I noticed a distinct lack of biomechanical and body horror style loras for SDXL, so I cooked up this abomination. Trained on a variety of cgi and AI generated images in an attempt to get it to work with a wide variety of styles. It can at the very least manage anime and photorealism to a certain degree. While "flesh" and "mutant" seem to be the most reliable trigger words, it seems to trigger off of a variety of horror related keywords so you'll have to play around with it. Also works to some degree with biomechanical subjects (the merged version is much better at generating cyborg and robotic characters). The merged version of the model should be used with lower weight ranges (0.35-0.6) because its a combination of multiple loras, some of which may be over trained.
Description
Trained on the same dataset as V3 with tweaked captions and fewer epochs at a lower resolution. Interestingly training SDXL at lower resolutions doesnt seem to impact the quality of the model all that much in my experience, especially if upscaling is used. Due to a lower training count for each individual concept used, it may not be as adept at generating individual features as V3, but it does seem to produce slightly higher quality upscaled images.