With NightCafe SDXL 1.0 I ran the single word text to image prompt “Sinister” with the following Negative prompts.
“text, signature, blood, bones, trees, moonlight, beautiful, woman, boring, sepia, cute”
Despite adding “text” to the negative prompt the generated image included text. It looks like a failed attempt at trying to create a page of a graphic novel or comic book. There is a comic book character called Sinister from the X-Men franchise. Maybe the AI was leaning towards that?
I guess there wasn’t enough in the positive prompt (just one word) and too much going on in the negative prompt. I rarely run single word prompts, so this probably wouldn’t be a problem if the positive prompt was of a reasonable size.
Continue Reading DALL-E 3 vs Stable Diffusion XL 1.0 : Prompt Test - Sinister





DALL-E 3 AI image: a man standing on top of a beach next to...
Stable Diffusion XL 1.0 AI image: a painting of a woman with flowers in...
DALL-E 3 AI image: a woman with blonde hair and blue eyes, trending on...
The reason for this AI text to image creation test was to determine how faithfully...
This Playground 2.5 AI generated image was from the text to image prompt: The Persistence...
DALL-E test prompt - Terrifying, Ghostly, Shadow Vampire by Greg Rutkowski. Horror, contrasting colors, action...