In the space of AI image generators, which operate on a text prompt, the leaders seem to be Musk’s GrokAI, Open AI’s Dall-E, and Google’s Imagen. In the case of the latter
Trying out a simple prompt like “Generate an image of a bullet train speeding towards Banff”:
Imagen allows you to modify the previous image, just by referring to it: “make the train faster”
Initial versions of images are fairly literal, just mashups of other real images. For example: “Generate an image of a panda playing volleyball”:
For example: “Generate an image of a cartoon panda playing volleyball”:
Then “now add in a volleyball net”:
Kind of fun to play with. Bit scary as these images become more and more realistic over time.
More in this series…
- Google Gemini - Google Gemini
- Anthropic Claude - Anthropic Claude
- Llama 3 - Llama 3
- ChatGPT 4o - ChatGPT 4o
- Anthropic Claude in Canada - Anthropic Claude in Canada
- LLMs on Android - AI in your pocket
- Google Gemma - Google Gemma v3 released.