Python Qt6 : tool for game development with PNG images.

Today, I worked with art artificial intelligence, to create tool for my game development.

I used python and PyQt6 and this tool help me to remove border, resize, split, rename and save images as PNG file type for Godot game engine.

Python 3.11.11 : Colab simple image to video with stabilityai - part 052.

Today, a simple test with artificial intelligence and stabilityai/stable-video-diffusion-img2vid-xt.

The result is not very good, but I believe the source code can be improved ...

pipe = StableVideoDiffusionPipeline.from_pretrained(
    'stabilityai/stable-video-diffusion-img2vid-xt',
    torch_dtype=torch.float16,
    variant='fp16'
)

pipe.enable_model_cpu_offload()

You can find the source code on my colab GitHUb projects - catafest_069.

Python 3.13.3 : ... Nuitka package works with python 3.12 and MinGW.

Nuitka is licensed under the Apache License, Version 2.0; you may not use it except in compliance with the License.

Nuitka is the Python compiler. It is written in Python. It is a seamless replacement or extension to the Python interpreter and compiles every construct that Python 2 (2.6, 2.7) and Python 3 (3.4 - 3.13) have, when itself run with that Python version.

Nuitka translates the Python modules into a C level program that then uses libpython and static C files of its own to execute in the same way as CPython does.

I used the pip command:

python -m pip install -U nuitka
Collecting nuitka
  Downloading Nuitka-2.7.tar.gz (3.9 MB)
...
Successfully built nuitka
Installing collected packages: zstandard, ordered-set, nuitka
Successfully installed nuitka-2.7 ordered-set-4.1.0 zstandard-0.23.0

[notice] A new release of pip is available: 25.0.1 -> 25.1.1
[notice] To update, run: python.exe -m pip install --upgrade pip

This version of python : 3.13.0rc1 not work !!!

I need to upgrade my version to 3.13.3 version today after I open an issue on github repo!

python.exe -m pip install --upgrade pip
...
Successfully installed pip-25.1.1

python -m nuitka --version
2.7
Commercial: None
Python: 3.13.0rc1 (tags/v3.13.0rc1:e4a3e78, Jul 31 2024, 20:58:38) [MSC v.1940 64 bit (AMD64)]
Flavor: CPython Official
GIL: yes
Executable: C:\Python313\python.exe
OS: Windows
Arch: x86_64
WindowsRelease: 10
Nuitka-Scons:WARNING: Windows SDK must be installed in Visual Studio for it to be usable
Nuitka-Scons:WARNING: with Nuitka. Use the Visual Studio installer for adding it.
Version C compiler: ~\AppData\Local\Nuitka\Nuitka\Cache\downloads\gcc\x86_64\14.2.0posix-19.1.1-12.0.0-msvcrt-r2\mingw64\bin\gcc.exe (gcc 14.2.0).

After upgrade the nuitka show me these results:

python -m nuitka --version
2.7
Commercial: None
Python: 3.13.3 (tags/v3.13.3:6280bb5, Apr  8 2025, 14:47:33) [MSC v.1943 64 bit (AMD64)]
Flavor: CPython Official
GIL: yes
Executable: C:\Python313\python.exe
OS: Windows
Arch: x86_64
WindowsRelease: 10
Nuitka-Scons:WARNING: Windows SDK must be installed in Visual Studio for it to be usable
Nuitka-Scons:WARNING: with Nuitka. Use the Visual Studio installer for adding it.
Version C compiler: ~\AppData\Local\Nuitka\Nuitka\Cache\downloads\gcc\x86_64\14.2.0posix-19.1.1-12.0.0-msvcrt-r2\mingw64\bin\gcc.exe (gcc 14.2.0).

Same error, I uninstall the Python: 3.13.3 version and I install the python version 3.13.0 and use the pip again to install this python package.

python -m pip install -U nuitka
Collecting nuitka
...
Installing collected packages: zstandard, ordered-set, nuitka
Successfully installed nuitka-2.7 ordered-set-4.1.0 zstandard-0.23.0

[notice] A new release of pip is available: 24.2 -> 25.1.1
[notice] To update, run: python.exe -m pip install --upgrade pip
python.exe -m pip install --upgrade pip
Requirement already satisfied: pip in c:\python_3_13_0\lib\site-packages (24.2)
...
Successfully installed pip-25.1.1

Using this version tell me same error with Windows and Visual Studio, but the MinGW is install from the first version.

The solution from artificial intelligence is to use another python version.

I used these commands:

py -3.12 -m pip install -U nuitka
Collecting nuitka
  Using cached Nuitka-2.7.tar.gz (3.9 MB)
  Installing build dependencies ... done
  ...
  Installing collected packages: zstandard, ordered-set, nuitka
Successfully installed nuitka-2.7 ordered-set-4.1.0 zstandard-0.23.0

[notice] A new release of pip is available: 24.2 -> 25.1.1
[notice] To update, run: C:\Python312\python.exe -m pip install --upgrade pip
py -0
 -V:3.13 *        Python 3.13 (64-bit)
 -V:3.12          Python 3.12 (64-bit)
py -3.12 -m nuitka --mingw64 hello.py
Nuitka-Options: Used command line options:
Nuitka-Options:   --mingw64 hello.py
Nuitka-Options:WARNING: You did not specify to follow or include anything but main
Nuitka-Options:WARNING: program. Check options and make sure that is intended.
Nuitka: Starting Python compilation with:
Nuitka:   Version '2.7' on Python 3.12 (flavor 'CPython Official')
Nuitka:   commercial grade 'not installed'.
Nuitka: Completed Python level compilation and optimization.
Nuitka: Generating source code for C backend compiler.
Nuitka: Running data composer tool for optimal constant value handling.
Nuitka: Running C compilation via Scons.
Nuitka-Scons: Backend C compiler: gcc (gcc 14.2.0).
Nuitka-Scons: Backend C linking with 6 files (no progress information available for
Nuitka-Scons: this stage).
Nuitka-Scons: Compiled 6 C files using ccache.
Nuitka-Scons: Cached C files (using ccache) with result 'cache miss': 6
Nuitka: Keeping build directory 'hello.build'.
Nuitka: Successfully created 'D:\PythonProjects\hello.exe'.
Nuitka: Execute it by launching 'hello.cmd', the batch file needs to set environment.

The test is a simple python script from the official website:

def talk(message):
    return "Talk " + message

def main():
    print(talk("Hello World"))

if __name__ == "__main__":
    main()

... and this python version works well with MinGW, the artificial intelligence used to fix these errors was ChatGPT.

hello.exe
Talk Hello World

Python 3.13.0rc1 : ... fal artificial intelligence and python test.

We have the most-popular models implemented and available as API endpoints for you to start crafting your own AI-powered app today. From the fal.ai website !

You need to set your A.P.I. key from this url.

system32>setx.exe FAL_KEY "e6fd708c-8065-4c73-ac2a-e3c73c6ff0fe:f70e0adb08362a3073993efa31b6acee"

SUCCESS: Specified value was saved.

Open a new terminal and with your editor create this simple example ...

import fal_client

response = fal_client.run("fal-ai/fast-sdxl", arguments={"prompt": "a cute cat, realistic, orange"})
print(response["images"][0]["url"])

Into the terminal run the python script and you will find the url of the image :

python test_fal_client_001.py
https://v3.fal.media/files/rabbit/kY2MZG6LLkzjyIT8J3oiI.jpe

This is the result output of the running source code as 1024px image, see the resize 112px I created:

Python 3.13.0rc1 : pig for AI-powered automation.

Pig is an API for AI-powered automation of Windows desktop applications and workflows. It allows AI agents to remotely navigate user interfaces and interact with software on Windows computers, even for applications without public APIs. Organizations might use Pig to automate complex, repetitive tasks involving legacy enterprise software, overcome limitations of traditional robotic process automation tools, and reduce the need for manual data handling by human workers.

Follow the install from the official website.

pip install pig-python
Collecting pig-python
...
Successfully installed aiohttp-retry-2.9.1 click-8.1.8 iso8601-2.1.0 pig-python-0.1.2 simple-term-menu-1.6.6 tabulate-0.9.0

From the API Keys url get the key and run a server:

piglet join --secret the_API_key
Display dimensions: 1280x720
Local server running at http://localhost:3000
Connected to control server

The local machine can be found on this webpage.

I go to machine chat and I ask to create a source script in python for test the artificial intelligence.

It looks like you're encountering an error with the Pig API. The error message indicates that the API key hasn't been set properly. To resolve this issue, you need to set the PIG_SECRET_KEY environment variable or pass the API key directly to the Client constructor when initializing the Pig client. Would you like me to help you with setting up the environment variable or modifying your code to include the API key in the Client constructor? yes , I need a python script example

The remote artificial intelligence machine move the mouse and open notepad, add source code and save to my desktop.

I add my API key and I run it, see the result:

This source script is the result of artificial intelligence processing

"""
Example script showing how to properly initialize the Pig client with an API key
using both environment variable and direct constructor methods.
"""

import os
from pig import Client

# Example API key (replace with your actual API key in production)
API_KEY = "SK-..."

def initialize_with_env_variable():
    """
    Method 1: Initialize Pig client using environment variable
    This is the recommended approach for production environments
    """
    # Set the environment variable
    os.environ["PIG_SECRET_KEY"] = API_KEY
    
    # Initialize the client (it will automatically use the environment variable)
    client = Client()
    
    print("Client initialized using environment variable")
    return client

def initialize_with_direct_key():
    """
    Method 2: Initialize Pig client by passing the API key directly
    Useful for testing or when environment variables are not preferred
    """
    # Initialize the client by passing the API key directly to the constructor
    client = Client(api_key=API_KEY)
    
    print("Client initialized by passing API key directly")
    return client

if __name__ == "__main__":
    # Example 1: Using environment variable
    client1 = initialize_with_env_variable()
    
    # Example 2: Passing API key directly
    client2 = initialize_with_direct_key()
    
    # Both methods achieve the same result
    print("Both initialization methods are complete!")

News : Ollama-Adaptive-Image-Code-Gen project test - need more memory.

Python code that leverages a language model (such as LLaMA) to generate images featuring basic shapes in 2D or 3D. The script randomly selects shapes, colors, and areas to create diverse visuals. It continuously generates images based on AI-generated code, validates them, and provides feedback for iterative improvements.

This source code can be found on this GitHub project named Ollama-Adaptive-Image-Code-Gen.

You can download this and use these commands to run and test this feature of create and generate images with ollama.

NOTE: Compose up process might upto 20 - 25 Mins. first time. Because it will download all the respective ModelFiles

Let's start:

git clone https://github.com/jaypatel15406/Ollama-Adaptive-Image-Code-Gen.git
Cloning into 'Ollama-Adaptive-Image-Code-Gen'...
Resolving deltas: 100% (30/30), done.

cd Ollama-Adaptive-Image-Code-Gen

Ollama-Adaptive-Image-Code-Gen>pip3 install -r requirements.txt
Collecting ollama (from -r requirements.txt (line 1))
...
Installing collected packages: propcache, multidict, frozenlist, aiohappyeyeballs, yarl, aiosignal, ollama, 
aiohttp
Successfully installed aiohappyeyeballs-2.4.8 aiohttp-3.11.13 aiosignal-1.3.2 frozenlist-1.5.0 multidict-6.1.0
ollama-0.4.7 propcache-0.3.0 yarl-1.18.3

Ollama-Adaptive-Image-Code-Gen>python main.py
 utility : pull_model_instance : Instansiating 'llama3.1' ...
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : pulling manifest
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : pulling 667b0c1932bc
 

Seams to work but I need more memory:

Ollama-Adaptive-Image-Code-Gen>python main.py
 utility : pull_model_instance : Instansiating 'llama3.1' ...
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : pulling manifest
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : pulling 667b0c1932bc
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : pulling 948af2743fc7
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : pulling 0ba8f0e314b4
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : pulling 56bb8bd477a5
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : pulling 455f34728c9b
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : verifying sha256 digest
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : writing manifest
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : success

=========================================================================================

 utility : get_prompt_response : Prompt : Choose the dimension of the shape: '2D' or '3D'. NOTE: Return only the chosen dimension.
ERROR:root: utility : get_prompt_response : Error : model requires more system memory (5.5 GiB) than is available (5.1 GiB) (status code: 500) ... 

Python 3.13.0rc1 : testing the elevenlabs with artificial intelligence.

Today I teste the elevenlabs python package to use it with artifical inteligence to create sound.

I install this python package with pip tool, I created a python script file and the basic script run well with the api key from the official website.

pip install elevenlabs
Collecting elevenlabs
...
Installing collected packages: websockets, sniffio, pydantic-core, h11, annotated-types, pydantic, httpcore, anyio, httpx,
elevenlabs
Successfully installed annotated-types-0.7.0 anyio-4.8.0 elevenlabs-1.52.0 h11-0.14.0 httpcore-1.0.7 httpx-0.28.1 
pydantic-2.10.6the official website pydantic-core-2.27.2 sniffio-1.3.1 websockets-15.0
...
pip install playsound
Collecting playsound
...
Installing collected packages: playsound
Successfully installed playsound-1.3.0
...
python elevenlabs_test_001.py
Fișierul audio a fost salvat la generated_audio.mp3

This is the source code:

import io  # Importarea bibliotecii io
from elevenlabs import ElevenLabs
from playsound import playsound
import tempfile
import os

# API Key pentru ElevenLabs
api_key = "API_KEY"
voice_id = "JBFqnCBsd6RMkjVDRZzb"


# Configurarea clientului ElevenLabs
client = ElevenLabs(api_key=api_key )

# Textul pe care vrei să-l convertești în audio
text = 'Hello! This is a test without mpv.'

# Generarea audio
audio_generator = client.generate(text=text, voice=voice_id)

# Colectarea datelor din generator într-un obiect BytesIO
audio_data = io.BytesIO()
for chunk in audio_generator:
    audio_data.write(chunk)
audio_data.seek(0)  # Resetarea pointerului la începutul streamului

# Specificarea căii de salvare pentru fișierul audio
save_path = 'generated_audio.mp3'

# Salvarea audio într-un fișier temporar
with tempfile.NamedTemporaryFile(delete=False, suffix='.mp3') as temp_audio:
    temp_audio.write(audio_data.read())
    temp_audio_path = temp_audio.name

# Redarea fișierului audio utilizând playsound
playsound(temp_audio_path)

# Salvarea fișierului audio generat într-o locație specificată
with open(save_path, 'wb') as f:
    audio_data.seek(0)  # Resetarea pointerului la începutul streamului pentru a citi din nou datele
    f.write(audio_data.read())

print(f'Fișierul audio a fost salvat la {save_path}')

News : Python and Grok 3 Beta — The Age of Reasoning Agents

On the official website of x.ai you can find this:

We are thrilled to unveil an early preview of Grok 3, our most advanced model yet, blending superior reasoning with extensive pretraining knowledge.

You can find a simle and good example with python and pygame how this can be used.

The Grok 3 artificial inteligence is used for :

Research

Brainstorm

Analyze Data

Create images

Code

For me, the artificial intelligence help me to be more fast into coding versus issues and bugs, game design, parse and change data.

I don't test this Grok 3, but I can tell you some artificial inteligence into develop area are bad even they say is dedicated to this issue.

Python 3.13.0rc1 : Testing python with Ollama local install.

I was very busy with development and testing for about two weeks and my laptop was stuck and I was working hard... Today I managed to test local background clipping on my laptop with a local Ollama installation separated by a Python module but with processing from the Python script. I also used Microsoft's Copilot artificial intelligence for python and it works well even though it is not theoretically specialized in development. The source code is quite large but the result is very good and fast:

import subprocess
import os
import json
from PIL import Image, ImageOps

class OllamaProcessor:
    def __init__(self, config_file):
        self.config_file = config_file
        self.model_methods = self.load_config()

    def load_config(self):
        try:
            with open(self.config_file, 'r') as file:
                config = json.load(file)
            print("Configuration loaded successfully.")
            return config
        except FileNotFoundError:
            print(f"Configuration file {self.config_file} not found.")
            raise
        except json.JSONDecodeError:
            print(f"Error decoding JSON from the configuration file {self.config_file}.")
            raise

    def check_ollama(self):
        try:
            result = subprocess.run(["ollama", "--version"], capture_output=True, text=True, check=True)
            print("Ollama is installed. Version:", result.stdout)
        except subprocess.CalledProcessError as e:
            print("Ollama is not installed or not found in PATH. Ensure it's installed and accessible.")
            raise
... 

Here is the result obtained after finishing running in the command line:

python ollama_test_001.py
Configuration file ollama_config.json created successfully.
Configuration loaded successfully.
Ollama is installed. Version: ollama version is 0.5.7

Available models: ['NAME']
pulling manifest
pulling 170370233dd5... 100% ▕██████████████▏ 4.1 GB
pulling 72d6f08a42f6... 100% ▕██████████████▏ 624 MB
pulling 43070e2d4e53... 100% ▕██████████████▏  11 KB
pulling c43332387573... 100% ▕██████████████▏   67 B
pulling ed11eda7790d... 100% ▕██████████████▏   30 B
pulling 7c658f9561e5... 100% ▕██████████████▏  564 B
verifying sha256 digest
writing manifest
success
Model llava pulled successfully for method process_images_in_folder.

Some "Command failed ..." but the result is cutting well and it has transparency !