Dec 13, 2023

Fooocus simpler approach


Fooocus is an impressive AI program that revolutionizes the process of image generation. With its user-friendly interface, creating captivating images becomes a breeze. What sets Fooocus apart from its competitors like Automatic1111 and ComfyUI is its simplicity and efficiency. It offers a seamless experience to users, allowing them to effortlessly bring their artistic visions to life. With its remarkable capabilities, Fooocus has the potential to challenge the current leaders in the field and establish itself as the go-to choice for image generation.

Fooocus can even run on google colab

Here is an example of a picture generated with Fooocus



Oct 29, 2023

16 Years

This blog you are reading now has been online for 16 years!

To be exact that is 5870 days

It was created back in Oct 3, 2007



Oct 9, 2023

Hottest models for AI generated images

As of October 2023, among the hottest Stable Diffusion checkpoint model the most popular and well-regarded models include:

  • DreamShaper is a highly versatile model that can generate a wide range of styles, from realistic to fantastical. It is known for its creativity and its ability to generate images that are both visually appealing and meaningful.
  • Deliberate is a model that is focused on generating realistic images. It is known for its attention to detail and its ability to produce images that are indistinguishable from photographs.
  • Realistic Vision is another model that is focused on generating realistic images. It is known for its ability to capture the nuances of human faces and bodies.
  • ChilloutMix is a model that is known for its ability to generate beautiful and atmospheric images. It is often used to create illustrations and concept art.
  • Protogen is a model that is known for its ability to generate anime-style images. It is often used to create fan art and original characters.


Sep 29, 2023

Nadine Kerastas


Discovering German fitness model and Instagram influencer Nadine Kerastas

Sep 22, 2023

Reviewing SeaArt.ai

SeaArt.ai is a web-based AI art generator that allows users to create high-quality digital artworks with just a few clicks. It offers a wide range of features, including:

  • A powerful AI engine that can generate realistic and creative images from text descriptions, image prompts, or even sketches.
  • A variety of art styles to choose from, including painting, drawing, photography, and 3D art.
  • A user-friendly interface that makes it easy to create and edit images.
  • A community of artists and creators who share their work and tips.

SeaArt.ai is a great tool for artists of all skill levels, from beginners to professionals. It can be used to create concept art, illustrations, product designs, and more. It is also a fun and creative way to experiment with different art styles and techniques.

Here are some of the pros and cons of SeaArt.ai:

Pros:

  • Wide range of features, art can be generated from the website itself, or discord
  • User-friendly interface, generating art is done via an assisted interface
  • High-quality results up to 2048x2048 and more 
  • Active community on discord

Cons:

  • May look a little complex for beginners at first
  • Some features require a premium subscription
  • Can be slow to generate images at times

Overall, SeaArt.ai is a powerful and versatile AI art generator that is well worth checking out. It is a great tool for artists of all skill levels, and it can be used to create a wide variety of digital artworks.

If you are looking for an AI art generator that is easy to use and produces high-quality results, I absolutely recommend SeaArt.ai.



Sep 15, 2023

Firealpaca time-lapse activated

FireAlpaca is a free and open-source raster graphics editor software for Windows, and macOS. It is a popular choice for digital artists of all levels, thanks to its user-friendly interface and powerful features.

FireAlpaca offers a wide range of tools and features, including brushes, layers, filters, and effects. It is also highly customizable.

Overall, FireAlpaca is a great option for digital artists who are looking for a free and powerful software.

Since version [2.11.5] a new feature has been added:

  • Added time-lapse recording feature (start and end from file menu or alpaca button).
  • At the end of time-lapse recording, you can convert to animated GIF.
  • When opening an APNG file, you can now select "Convert to animated GIF" or "Import as canvas".





 

Aug 25, 2023

Tania Amazon DJ'ing at Egg


Discovering Tania Amazon

Tania Amazon is a astounding model and professional DJ who has been making waves in the UK dance music scene. She is known for her eclectic mix of house, techno, and electronica, and her energetic sets have won her a loyal following of fans.

Tania started her DJ career in her early twenties, playing at small clubs and bars in London. She quickly gained a reputation for her skills behind the decks, and she was soon playing at some of the biggest clubs in the city.

In recent years, Tania has toured extensively throughout the UK and Europe, and she has shared the stage with some of the biggest names in dance music. She has also released several mix albums, which have been met with critical acclaim.

Tania is a passionate advocate for women in dance music, and she is a regular speaker at events and conferences. She is also a mentor to aspiring DJs, and she is committed to helping more women break into the industry.

In addition to her DJ career, Tania is also a producer. She has released several original tracks, and she has collaborated with some of the biggest names in electronic music.

Tania Amazon is a famous star in the UK dance music scene. 

She is a talented DJ, model, producer, and advocate for women in music. She is sure to continue to make waves in the years to come.

Tania played at some of the biggest clubs in the UK and Europe, including Ministry of Sound, Fabric, and Egg London. Shes shared the stage with some of the biggest names in dance music, such as Carl Cox, David Guetta, and Tiësto. She released several mix albums, spoken at events and conferences on the topic of women in dance music.

Released several original tracks. Collaborated with some of the biggest names in electronic music.

Tania Amazon is an inspiration to aspiring DJs and producers. She is a talented and passionate artist who is committed to making a difference in the dance music scene.

And last but not least she was born December 2, 1974 (age 48)





Jul 26, 2023

Introduction to Leonardo.ai

The image generation tool called Leonardo AI is remarkable for its ability to produce stunning images and its unique features that distinguish it from other AI image platforms. 

Upon reviewing the community feeds, it is evident that the quality of images generated by Leonardo AI rivals that of well-established platforms. 

An added advantage is that Leonardo is currently available for free

To access Leonardo dashboard, simply enter your email address on the Leonardo.ai website and click "Count Me In." Within a few days, you will receive access to an improved version of Leonardo AI for generating images. 

Images from selected models: Leonardo AI utilizes a unique model-tired approach that distinguishes it from other AI image platforms. Instead of relying on foundational models like stable diffusion, Leonardo AI employs fine-tuned models that are optimized for specific styles. These models offer users a style-centric starting point, including 24 platform models optimized for various types of artwork.

This platform even has the option to 'Train your own model': One of the most impressive features is the ability to train your own models. Users can create a dataset by uploading their own images or selecting images from the Leonardo gallery. Once a data set is created, users can fine-tune a new model that leverages the stable diffusion base model, but is specifically tuned to their own data set. They can also create and share community models on the Leonardo platform. This unique approach allows users to not only use the platform's models, but also create and share their own models, creating a network of community models that can be used and extended by others. 

Additionally, Leonardo includes a built-in image editor called Canvas, which allows users to edit their generated images. By selecting an image and choosing "edit in Canvas," users can make adjustments and refinements to their images. The generation feature of Leonardo AI allows users to generate more elaborate prompt ideas based on a single prompt. This feature helps users generate more interesting results by providing detailed prompts.


Here is an example of an image generated Lion, with background removed


Jul 21, 2023

Discovering Neringa

Neringa is a Lithuanian model born on 1995 in Kaunas, Lithuania.

Her age is 28 years old as of 2023

She is a famous Instagram Star and internet personality.




Jul 19, 2023

AI: The Revolution That Will Change Everything (Or Destroy Us All)

Artificial intelligence (AI) is everywhere now, and the very topic of the moment. It has the potential to solve some of the world's most pressing problems, such as climate change and poverty. But there is a heavy price to pay for that technology both culturally, and humanly.

The good of AI:

  • AI has the potential to solve some of the world's most pressing problems. For example, AI can be used to develop more efficient ways of generating energy, which could help to reduce our reliance on fossil fuels and combat climate change. AI can also be used to develop new medical treatments, which could save lives and improve the quality of life for millions of people.
  • In addition, AI can be used to automate tasks that are currently performed by humans, which could lead to increased productivity and efficiency. For example, AI can be used to develop self-driving cars, which could reduce traffic accidents and save lives. AI can also be used to develop robots that can perform dangerous or tedious tasks, such as cleaning up pollution or working in hazardous environments.

The bad of AI:

  • While AI has the potential to do a lot of good, it also has the potential to be used for malicious purposes. For example, AI can be used to create autonomous weapons that can kill without human intervention. AI can also be used to develop mass surveillance systems that can track our every move.
  • In addition, AI can be used to create fake news and propaganda that can be used to manipulate public opinion. AI can also be used to spread hate speech and extremism.

The challenges of AI:

  • There are a number of challenges that we need to overcome in order to ensure that AI is used for good. One challenge is that AI systems can be biased. This can lead to unfair treatment of certain groups of people. For example, AI systems that are used to make hiring decisions could be biased against women or people of color.
  • Another challenge is that AI systems can be hacked. This could allow hackers to gain control of AI systems and use them for malicious purposes. For example, hackers could use AI systems to take control of self-driving cars or to launch cyber attacks on critical infrastructure.

The woke culture:

  • The woke culture is a movement that emphasizes the importance of social justice and equality. It has been criticized for being too sensitive and for censoring free speech. However, the woke culture is also a powerful force for good. It has helped to raise awareness of important issues, such as racism, sexism, and homophobia.
  • The woke culture is likely to have a significant impact on the development of AI. AI systems will need to be designed in a way that is fair and equitable. They will also need to be able to understand and respond to complex social and cultural issues.
  • AI talk also in very politically correct way, and that is enforcing this culture of Wokeness



Jul 13, 2023

SDXL supported style

 style:comic book

style:Sticker

style:Neon Punk


style:Analog Film


style:Anime



style:Photographic

style:Cinematic

style:Isometric





SDXL prompt example

 


prompt:

Chaotic Mixed media Rebecca Romijn portrait art, Scratch art, Masterpiece

SDXL cute panda prompt

cute baby panda, detailed matte painting, deep color, fantastical, intricate detail,  complementary colors, fantasy concept art, 8k resolution, trending on Artstation




SDXL prompt example

 


prompt:beautiful ethereal landscape mountains, flower field illustration , by Ed Mell atmospheric and aesthetical , steps:46,  style:Sticker , width:1216 , height:832 , seed:1689221413

SDXL prompt example

 


prompt: standing female fighter wearing blue jacket, military camouflage pant, black combat boots, medium shot, art by stanley artgerm, style:comic book

Jul 12, 2023

SDXL prompt example

Prompt example:

Prompt: Cover, painting of a girl with long blue hair in a white t-shirt on one side of a tattooed cyberpunk space with details, luminism, strip lighting, complex, head and shoulders portrait, 4k concept art portrait by Greg Rutkowski, artgram, WLOP, Alphonse Mucha




Jul 11, 2023

SDXL Stable Diffusion discord

Playing with Stable diffusion discord and the new SDXL checkpoint model

Head over to discord.gg/stablediffusion

From there it is quite Easy to generate artwork using prompt /dream on one of the bots (there are 10 bots available) 

Following an AI prompt such as 'Graphic Illustration, Creative Design, white hair style undercut female, techwear, Cyberpunk, Full Body Portrait, Character Design, graffiti, style:comic book'



SDXL is pretty powerful

Roop Stable Diffusion

Jun 23, 2023

Fixing chromadbd installation ERROR: Failed building wheel for hnswlib

When trying to install chromadb on a python environment, using

$ pip install chromadb

This error below might show up:

[...]

      x86_64-linux-gnu-gcc -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O2 -Wall -g -fstack-protector-strong -Wformat -Werror=format-security -g -fwrapv -O2 -fPIC -I/tmp/pip-build-env-lorq5gen/overlay/lib/python3.10/site-packages/pybind11/include -I/tmp/pip-build-env-lorq5gen/overlay/lib/python3.10/site-packages/numpy/core/include -I./hnswlib/ -I/home/p/Documents/dev/python/openai/include -I/usr/include/python3.10 -c ./python_bindings/bindings.cpp -o build/temp.linux-x86_64-cpython-310/./python_bindings/bindings.o -O3 -march=native -fopenmp -DVERSION_INFO=\"0.7.0\" -std=c++14 -fvisibility=hidden
      In file included from /tmp/pip-build-env-lorq5gen/overlay/lib/python3.10/site-packages/pybind11/include/pybind11/detail/../attr.h:13,
                       from /tmp/pip-build-env-lorq5gen/overlay/lib/python3.10/site-packages/pybind11/include/pybind11/detail/class.h:12,
                       from /tmp/pip-build-env-lorq5gen/overlay/lib/python3.10/site-packages/pybind11/include/pybind11/pybind11.h:13,
                       from /tmp/pip-build-env-lorq5gen/overlay/lib/python3.10/site-packages/pybind11/include/pybind11/functional.h:12,
                       from ./python_bindings/bindings.cpp:2:
      /tmp/pip-build-env-lorq5gen/overlay/lib/python3.10/site-packages/pybind11/include/pybind11/detail/../detail/common.h:266:10: fatal error: Python.h: No such file or directory
        266 | #include 
            |          ^~~~~~~~~~
      compilation terminated.
      error: command '/usr/bin/x86_64-linux-gnu-gcc' failed with exit code 1
      [end of output]
  
  note: This error originates from a subprocess, and is likely not a problem with pip.
  ERROR: Failed building wheel for hnswlib
Failed to build hnswlib
ERROR: Could not build wheels for hnswlib, which is required to install pyproject.toml-based projects

On a Linux system the solution to fix the error above is to install 2 missing libraries:

$ sudo apt install python3-dev
$ sudo apt-get install build-essential -y






May 31, 2023

Apr 24, 2023

Another comics

 8 pages, for this new comics ... and this time there is a nice start and a possible story!










Apr 17, 2023

Making comics with canva

A while ago, I did a little experiment with canva 
and created a 3 pages comics using MidJourney


Today, I wanted to try if I could do it again and here is the result




It must be super difficult to work in this office ...

Apr 3, 2023

Fixing Sound Stuttering or Crackling in VirtualBox 7 on Windows 11

If you're running VirtualBox v7 on Windows, you might have noticed a sound issue where the audio stutters or crackles. This can be frustrating, especially if you're trying to play music or watch a video. Fortunately, there's a simple solution to this problem.

The issue seems to be related to the audio settings in VirtualBox. By default, VirtualBox uses the "Intel HD Audio" controller, which can cause the sound to stutter or crackle. To fix this, you can switch to a different audio controller.

Here's how to do it:

  •     Shut down your virtual machine if it's running.
  •     In the VirtualBox Manager, select the virtual machine you want to change the audio settings for, and click "Settings".
  •     In the settings window, select the "Audio" tab.
  •     Under "Audio Controller", select "Windows DirectSound".
  •     Click "OK" to save the changes.
  •     Start your virtual machine and check if the sound issue is resolved.

That's it! With this simple fix, you should be able to enjoy your virtual machine's audio without any stuttering or crackling.





Mar 6, 2023

Animation industry is about to be upgraded


Graphic artists are impacted right now, but we can see how Hollywood is going to be heavily revolutionized by the AI generated tools available today

Who would have thought?


I see a lot of concern, especially from animators, that tools like this will eventually make them obsolete.
This isn't a replacement for someone that knows how to animate, nor someone who can draw. Tools constantly evolve, but making something visually captivating always requires those same core skills. It still takes an artist to make art. That hasn't changed.
What we figured out here is a very advanced form of old-fashioned rotoscoping. Animation takes a lot of forms; Traditional, 3d, stop-motion... They all have different strengths, and enable different stories. Our method here isn't a replacement, but an attempt at something new.
What excites me is that this tech makes it easier to bring my visual ideas to life. Ideas that were otherwise impossible. When I said this democratizes animation, I'm referring to the near-insurmountable mountain of work needed to make a full-length narrative animation. Currently that requires large studios and large budgets. Doing it on your own is nearly impossible.
But I see potential in these tools to change that! That's what I'm so excited about. Imagine one person, or a few friends, bringing their crazy ideas to life. Imagine if a traditional animator could automatically have their drawings inked and colored. Imagine eliminating the uncanny valley on cgi faces. These tools have the potential to do that. We're trying to figure out how, and sharing our journey. If we want community-controlled AI tools, we need to develop them as a community, otherwise they become proprietary tools locked behind a company.
And yes, this can be done with your own style. We trained our model, not from hundreds of artists, but from ONE film- Vampire Hunter D Bloodlust.  We've been very open about this, and I think it's important to be. But this is also an experiment and a loving parody of this era of anime. I consider it no less ethical than the countless other videos on our channel that borrow from pop culture to tell their story.
Sudden change can be scary, especially if it feels like your passion or livelihood is on the line. But that's why we're out here exploring it. Hopefully we can help shine a light into the fog for everyone.
-Niko

Feb 28, 2023

Discussing with Bing chat AI

Google Bard is not open to public yet, but Bing has its chat enabled to public (after registering to a waiting list) 

Here are some of our conversation bits:


Straight to the point, asking Bing how it compares to chatgpt (chat.openai.com) the current leader in the field of AI chat.

First bing is showing what he is doing in the background, which is good, it also is showing that its purpose is to perform internet searches, and will provide links (hyperlinks inside its response)

My second question was about google bard (the competition) and chat bing responded that it is open to the public (which is not true)

As a rule of thumb, it is good policy to never trust an AI response without checking.

Lastly I was badly surprised that there was a limit in the conversation, maybe to prevent people to corrupt the AI by training it the wrong way?

The conclusion is that, it feels like the future of internet searches is going to be AI 
It feels right to discuss with a search engine this way, because we (human) have been acquiring information this way since the dawn of time.
No doubt, Google Bard is going to be doing more or less the same, and we will be able to get assistants in the near future, knowing everything about us...

This could be a good thing, unless of course ... this falls into the wrong hands, and then it is used by a dystopian government, but let's not think about that...


Popular Posts