GitLab

After some quick tests compress_level=4 seems to give the best compression
performance ratio for stable diffusion images.

It's 10x faster than max compression for an image size increase of only
2.5%.

Workflows will be auto updated.

Fixed jpg
Added dupe support
Changed to use existing nodes

It needs the CLIPVision model so I added CLIPVisionLoader and CLIPVisionEncode.

Put the clip vision model in models/clip_vision
Put the t2i style model in models/style_models

StyleModelLoader to load it, StyleModelApply to apply it
ConditioningAppend to append the conditioning it outputs to a positive one.

from the CLIPLoader node.

Use a more simple way to detect if the model is -v prediction.