Dall-E3 Is Here And It’s Mind-Blowing
After ten months of silence, OpenAI has finally released Dall-E3, the latest version of its popular AI image generator. Dall-E3 is said to be a significant improvement with more nuance and details over Dall-E2.To better illustrate the difference, take a look at the example below. The two images used the same prompt: Prompt: A paper craft art depicting a girl giving her cat a gentle hug. Both sit amidst potted plants, with the cat purring contentedly while the girl smiles. The scene is adorned with handcrafted paper flowers and leaves. This example shows Dall-E3’s ability to understand and generate complex concepts. Among other things, I noticed the girl in the right image is neither smiling nor hugging the cat.
Another significant update is the ability to spell words correctly and legibly. For example, you could use Dall-E3 to generate a vintage travel poster: Prompt: A vintage travel poster for Venus in portrait orientation. The scene portrays the thick, yellowish clouds of Venus with a silhouette of a vintage rocket ship approaching. Mysterious shapes hint at mountains and valleys below the clouds. The bottom text reads, ‘Explore Venus: Beauty Behind the Mist’. The color scheme consists of golds, yellows, and soft oranges, evoking a sense of wonder.
0 Comments