Example of negative prompts

• nsfw, worst quality, low quality, depth of field, blurry, greyscale, monochrome, 3D face, nose, cropped, lowres, text, jpeg artifacts, signature, watermark, username, blurry, artist name, trademark, watermark, title, tan, muscular, loli, petite, child, infant, toddlers, chibi, sd character, multiple view, Reference sheet
• NSFW, lowres, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts,signature, watermark, username, blurry, artist name, humans, castle, solo, bad face, deform face, nude, scantily clad, deform hands, nude, naked,  text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck,easynegative, ng_deepnegative_v1_75t, negative_hand, bad_pictures

Png extracting workflow for ComfyUI (Better version )

requires PIL 

 so maybe do a 

 $pip install PIL 

 beforehand

import argparse
import PIL.Image
import PIL.PngImagePlugin

def extract_text(filename):
    """Extracts text from a PNG file."""
    img = PIL.Image.open(filename)
    info = img.text["workflow"]
    return info

## usage python readpng.py ~/Downloads/example.png > comfy_workflow.json

def main():
    """Parses arguments and extracts text from a PNG file."""
    parser = argparse.ArgumentParser(description="Extracts text from a PNG file.")
    parser.add_argument("filename", help="The PNG file to extract text from.")
    args = parser.parse_args()
    text = extract_text(args.filename)
    print(text)

if __name__ == "__main__":
    main()

Extracting metadata from a png file in Python

 A very simple program using PIL to extract the png text embedded as metadata by comfyUI 

import PIL.Image
import argparse

def extract_text(filename):
    png = PIL.Image.open(filename)
    return png.text

if __name__ == "__main__":
    parser = argparse.ArgumentParser(description='png metadata infor')
    parser.add_argument('filename', help='png File to check')
    args = parser.parse_args()
    text = extract_text(args.filename)
    print(text)

The state of the AI vs classic artwork discussion

The introduction of AI technology into the artistic sphere garnered significant attention a few months ago, inciting heated debates, lawsuits, and controversies. However, the novelty of this trend appears to have diminished recently.

I can see some artists still balancing from the old ways and now including AI into their workflow

One artist in particular caught my attention, he seems to be swinging back and forth, posting drawings and then AI artwork 

Here is the link to his blog blogclif.wordpress.com/

Here is a recent sample of his drawing

and here is the AI generated from the drawing

My current view is that he should create numerous drawings and select the best ones to evaluate their appearance in the AI artwork style.

ComfyUI

How to download a ckpt model

These ckpt files are huge (at least 2GB and usually 4GB, they can reach up to  8GB) 

First method:

1. An easy way to get them inside of a google colab

by adding these commands inside a code snipet:

!git lfs install
!git clone https://huggingface.co/WarriorMama777/OrangeMixs

git lfs install is required to download file heavier than 100MB

and the clone command is a way to copy the huggingface.co repository 

in this example the OrangeMixs model

2. Alternative way

Using the huggingface-hub library for Python

!pip install huggingface-hub
from huggingface_hub import hf_hub_download
hf_hub_download(repo_id="WarriorMama777/OrangeMixs", filename="VAEs/orangemix.vae.pt", cache_dir="./")

Training a lora (stable diffusion) [part 1]

Step by step Lora Training

Training a model is very demanding, and the result is a minimum 2GB file ; while a Lora (Low-Rank Adaptation) will be less than 150MB.

Where to start?

I would recommend this google colab link

Linaqruf/kohya-trainer/blob/main/kohya-LoRA-dreambooth.ipynb 

Step 1:

Requirements: The preparation of a set of images, and texts (dataset)

Another requirements is a google account (to use the colab link and google drive)

Each image and text's name must match - the size of the images should be 512x512 pixels 

It is convenient to use https://www.birme.net/ to resize the dataset.

For the text, best is to give a little description on each file, or to use the img2txt feature and get the terms directly from the AI.

 Only 5 images (and texts) are going to suffice, but 15 or more will make the model more reliable.

Once the dataset is complete, put these files into a folder with the number of repeats (5 or 10) and the concept (something like exp, or person, or Bcloth, etc ...)

Once ready add the datasets into the google drive

Step 2: 

Open the colab trainer

Go to github.com/linaqruf/kohya-trainer

and pick Kohya Lora Dreambooth

To be continued ...

InvokeAI Unified Canvas

There is a certain frustration that comes after generating AI artwork ; it feels like a lottery, some prompts will return great images (but with a little defect here and there) and then there are many failed attempts, where the images are just not good, partly out of frame, or simply with deformities, or artifacts (purple blotches, weird eyes, weird hands, etc ...)

Surely, this is normal, and AI artwork is still in its infancy, or at least early ages ; it is still impressive. but as an artist, you need a little more control than just changing a word here and there, and pressing 'run' or 'launch' and hope for the best.

In the coming year, there probably will be some kind of a sketch application, and AI will then improve the images (man made) ; instead of asking the AI to do everything, this is probably what will be the definitive step forward.

controlNet is going in that direction, by helping an AI or strongly suggesting a pose to start with.

It can be based on a sketch. And then there is invokeai, which offer an environment for the creative minds. 

Creating content is so easy now

Cartoonists, musicians, voice actors, and more broadly every artists or content creators are now in competition with AI generated contents.

This is a game changer, and we have not completely understood or contemplated how much of a revolution we are seeing emerging ... in early 2023

It took me less than 10 minutes to create a new super hero from scratch, write a backstory, and several scenarios, in less than a day, I could self publish an entire comic book featuring this new Dark violet super hero ...

I used lexica.art, dreamlike and stable diffusion to get a different artstyle

lexica.art is crazy good

exica.art/prompt

prompt:

highly detailed portrait of a sewer punk lady student, blue eyes, tartan hoodie, white hair by gustav klimt , art neuveau, atey ghailan, by greg rutkowski, by greg tocchini, by james gilleard, by joe fenton, by kaethe butcher, gradient yellow, black, brown and pink color scheme, grunge graffiti tag wall background

https://lexica.art/

Examples of AI Artwork

 

Using this negative prompt:

nsfw, (worst quality, low quality:1.3), (depth of field, blurry:1.2), (greyscale, monochrome:1.1), 3D face, nose, cropped, lowres, text, jpeg artifacts, signature, watermark, username, blurry, artist name, trademark, watermark, title, (tan, muscular, loli, petite, child, infant, toddlers, chibi, sd character:1.1), multiple view, Reference sheet

Tsu interview : Anna Lioce (aka MisaLioce)

Q1: Can you introduce yourself (give a short bio) ?

I live in South Italy and I am a geek girl.
I love drawing comics with my husband (he is my favorite writer) and watching SCI-FI and horror series (always with him).
I've been drawing since I was a little child and I hope one day to become a professional comic artist.

Q2: What convinced you to join tsu.co?

I joined tsu because I'm interested in new media (I am a graphic designer and Marketing expert too).

Q3: What are the main tools of your trade?

I use Manga Studio and Photoshop.

Q4: What are the biggest struggles you encounter as an artist?

People!! People thinking that drawing is something easy and/or stupid!

Q5: What are your visions of art for the future?

For me, art will be web-based and shared with the world and other artists, giving people the unique opportunity to know other cultures and way of expression

Q6: Where can we find you on the web?

twitter : https://twitter.com/Misa0027
tsu: http://www.tsu.co/MisaLioce
Ghostbusted comics : http://www.staynerd.com/nerdstuff/stay-nerd-comix-attenti-a-quaynerd-06-ghostbusted-finale/

Thanks for the interview Anna Lioce,

you can join her network at http://www.tsu.co/MisaLioce

Tsu interview : Sara Elena Meloni

Q1: Can you give a short bio?

Hi, my name is Sara, in art SEM. I'm 26 and I'm Italian.
I did art school and academy of fine arts, painting, but i learned much from internet, tutorial, and virtual friends.
Now I make portraits on commissions, I teach courses of portraiture and I participate in art exhibitions in Italy, mainly in my region.

Q2: What convinced you to join tsu.co?

I'm here on tsu (SaraElenaMeloni_SEM) because I like to see and communicate with people that have my same passion: art.
Others socials networks are more dispersive.

Q3: What got you into art?

I know many people related to me, artists and art lovers.
Art is also a cure for depression in this period of economic crisis that is not working.
Art makes us live. And I thank the art every day.

Q4: What are the required qualities of an artist?

Depends, there are many different kinds of art. It starts from the dialogue and technique. A right mix of technical ability combined originality, communication and imagination should be ideal for an artist.

Q5: What are your visions of art for the future?

I do not know. The art is in all parts of the world, art can help entire peoples through communication.
Unfortunately, many people are far from art, art should be more interactive, go to the people who does not know and help them to live better.
The art makes the person feel good.

Q6: Where can we find you on the web?

I try to follow many social networks and blogs, the main ones are:
facebook: https://www.facebook.com/pages/Sara-Elena-Meloni-SEM/44426639607
instagram: https://instagram.com/saraelenameloni_sem_art/
tsu: http://www.tsu.co/SaraElenaMeloni_SEM
deviantart: http://sarameloni.deviantart.com/
youtube: https://www.youtube.com/channel/UC9Coq_n7tq2p-N5MyBnkETA
twitter: https://twitter.com/semmy888
and my blog: https://saraelenameloni.wordpress.com/
Thank you =)

Thanks for the interview Sara Elena Meloni,

you can join her network at http://www.tsu.co/SaraElenaMeloni_SEM

Tsu interview : Giuseppe Marinello

 

Q1: Can you give a brief biography? 

 I live and work in Italy, I was born in a small southern town. I drew as a child but my training course was a bit 'slow and tortuous. Mostly because coming from a small urban center did not have people with to appreciate the drawing. Only later, around 27 years old, I decided to attend a school to learn the techniques of film and cartoon storyboard.  

Then I worked many years in the field of video games as a 2D pixel artist and advertising. Meanwhile, I was also the assistant in a study that dealt with comics and this was useful because it taught me to never abandon the classical technique (pencil and ink) to draw. I have done many commercials and storyboards for video games, but the problem is that the storyboard is a just a "task" so no one will ever know that you drew those things. People find about it only when you have them on your own design, where is your signature.  

Q2: What convinced you to join tsu.co? 

 I joined (tsu.co) because I was looking for something different from the usual social media. A place to put my work and admire the work of artists from around the world, with no particular barriers. TSU, from this point of view, is ... perfect!  

Q3: What got you into art? 

 This is the most difficult question: I think it all starts from a desire to emulate. As a child, I admired the designs of Romano Scarpa of Mickey Mouse or John Romita Spider Man. Then you think ... "I want to draw too!". But then life is much more complicated and paths can be quite tortuous.  

Growing up, then I change the references. So then was born the love for the classics like Alex Raymond or Stan Drake with the synthesis of Alex Toth and charm for women designed by Leone Frollo. It means that everything is mixed, you look up to so many influences. Today my design is the sum of many things that I have looked and I have assimilated.  

Q4: What are the qualities required of an artist?  

First of all, I think that today it is very easy to be an "artist". Anyone can open a page on a social network and defined himself as such. So the first quality you need is humility. The design is a challenge every day against their limits.  

I've seen guys with great talent completely lost and unseen and people with no particular talent being perceived or sometime becoming great artists. Especially in the comic industry, talent serves relatively : if your starting skill is good, you're lucky but must be fed with the technique and continuous study. So in a nutshell the qualities are : humility, patience, tenacity, desire to improve without ever thinking of having arrived. 
  

 Q5: What are your visions for the future of art?  

Today the art, with the web, is available to everyone. Every day I can discover new talent. I recently fell in love with a Russian painter contemporary Serge Marshennikov.  
Does the wonder of touching the oil paintings on canvas be more Realistic. Without the web, possibly I would not have known this painter : then my hope is that it is easier to educate the new generations to the art, to ensure that its value is not lost and will always remain a heritage to protect. All art! From drawing, sculpture, painting, music ... without distinction!

In my specific future, however, we will be publishing on the number 3 of "Black Death" comic published in Italy by Edizioni Inkiostro. 
I'm running out of inking tables and can not wait to see it printed. 
Thanks for the questions and ... greetings from Italy!

Thanks for the interview Giuseppe, please excuse in advance if there are some error in the translation (my Italian is a bit "rusty" to say the least).

you can join his network at http://www.tsu.co/marin_x

Tsu interview : Melissa Falconi

Q1: Let’s start with the common question, if you can introduce yourself.

Hi, my name is Melissa, I'm 22, I come from Italy, and I'm an office worker but I don't really like my work so I decided to frequent a master's degree in graphic and web design.
I love everything related to art and design, I love drawing and this has been my passion since I was a child.
I wish my passion will help me to find a work regarding art.

Q2: How did you get into tsu.co

I joined Tsu thanks to a friend and I find this social very helpful for artist like me because I saw many of them that I never knew, thanks to the large sharing of artworks.
I also found pages that help artists to promote their art without asking money and I think it's a nice idea.

Q3: What got you into art?

I always had a big passion, I love watching people and the world around me to find every single detail.

Q4: What are the required qualities of an artist?

I don't know, but I think that an artist has to be inquiring, he has to be interested to discover and being persevering in order to improve his skills.
Heart, passion and fantasy mixed together will be the perfect formula for creating perfect artworks.

Q5: What are your visions of art for the future ?

I can't see what will happen but I really hope that art will help people to be more creative and to open their mind to the world.
I hope that art will be considered more important, especially in my country (Italy), where it's so hard to find a work related to it.
I think art is the essence of the human being and it would be perfect if everyone could express it and share colors with others.

Thanks for the interview Melissa,

you can join her network at http://www.tsu.co/Menny_F

Tsu interview : Andrea Giovagnoli

Q1: Let’s start with the common question, if you can introduce yourself.

My name is Andrea , I'm a graphic designer and video maker who has a deep love for everything related to art and graphics in general.
I have two cats and a dog, they are my passion and i also love the world of anime and manga.

Q2: How did you get into tsu.co

I joined Tsu.co because a friend of mine, an artist, showed it to me and i thought it could be fun.
Well i'm not an artist but i live thanks to my "artworks", but this is another story.
I love art especially Japanese art and i admire many of my artists friends.

Q3: What are the required qualities of an artist?

Heart and passion, nothing else.

Q4: What are your visions of art for the future ?

I really don't know what can happen, i'm an expert of viral marketing and i can say that augmented reality and social media marketing will be the future of advertising,
but nobody can say how art will change in the future and i think that this the reason of art being wonderful

Thanks for the interview Andrea

you can join her network at http://www.tsu.co/gara1978

tsu.co the future of social media?

Like i wrote previously - I would never joined facebook ; but recently I've been invited to tsu.co and I created an account at https://www.tsu.co/alashazam

Account creation is easy 

The good thing is you can change everything if you made a mistake
first name, lastname, even the url (what tsu call "username") can be changed.

After the account is created, you will have to acknowledge the analytics page (with a warning against spam) - and the bank page (with a warning against abuse)
what you can do on tsu - is post images (they are protected against copy - but not against screen capture obviously)
post texts, currently you can't post video - but you can put youtube links. Then you can share what other people are posting, comment and like their posts.
You can send messages, you can use hashtags, or mention someone in a post using @ and their username.

All that is the ABC of social media - facebook, ello, diaspora, tumblr are doing the same.

Now where tsu.co is a big game changer is that he rewards users to post, and stay on the site by sharing the advertising money with their users.

Game Changer

The question is then raised -why isn't tsu.co not draining all social media users ?- and the answer is probably because not many people are aware of informed about tsu.co

For people addicted to social media - being paid to post, share, like and interact with friend is like a dream come true.
but I guess, for other people the resistance to switch to tsu.co is simply because their friends are not there but stays on mainly facebook.

Money, money, money

Back in October 2014 - for the early adopters money was pretty good - making 0.10$ on the first day wasn't uncommon - now it is more like 0.01$  - but as all passive income, the amount isn't important - what is important is the regularity of the flow.
Many people are just starting to understand the potential - but since everyone is collecting small sums donation to charities are possible, donation between users too - and in the future maybe paying artists for services or commission.

Time will tell how tsu.co will evolve, I hope it will attract many celebrities, writers, artists, musicians, freelance (content creator) and will allow them to gain visibility and money.
It has potential to attract people from fiverr, or other low income freelance services, and even from from paypal (when the money to be transferred doesn't exceed 100$) - Letting other social media like facebook for family or close friends interaction.

Fundamentally what is the benefit of having 1 millions likes or followers if a celebrity on facebook doesn't make any money out of it?

Some facebook power-users have found that putting a gofund.me link is a lucrative way to earn money - as a rule of thumb, for every genuine 10,000 likes a page can make a sell.

Maybe this sell come from poster print, etsy shop, zazzle links or donation - on tsu.co all this merchandising is possible but with the addition of redistributed advertising money as a regular income.

Now as for tsu.co power user you can check the "discover user section" and you will undoubtedly see the real King of Morocco - that sets a precedent.

If you are looking for an invitation link - here's mine I'd be glad to be your parent
https://www.tsu.co/alashazam