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.
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.
We will know soon the actual quality as we go.