Generative AI: Images & Art
AI Image Generation (including Art Generation). Complex machine learning models that generate images often based on input text, other images or both. Recently, they’ve got a lot of attention as the models’ results are getting better and better. Almost monthly we can witness new astounding breakthroughs, making us wonder where could this lead to.
As we have seen many different AI image generation models, we think these ones deserve special attention:
Midjourney [By self-funded team called Midjourney; you can apply for their beta version for great art generation]
DALL-E 2 [By OpenAI; image editing e.g. replacing a dog with a cat; realistic image generation e.g. Koala that makes a dunk; watch video for more]
Nightcafe [By NightCafe Studio; compelling art generation; print to hang in your home or office]
Deep Dream Generator [By Google; famous for running images backwards through differently pre-trained neural networks]
Artbreeder [By Joel Simon; Tech - a StyleGAN + BigGAN - see open source version here; one can breed images and users can collaborate in the sense of merging their results]
Parti AI [By Google; most imaginative results + understands to include the right text in the image itself; Tech - autoregressive]
🔥 Parti AI outperforms all other AI Image models by being able to accept large text prompts (a challenge for other models) and with its autoregressive approach (splits image generation into simpler sub-problems) generates images imaginatively in high-quality and high resolution. Most impressive: it is even capable of generating text on signs in its results, but only if the model is big enough (~20 Billion parameters).
Watch Parti AI’s crazy results (read description below):
💡 What could this mean?
3D object generation: What if we go from 2D to 3D? Imagine 3 dimensional images translated into the right coordinates, creating a CAD file out of it, and perhaps being able to print 3D objects out of these files. There is already generative design, trying to find the optimum between material used and stability. However, this could go much further. Any ideas?
Third-party integrations: What could the opportunity be? Software to software, for a seamless life cycles for design? Imagine you could create web apps or a webpages just from a written workflow list describing its actions after certain buttons being clicked - all in various design themes that you choose.
Software for professionals: A tool where interior designer can upload the layout of an apartment and let it pre-design into e.g. 1766, American Colonial, mainly green. The professionals perform the fine-tuning and harder creative work.
Parti (Pathways Autoregressive Text-to-Image model) Research & Webpage.
Lastly, we believe these AI tools are ideal for developing thoughts and drawings, which then can be enhanced and customized. They support artists, designers, and developers rather than replace them. 🧡