Hacker News Reader

> Supports up to 4.5k token input, effortlessly generating complex layouts such as newspapers, storyboards, and exam papers.

Impressive.

Btw, what is currently the best model to run locally on a 16GB Vram? Is it Z-Image Turbo?

View on HN

Krea-2-Turbo. I've even got it working locally on my M5 iPad Pro.

thanks mate. Sadly not supported yet by Invoke, but I will take a look.

> We implemented safety measures across the full model development lifecycle.

Any suggestions for the best open, non-opinionated model?

It is a reasonably non-opinionated model. My usual test is to ask these models to generate comic book and cartoon characters that hosted image generation models refuse to generate. I think that text is just CYA legalese.

What's your favourite (online or offline) model for image generation?

Krea-2-Turbo and Z-Image-Turbo, both offline.

You can also ablate it.

It depends on what you need, but Krea/Klein9b/Ideogram4/Z-Image are among the best right now for text2image and Qwen Edit and Klein are probably still the best at editing.

Reply on news.ycombinator.com