.

All wolves are four-legged and I did not use negative prompts.

Test #3 – Zombie silhoutte

Prompt: A silhouette of a zombie approaches the viewer on a full moon night in an eerie, fog-shrouded forest. Pale bluish color scheme.

Result: I like the color tone and the overall mood of the images. It was a good idea to describe the colors in the prompt. The second picture turned out to be scary enough. The last image has a strong, centered composition. Zombie eyes can be made more dramatic with a small brush in an image editing software.

Summary

Pixlr AI Image generator is a pretty interesting app with good image generation capabilities. The images can be customized prior to the generation with styles, color tones, lighting and composition. These customization techniques was not the topic of this article. I will test the custom features maybe later.

Tip: You have also the opportunity to post process the image. Just click on the paint bucket icon and then choose the AI Tools from the left toolbar.

Note: All AI tools costs additional credits.

As I scrolled the gallery on the Pixlr site I noticed that many of the generated images have anomalies like humans with 6 fingers, not physically accurate electronic devices, unwanted objects or inaccuracy in texts. These are other areas where Pixlr can make further enhancements.

Notice: I don’t tested the negative prompt feature which maybe can solve some of this common problems.

What you think about this tool? Share your thoughts and experience in comments!

Thank you for reading this article! Don’t forget to check other AI image topics!

The post AI Image Generator Test – Pixlr appeared first on AI Art Blog.

Metatags in Suno are special instructions embedded within song lyrics, enclosed in square brackets, to help customize musical elements such as instruments, voices, and song sections. They allow for precise control over the generated music, aligning it with your creative vision.

Read more about the v3.5 model of Suno and it’s new features.

Basic Guidelines

1. Keep It Simple: Use a maximum of three words per tag for clarity.
   • Good Example: [Syncopated Bass]
   • Bad Example: [call and response between percussion and bass]
2. Tagging Sections: Pair a brief style description with a noun indicating the instrument or voice.
   • Example: [Soft String]

Types of Metatags

1. Song Structure Tags: Define parts of the song.
2. Instrumental Tags: Specify instruments to be used in certain sections like [Syncopated Bass], [Fingerstyle Guitar Solo], [Build].
3. Voice Tags: Indicate the type of vocal performance or effects desired. Some metatag examples for vocals style: [Gospel Choir], [Primal Scream], [Rap Verse]

Song Structure Metatags

Verses and Choruses

Verses and choruses form the backbone of most songs. Use these tags to specify their presence:

• Verse: [Verse] or more specific like [Verse 1]
• Chorus: [Chorus]

Pre-Chorus and Bridge

Pre-choruses build up to the chorus, and bridges offer a contrast to the main lyrics:

• Pre-Chorus: [Pre-Chorus]
• Bridge: [Bridge]

Additional Structure Tags

1. Intro: Short instrumental start.
   • Example: [Short Instrumental Intro]
2. Hook: Repetitive catchy phrases.
   • Example: [Catchy Hook]
3. Break: Instrumental pauses.
   • Example: [Percussion Break]
4. Interlude: Instrumental sections.
   • Example: [Melodic Interlude]
5. Outro: Ending sections.
   • Example: [Outro], [Big Finish]
6. End: Explicitly mark the end of a song.
   • Example: [End], [Fade to End]

Best Practices

• Precision: Avoid overly complex tags to prevent misinterpretation.
• Genre Appropriateness: Some tags work better in specific genres, so tailor them to the music style you’re aiming for.

Conclusion

Suno Metatags enhance the specificity and quality of the music generated by Suno AI. By following the guidelines for simplicity and relevance, you can effectively shape your songs to match your creative ideas.

Feel free to experiment with these metatags to make better customized songs!

For detailed information on metatags and their uses, refer to the official Suno Metatags FAQ.

The post Generate AI Music with Suno Metatags appeared first on AI Art Blog.

New features of the v3.5 model

• Generating 4-minute tracks: you only have to click the Create button once and after a few moments the entire full song track is ready
• we can extend the music by up to 2 minutes
• improved music structure and vocal flow (this means that the music generation has been improved, so more relevant content is created for the prompt, metatags are taken into account better and the vocal will be more accurate and of better quality)
• download songs in .wav format (only for Pro and Premium subscribers)

Of course, it is possible to use one of the older models before starting the music generation.

How to create your full-length (up to 4 minutes) AI music?

The steps for generating music have not changed compared to before:

1. Open the Suno website and log in to your account. If you don’t have access yet, sign up by clicking on the Sign Up link in the bottom left corner of the home page.
2. You can also log in with a Discord, Google or Microsoft account.
3. Click the Create button from the menu (top left).
4. Enter the prompt of the song or use the randomly generated prompt.
5. Check if the v3.5 model is selected
6. If you don’t want lyrics for the music, activate the Instrumental setting
7. Click the Create button
8. You can find the download button by clicking the ellipsis button next to the number

So based on the steps above, you can also create your own songs.

Testing Suno v3.5

I generated 4 full songs with this AI music generator:

Country rock Electronic Dance Music
Prompt: country rock EDM
From the Lyrics: “Lost in the beat, never found my way home.”

African tribal music
Prompt: Traditional 120bpm african tribal music with relatively strong drums and this instruments: kora, djembe, balafon, shaker. Transition to silence at the end.

Chill-out lounge music (Instrumental)
Prompt: chill out lounge background music for cafe bar

Epic instrumental music
Prompt: battle of dragons full epic song with dramatic mood, strong instruments, strings, medium drums, dramatic melody, female choir at the cathartic points, transition to silence at the end

Summary

Suno’s v3.5 model made it even easier to generate music. Thanks to the new developments, we can generate up to a 4-minute full song with Suno just by entering the appropriate prompt and hitting the Create button.

The generated track will not always be exactly 4 minutes long of course. The exact length depends on the musical style, the tempo of the music and the lyrics.

Read the Generate AI Music with Suno Metatags article, to learn how to fine-tune your songs with meta tags.

It is said that Suno is already working on the v4 model, which will put a lot of emphasis on high-quality vocals and, according to the promise, will generate even more appropriate music for the prompt.

The post Create full song with Suno – New features in the AI music generator appeared first on AI Art Blog.

Users who install the IKEA Kreativ app can use their mobile phone to see, via augmented reality, how each piece of furniture would look in their home or office. Artificial intelligence also gives users the option to remove existing furniture from view, so they can even design completely empty spaces.

Future customers can design their interiors in two ways: they can use templates created by IKEA or scan their own existing spaces using the app’s Scene Scanner feature. All they need to do is take a few photos of the space using the app. The system then creates a realistic 3D copy of the existing room, with accurate dimensions and perspectives. They can then try out the furniture and fixtures IKEA has to offer.

The free interior designer app also allows you to save and share designs and ideas, and of course order furniture online.

It is also available on IKEA’s Android and iPhone apps, but the company’s website can also be used for planning.

Cover Photo from the IKEA Kreativ promotional video.

The post IKEA has released an AI-based interior designer app appeared first on AI Art Blog.

In this article, we’ll take a look at what OpenAI’s latest GPT-4o model can do. If you’re curious about its capabilities, be sure to read on.

On Monday, OpenAI announced its newest, fantastic model named GPT-4o. They practically wrote an article and there are plenty of videos on their YouTube channel in which they demonstrate its capabilities.

We will go through them in broad outline, so that by the end of the article you will have a comprehensive picture of what makes this new large language model (LLM) so groundbreaking.

It is noteworthy that GPT-4o will also be available for free.

News about GPT4-o

Its most notable ability is that you can practically have a conversation with it. The reaction time for answering has been reduced to a minimum with this AI model, and you can also interrupt his speech.

The previously available Voice service of ChatGPT needed 4-5 seconds for the answer, now that has completely changed.

Watch this example video to see what’s new.

The GPT4-o model

In the description, you can read that this model is actually an omni model. This means, that it can not only interpret your voice (Voice mode) and text, but can practically handle both.

The interpretation of images and videos is made possible by the Vision mode.

The Memory mode remembers our previous conversations, which ChatGPT can use later. With the Analyze mode, complex data can be analyzed quickly and efficiently. Examples: Excel spreadsheets or even a chart that you show as an image to chatGPT.

Practical examples

If you look at the introduction page of GPT-4o, you can see many examples of people using their phone’s camera with the ChatGPT app and asking ChatGPT what it sees in the camera, and it then answers them “verbally”.

So the same thing can now be done in real time with your phone’s camera. The big difference between the current GPT-4o and the previous Voice service is that a completely new model was actually trained here with voice, text, videos and images.

It is also worth watching the video where they show that one person speaks Italian, the other person speaks English. The phone interprets it in real time. This means that as soon as the Italian text is spoken, ChatGPT immediately translates it into English and vice versa.

You’ve may seen conversations, where politicians spoke in their own mother tongue and still understood each other. It was thanks to the dubbing service in the background.

In the future, this will probably be completely replaceable with such an AI solution.

Performance of GPT-4o

There is a comparison chart on the hello-gpt-4o page in the Model evaluations section, with which we compare the GPT-4o model through various benchmarks, for example with GPT4 turbo, or even with the paid Claude 3 Opus and Gemini Pro 1.5.

The speed difference according to the graph will become visible in practice. All models are already very fast and are therefore capable of responding in real time.

You can feel the difference between a free ChatGPT, i.e. GPT 3.5 and GPT 4, but the difference between the above big models is not really noticeable anymore.

Security and limitations

The good news is that they also put a lot of emphasis on security. It’s highly likely that you won’t be able to say obscene words with it and you won’t be able to ask ChatGPT for other silly things either.

This model is subjected to serious, in-depth testing, which means that a team tries to hack these systems and extract answers from them. The name of the testing method is the so-called red teaming.

The future

These services are constantly being improved. Maybe by the time you read this article, the entire interface will look completely different.

Thanks to the Memory mode, ChatGPT will also remember previous conversations. You can turn this off if you don’t want it to store information about you.

The Analyze mode is good for uploading documents and requesting all kinds of analytics from it. So there will be improvements here in the free GPT as well.

Summary

This new model contains huge innovations. It almost feels like talking to a live person. It can also be used to facilitate scientific tasks, such as the analysis of complex data, graphs, and images.

If this is also combined with image and video generation, or perhaps with the generation of sound and music, the limit to what we can create with it is the imagination.

Of course, he won’t cook lunch for you, but he can help you in creative and scientific tasks.

Thank you for reading this article!

Image by Franz Bachinger, Pixabay

The post OpenAIs GPT-4o model is free to use! appeared first on AI Art Blog.

In recent months, the music industry has witnessed a rapid evolution driven by advancements in artificial intelligence (AI). Among the groundbreaking innovations are AI music generation tools like Suno and Udio. These tools have revolutionized music production, inspiring artists and composers worldwide. In this article, we’ll explore the capabilities of these tools, provide a basic step-by-step tutorial, and discuss their impact on music creation.

The Fast Development of AI Music Tools

Suno V3 and Udio represent the cutting edge of AI-driven music composition. Their algorithms analyze vast amounts of existing music, learn patterns, and generate original compositions. Unlike traditional music software, which relies on human input, these tools autonomously create melodies, harmonies, rhythms and even vocals from simple prompts. Let’s dive into how you can use them to create your own music.

Step-by-Step Tutorial: Creating Music with Suno V3 and Udio

1. Choose Your Style:
   • Both Suno and Udio recognizes various music styles, from classical to electronic. 
   • Find out what style of song you want to generate and write it in the prompt. 
   • Both music generators will suggest a random prompt, like: a song about a reunion of childhood friends, jazz
2. Input Parameters:
   • Specify parameters like tempo (for example 130BPM), mood (melancolic, happy, uplifting), and instrumentation in the prompt.
   • Suno and Udio will generate a melody and even vocals based on your input. 
   • Suno creates music of about 50 seconds, Udio about 30 seconds, which can be extended later.
3. Review and Edit:
   • Listen to the two versions of the generated music and decide which sounds better.
   • Generate other versions with the same prompt or extend your favorite songs.
4. Export Your Composition:
   • Once satisfied, export your composition as an .mp3 file.
   • For further fine tuning edit the music in an AI-based digital audio workstation (DAW) like RipX DAW.

Enhancing Music Production

• Inspiration: AI tools like Suno and Udio spark creativity. They offer fresh ideas and unexpected chord progressions, pushing artists beyond their comfort zones. Suno has a great function: Explore. Use it to experiment with various genres.
• Time Efficiency: Instead of spending hours composing, artists can use AI-generated material as a starting point, saving time and energy.
• Collaboration: AI tools facilitate collaboration between musicians. Imagine a guitarist collaborating with an AI-generated orchestral arrangement!

Legal Usage and Possible Drawbacks

While AI music tools are exciting, they raise legal and ethical questions:

1. Copyright and Ownership:
   • Who owns the rights to AI-generated music? The artist, the AI, or both?
   • Legally, it’s uncharted territory. Open questions remain about royalties and licensing.
2. Originality and Plagiarism:
   • Can AI truly create something original, or is it just remixing existing content?
   • Detecting plagiarism in AI-generated music poses challenges.
3. Loss of Human Touch:
   • Some argue that AI lacks the emotional depth of human composers.
   • Are we sacrificing authenticity for efficiency?
4. Bias and Representation:
   • AI models learn from existing data, which may perpetuate biases.
   • How do we ensure diversity and fairness in AI-generated music?
5. Limited Sound Quality:
   • Suno and Udio generates radio quality music, which is far from the professional studio quality (CD quality) at this moment, but these music generation technologies are advancing so fast that CD quality may soon be available for the public. 

Conclusion

Suno and Udio exemplify the fusion of art and technology. As we embrace these tools, let’s explore their potential while remaining vigilant about legal, ethical, and creative implications. The future of music lies at the intersection of human creativity and AI innovation.

More interesting articles to come in the future. Happy music-making!

The post Revolution of AI Music Generation: Suno and Udio appeared first on AI Art Blog.

Here are a few free AI image generators you might want to try:

Playground AI

Playground AI is a popular web application that allows you to generate images in different styles. You can even specify an image to be generated and have the AI create an image based on it.

https://playgroundai.com/

General features:

• User gallery (Community Feed)
• Possibility to remix generated images by others
• Keyword search
• Canvas editor

Limitations of the free version:

• Maximum resolution of generated images: 1024 x 1024 pixels
• Slower image generation
• Other image quality restrictions

Leonardo AI

https://leonardo.ai

Leonardo AI is also a web-based, powerful image generator that can be used to generate images of different styles, such as landscapes, portraits, animals, illustrations or still lifes. This tool is constantly being improved and enhanced with innovative features.

General features:

• User gallery (Recent Creations)
• Possibility to remix generated images by other users
• Canvas editor
• Realtime Canvas (originally called live canvas, see my article and youtube video)

This application has additional extra features such as:

• texture generation for 3D models
• video generation

Limitations of the free version:

• 150 fast tokens, resets once per day
• no private generations
• Images can be up to 1024×1024 pixels

Stable Diffusion

https://stablediffusionweb.com/

Stable Diffusion has a very good image generating engine. We cannot view and use other users’ images as a base, but the prompt database can help to inspire and achieve better results.

General information:

• Stable Diffusion don’t collects any personal information
• They don’t store our text or image

Advantages of the free version:

• Unlimited number of images can be generated
• No registration required

Limitations of the free version:

• Slower image generation
• Watermarked images
• Only one image version per generation
• Images can be up to 1024×1024 pixels

DALL-E 2

https://labs.openai.com/

OpenAI was among the first to create an AI image generation tool. A few months ago, version 3 of DALL-E was released and integrated into the paid version of ChatGPT.

General information:

• Free credits to those who registered before 6 April 2023
• Free credits reload 1x per month
• You can create 4 image versions with 1 credit
• Currently $15 gets you 115 credits

Benefits of the free version:

• easy to use
• generates 4 different versions based on a prompt

Limitations of the free version:

• not as detailed and realistic as DALL-E 3
• watermarked images

Summary

Free AI image generators are a good way to try AI-based image generation. If you’re on a limited budget or just curious to see what these apps can do, it’s worth trying at least one of them out.

Good luck and have fun experimenting!

The post These are the best free AI image generators of 2023 appeared first on AI Art Blog.

Still in Beta stage (early access), but very easy to use. I really enjoyed the testing process.

How to use?

Just log in into Leonardo Ai, open the Realtime Canvas feature, give some short prompt and start drawing! You can use different colors, different brush thickness. Realtime Canvas shows the result immediately!

I recommend you to try out this feature: just play with the settings, try different prompts and see what’s happening. It’s a big FUN and you can activate your fantasy with them.

Use it for example in the planning process of your project, creating concept art or to get ideas how to enhance your drawings.

If you would like to see it in action and get some ideas what and how can be draw with Realtime Canvas, just watch my video on YouTube:

In this video I show you how easy to use Realtime Canvas. I draw various objects like a simple tree, a car, a house and so on. I give you also some tips how to rotate the objects in three dimensions.

Furthermore you can learn how positioning the sun affects the overall mood of the house image.

If you are new to AI, then I would recommend to read the Artificial Intelligence Guide first.

The post Leonardo Ai’s new feature for free: Realtime canvas appeared first on AI Art Blog.

Hey there, AI users! I think that many of us just hitting the Generate button because it’s a fast and simple way to create text or visual content. I want to share some thoughts about a topic that’s been on my mind: the consequences of overusing AI in our creative projects.

AI is Attractive

It’s no secret that AI has revolutionized the way we generate content. From crafting blog posts to generating stunning visuals, artificial intelligence has become our trusty “coworker”, always ready to assist. The attractivity of efficiency and productivity invited many of us into relying heavily on AI tools, but are we losing something crucial in the process?

Overusing AI

I know it’s easy to overuse AI tools: falling into the trap of letting algorithms do the heavy lifting, but what happens when our creativity takes a backseat? Here are a few ways AI can be used more than recommended:

1. Lack of Originality

One of the glaring consequences of overusing AI is the potential dilution of originality. When we let algorithms dictate our creative choices, we risk producing content that lacks the unique flair that sets us apart.

2. Loss of Personal Touch

AI-generated content might be polished, but it often lacks the human touch that resonates with audiences. Genuine connection comes from authentic, human-created content that reflects our individual perspectives and experiences.

3. Dependence on Templates

Templates are fantastic time-savers, but sticking always to AI-generated templates can lead to a “cookie-cutter approach” to content. Our work starts to blend in rather than stand out.

Finding the Right Balance

So, how do we avoid the pitfalls of AI overuse and make a harmonic balance between technology and creativity? Here are some tips:

1. Set Clear Boundaries

Establish guidelines for when and where AI can be used in your creative process. Reserve its assistance for tasks that enhance rather than replace your creative input.

Some examples for clear boundaries:

• using AI only for inspiration
• using AI only for draft creation
• not using AI at brainstorming, but using in the realizing phase

2. Trust in Your Creative Intuitions

Don’t let the convenience of AI suppress your creative intuitions. Regularly engage in manual content creation to keep your skills sharp and maintain a genuine connection with your work.

3. Embrace Collaboration

Consider AI as a collaborator rather than a replacement. Use it as a tool to complement your creative process, bouncing ideas back and forth to achieve the best of both worlds.

4. Work in a Team

Don’t isolate yourself too much. Creating something new in a team can be fun. Interaction, creative brainstorming are inspiring activities and brings people together.

5. Evaluate the Results Regularly

Periodically assess the impact of AI on your content. Are you maintaining the level of authenticity and originality you desire? Adjust your approach as needed to find the right balance for your unique creative style.

In conclusion, while AI is a powerful ally in our content creation journey, it’s crucial not to let it overshadow our creative instincts. By setting boundaries, trusting in creative instincts, embracing AI as a collaborator and work with other people we can navigate the vast landscape of content creation with love, producing work that is both efficient and authentically ours.

The post Navigating the AI Jungle: the Pitfalls of Overusing AI appeared first on AI Art Blog.

In a previous development of Luminar Neo the GenErase feature was introduced. GenErase can easily remove an object from an image and fills that area with relevant visual content. This also saves a lot of time when post-processing photos.

The post Skylum announced GenSwap in Luminar Neo 1.16.0 appeared first on AI Art Blog.