AI Generative Artwork
AI Generative Art Work Experiments
AI Generarive Experiments
Some explorations and experiments using the most powerful AI tools in the current market
- All
- Dall-E
- MidJourney
- CrAIyon
- DreamStudio
- Adobe Firefly
- StarryAI
About GPT-4
ChatGPT is an advanced language model developed by OpenAI, based on the Generative Pre-trained Transformer (GPT) architecture. It's designed to understand and generate human-like text based on the input it receives. ChatGPT can perform a wide range of tasks, including answering questions, providing explanations, composing emails, writing creative content, and more. It's trained on a diverse range of internet text and is capable of understanding context, making it a versatile tool for generating coherent and contextually relevant text responses.
1. Research
GPT-4 is the latest milestone in OpenAI’s effort in scaling up deep learning.
View GPT-4 research
2. Infrastructure
GPT-4 was trained on Microsoft Azure AI supercomputers. Azure’s AI-optimized infrastructure also allows us to deliver GPT-4 to users around the world.
3. Limitations
GPT-4 still has many known limitations that we are working to address, such as social biases, hallucinations, and adversarial prompts. We encourage and facilitate transparency, user education, and wider AI literacy as society adopts these models. We also aim to expand the avenues of input people have in shaping our models.
4. Availability
GPT-4 is available on ChatGPT Plus and as an API for developers to build applications and services.
About MidJourney
Midjourney is an AI tool that specializes in generating images from textual descriptions. It uses advanced algorithms to interpret text prompts and translate them into visually detailed and creative images. This AI-driven approach allows users to create a wide range of visual content, from realistic scenes and objects to imaginative and abstract art, simply by describing what they want to see.
1. Discord Interface
You can interact with the Midjourney Bot on Discord. The Midjourney server has channels for working collaboratively, technical and billing support, official announcements, offering feedback, and discussions. The community is supportive, encouraging, and eager to share their knowledge with users just starting out.
Midjourney Discord https://discord.gg/midjourney
2. Direct Messages
Midjourney subscribers can work one-on-one with the Midjourney Bot in their Discord Direct Messages.
3. Image Prompts
You can use images as part of a prompt to influence a Job's composition, style, and colors. Images prompts can be used alone or with text prompts—experiment with combining images with different styles for the most exciting results.
4. Stylize
The Midjourney Bot has been trained to produce images that favor artistic color, composition, and forms. The --stylize or --s parameter influences how strongly this training is applied. Low stylization values produce images that closely match the prompt but are less artistic. High stylization values create images that are very artistic but less connected to the prompt.
About DreamStudio
DreamStudio is a web application for generating and editing images with Stability.ai’s latest Stable Diffusion models.
DreamStudio offers two distinct modes that can assist you with your image generation workflows:
A) Generate Mode: An image generation interface that allows you to prompt, perform image-to-image requests on uploaded images, and generate variations on images both in your generation history and ones uploaded directly into DreamStudio.
B) Edit mode: A canvas based editor mode that allows you to modify your creations by inpainting and outpainting your uploaded images or images carried over from your generation history.
1. User Interface
On logging into DreamStudio for the first time you'll first encounter the Generate Mode panel. Generate Mode is where you'll be able to generate your first images, alongside a number of other creative operations. See below for a breakdown of Generate Mode's various features.
2. Edit
DreamStudio’s Edit mode empowers artists to use their imaginations in powerful new ways! Change specific details about your images according to new prompts, create variations on specific images with your existing prompts, or expand your images outward with outpainting.
3. Introduction to Prompting
If you're new to the world of AI art, the idea of prompting may be intimidating. However, at its most basic form, prompting is merely using words to paint the picture of what it is you are looking to create. In this guide, we'll discuss the basic building blocks of a prompt to provide you with a solid foundation that can be used to generate the images of your dreams!
4. High-Quality Outputs
The AI algorithms can generate high-resolution, detailed images that are visually appealing and often indistinguishable from those created by human artists.
About CrAIyon
Previously known as DALL·E mini, Craiyon is the new kid on the tech block and the best AI art generator (in our community’s words!). The brainchild of our CEO, lead researcher, and AI hero, Boris Dayma, Craiyon is a free AI image generator that’s painting a new generation for the AI art revolution through our own model. Since 2022 They’ve been ushering in the next era of AI image generation.
If you can dream it, Craiyon can draw it. Thanks to our advanced in-house-developed tech, a simple text prompt is all Craiyon needs to turn your imagination into AI reality – in seconds.
1. Will Craiyon’s text-to-image AI always be free?
We hope so! Paying members also help us continue researching text to image model technology, generative AI, developing, and building new AI models to ensure your Craiyon experience only gets better and better. For our free AI art creators, ads help pay for our (incredibly expensive) AI models behind the scenes.
2. Is it related to DALL·E mini?
Yes, Boris Dayma who trained the current version of the AI model, Pedro Cuenca who worked on the backend, and Suraj Patil are part of the Craiyon team.
3. Images quality
They are constantly working on improving image quality. Make sure to use the "Upscale" option when there is an image you like to get a higher resolution. Their AI gets better every single day so the quality of the images will improve over time.
4. Negative words
Is there anything you definitely DON’T want to see in your AI generated art? Like an awkward hat on your drawing of Mozart painted by Van Gogh? No problem. In the “Negative Word” section, simply type out concepts you’d like Craiyon to avoid, like “hat”, or “crocs”. 😆
About Adobe Firefly
Adobe Firefly is a standalone web application available at firefly.adobe.com. It offers new ways to ideate, create, and communicate while significantly improving creative workflows using generative AI. In addition to the Firefly web app, Adobe also has the broader Firefly family of creative generative AI models, along with features powered by Firefly in Adobe’s flagship apps and Adobe Stock.
Firefly is the natural extension of the technology Adobe has produced over the past 40 years, driven by the belief that people should be empowered to bring their ideas into the world precisely as they imagine them.
1. Enhance the creative process.
The vision for Firefly is to help people expand upon their natural creativity. As both a product and an embedded model inside Adobe apps, Firefly offers generative AI tools made specifically for creative needs, use cases, and workflows.
2. Give creators practical advantages.
Trained on Adobe Stock images, openly licensed content, and public domain content, Firefly is designed to be safe for commercial use. To ensure that creators can benefit from generative AI, we’ve developed a compensation model for Adobe Stock contributors whose content is used in the dataset to retrain Firefly models.
3. Set the standard for responsibility.
Through efforts like the Content Authenticity Initiative and the Coalition for Content Provenance and Authenticity, we’re standing up for accountability, responsibility, and transparency in generative AI. We’re working toward a universal “Do Not Train” Content Credentials tag that will remain associated with a piece of content wherever it’s used, published, or stored.
4. Where does Firefly get its data from?
The current Firefly generative AI model is trained on a dataset of licensed content, such as Adobe Stock, and public domain content where copyright has expired.
As Firefly evolves, Adobe is exploring ways for creators to be able to train the machine learning model with their own assets so they can generate content that matches their unique style, branding, and design language without the influence of other creators’ content. Adobe will continue to listen to and work with the creative community to address future developments to the Firefly training models.
UX Design Articles
Learn more about AI, UX Design and Innovation
AI / Systemic Design