Hacker News Reader

Text only, when local multimodal became table stakes last year.

The community can always figure out hooking it up to other modalities.

Native might be better, but no native multimodal model is very competitive yet, so better to take a competitive model and latch on vision/audio

> so better to take a competitive model and latch on vision/audio

Can this be done by a third party or would it have to be OpenAI?

No, anyone can do it: https://github.com/haotian-liu/LLaVA

Honestly, it's a tradeoff. If you can reduce the size and make a higher quality in specific tasks, that's better than a generalist that can't run on a laptop or can't compete at any one task.

We will know soon the actual quality as we go.

That's what I thought too until Qwen-Image was released

When Queen-Image was released… like yesterday? And what? What point are you making? QwebImage was released yesterday and like every image model, its base model shows potential over older ones but the real factor is will it be flexible enough for a fine tune or additional training Loras.

Reply on news.ycombinator.com