language: en
license: unknown
tags:
- stable-diffusion
- text-to-image
.safetensor model for automatic1111 webui.
Strange_Dedication_v3 is an improvement to Strange_Dedication_v2 using Anything_v4.5. It's better at the cutesexyrobutts style, without having to use a trigger. Also, it's good at shiny_skin and shiny_clothes and artistical backgrounds.
I have only used it with "vae-ft-mse-840000-ema-pruned", CLIP-Skip 1 and with danbooru tags. Lately I have started using the negative embed "bad-hands-5", which was used for the example images as well. If you work with those you should be able to prompt images like these (prompts in .png metadata):
Strange_Dedication_v2 is a model mix I did for myself. It's based mostly on two models, which are specialised in the artists cutesexyrobutts and free_style(yohan1754). I have added some different danbooru and r34 models to increase the affinity with uncommon prompts, can't specify which exactly.
I have only used it with "vae-ft-mse-840000-ema-pruned", CLIP-Skip 1 and with danbooru tags. If you work with those you should be able to prompt images like these (prompts in .png metadata):
The cutesexyrobutts style model had the trigger "by_cutesexyrobutts", which still works. The free_style(yohan1754) model worked without trigger, but maybe the artist name works as well, haven't tested it yet.