"AI models don’t contain reality. They rely on the complex statistical abstraction of digital data. This limits their real-world creative significance and their capacity to produce “eureka” moments.
To differentiate AI-driven creativity from old-fashioned creativity, I have proposed a new term: generic, or g-type, creativity. It formalises the fact that while AI models are capable of provoking new thought, they are limited by the underlying data they have been trained on."
Since it's now so easy to create beautiful images the challenge is to come up with ways to introduce difficulties in order to end up with beautiful /interest images that are NOT easy to create. Comments?
Since it's now so easy to create beautiful images the challenge is to come up with ways to introduce difficulties in order to end up with beautiful /interest images that are NOT easy to create. Comments?
@WeavingWithAI in Auto1111, adding random words (I sometimes add both general and common 9-letter words using a prompt-creator I wrote in Processing), and adding several LoRA's at low amounts can help - but it's more a case of suck it and see (which again, I have some automation around). The way AI "bleeds" concepts (eg: "marbling" doesn't only apply to floors, it applies (in the AI's mind) to skin, clothes erc) can often generate interest. boring Composition is perhaps the hardest to avoid
Prompt: Then, during the Third Reconciliation of the Last of the Meketrex Supplicants, they chose a new form for him, that of a giant Sloar! Many Shubs and Zuuls knew what it was to be roasted in the depths of a Sloar that day, I can tell you!