開局先上超級英雄：

感覺如何？這些可是通過直接用陳述性文字直接產(chǎn)生的圖片哦！為了實現(xiàn)這種效果，需要先安裝一個插件：

https://github.com/hallatore/stable-diffusion-webui-chatgpt-utilities

安裝好后的界面是這個樣子的：

以上面的蜘蛛俠為例，輸入的提示詞為：

Beautifully illustrated scene of Spiderman standing tall on an iconic skyscraper, taking in the breathtaking beauty of the modern, polished city below. A remarkable and stylized portrayal of a nefarious villain. by J. Scott Campbell's and Jim Lee's heavily detailed and dynamic

怎么樣？不像傳統(tǒng)的文生圖要輸入多個詞組吧？此外還有其他參數(shù)不要忘了：

Negative prompt:?NSFW, nudity, By bad artist, (worst quality:2), (low quality:2), (normal quality:1.2), lowres, (bad proportions:1.331), extra limbs, (missing arms:1.331), (extra legs:1.331), (fused fingers:1.61051), (too many fingers:1.61051), (unclear eyes:1.331), bad hands, missing fingers, extra digit, bad body, (out of frame:2)

Steps: 22, Sampler: UniPC, CFG scale: 6.5, Seed: 2247828476, Size: 448x832, Model hash: 76b00ee812, Model: icomix_V02Pruned, Denoising strength: 0.7, Clip skip: 2, Hires upscale: 2, Hires upscaler: Latent

心不心動？趕緊上手試試吧！