对DALL-E 2的初步分析
A very preliminary analysis of DALL-E 2
摘要:
DALL-E 2系统生成对应于输入文本的原始合成图像作为字幕。我们在这里报告的结果,该系统的14个测试,旨在评估其常识,推理和理解复杂文本的能力。我们所有的提示都有意比最近几周展示的典型提示更具挑战性。尽管如此,在14个提示中,有5个提示中的10个图像中至少有一个完全满足了我们的要求。另一方面,在没有提示的情况下,所有的十个图像都满足了我们的要求。
英文摘要:
The DALL-E 2 system generates original synthetic images corresponding to an input text as caption. We report here on the outcome of fourteen tests of this system designed to assess its common sense, reasoning and ability to understand complex texts. All of our prompts were intentionally much more challenging than the typical ones that have been showcased in recent weeks. Nevertheless, for 5 out of the 14 prompts, at least one of the ten images fully satisfied our requests. On the other hand, on no prompt did all of the ten images satisfy our requests.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。