This looks like important research, but the pre-trained models may not do what you hope. From the model card [1]:

> These models sometimes produce highly unrealistic outputs, particularly when generating images containing human faces. This may stem from ImageNet's emphasis on non-human objects.

I guess we’ll see what other companies do with this research? It would be great to have image generation times that are closer to image search.

[1] https://github.com/openai/consistency_models/blob/main/model...