A true return to form - this is quite similar to the previous 6.0 model but it's improved by a... quite important 5%. Images will be similar, but I trained a few LoRAs that I've merged with the model in order to tell it what types to images to avoid. This has been quite a long journey and after more than 250 iterations I've finally reached a new high for this model.
The whole point for this and other models I create is to bring results that don't really looks like AI, they might be a little bit stubborn and might require multiple img2img evolutions to get exactly what you're looking for - but if you're still a fan of SD1.5, you probably know what you're going to get.