You can use Dalle 3 completely free on the Bing AI website.
Additionally, the image generation itself is quite different. ChatGPT's DALL-E seems to create much more stylized images - much harder to get plain shots that don't heavily embellish your description.
My own observation: this kind of hack is possible only since/with GPT-4 - it takes an LLM this powerful to reliably extend and enrich arbitrary user input into much longer prompt, that's coherent, consistent, and a plausible (to human) interpretation of the original input.
Now this may fan the flames on the "is it or is it not" AI discussions, but: you could almost say that GPT-4 is engaging in creative process here.