This notebook demonstrates how to generate images using diffusion models. It provides examples of different models and prompts you can use to generate images.
To run this notebook, you'll need Google Colab, HERE
Here is the notebook :
Simple :
Advanced :
Short Explanation About Google Colab :
Google Colab, short for Google Colaboratory, is a cloud-based platform provided by Google that allows users to write and execute Python code within a web-based integrated development environment (IDE). It offers a convenient and free environment for developing and running machine learning models, data analysis, and various data science tasks.
You can choose from different diffusion models to generate images. Select one of the following models and run the respective cell to set up the model.
Realisian Model: OUTPUT EXAMPLE
Waifu Diffusion Model: OUTPUT EXAMPLE
OrangeMix Model: OUTPUT EXAMPLE
You can specify a prompt to generate images using the selected model. There is some required prompt so that the image can be generated :
Prompt : start with a written description, often in natural language, that conveys what you want to see in an image. This can be a detailed description of objects, scenes, characters, or any visual concept.
Negative Prompt : a "negative prompt" is a textual input that is used to guide the model in generating images that are different from what the prompt describes or specifies. It's essentially a way to instruct the model to avoid certain features or characteristics in the generated image.
Width: The width of the image represents the number of horizontal pixels in the generated image. It determines how wide the image will be from left to right.
Height: The height of the image represents the number of vertical pixels in the generated image. It determines how tall the image will be from top to bottom.
You can also use the code cell to fix false NSFW detection if required.
Enjoy generating images using diffusion models! You can modify prompts and explore different models to create stunning images.