News for hackers. Stuff that matters.
Re:SuperPrompt: Better Text to Image Prompts in 77M Parameters by lionkor on Thursday March 14, 2024 @04:34PM (#39708636)
> Left: Drawbench prompt "A rainbow penguin in a tuxedo". Right: SDXL output with SuperPrompt applied to the same input prompt.

Neither is wearing a tuxedo.

Re:SuperPrompt: Better Text to Image Prompts in 77M Parameters by roborovskis on Thursday March 14, 2024 @04:48PM (#39708777)
Yup, the model will still forget details sometimes. This is a common issue with prompt upsampling methods, but I'm hoping to improve this with the next version.
Re:SuperPrompt: Better Text to Image Prompts in 77M Parameters by hanniabu on Thursday March 14, 2024 @05:08PM (#39708996)
I wonder how much of that could be due to "tuxedo penguin" being a thing