This model has been renamed to WoopWoop-General, as it is now a general-purpose model that can handle a huge variety of styles and subjects.
Latest release is 2.0 BETA, please read the version description for information on how to use this model. This is a TEST MODEL, if you want something with predictable results please use version 1.1.
A model trained to make detailed, anatomically-accurate (hands, faces, ????????, etc) illustrations of humans and non-humans alike. This is the model aiming at photorealism. Trained to require few negative prompts (see examples). For the anime/hentai model, see here.
Suggested style prompt: ((photograph, photographic photo, photogenic, rule of thirds))
I highly suggest using vae-ft-mse-840000-ema-pruned.ckpt with this version.
Easy Launch on Vast.AI:
Follow this guide on how to launch Stable Diffusion on Vast.AI, except where it says to put "/start.sh" in as the on-start script, instead copy/paste in the contents of this file instead.
Description
Complete rework of the models and datasets used. In order to get better skin texture, there is significantly more NSFW content in this model. This second alpha version is no longer "horny" like the first, so I've removed the NSFW tag. This model is still CAPABLE of whatever you want, but I do not showcase its NSFW capabilities publicly on this page.
Limited example images for now, as this is in Alpha state. Currently not fine-tuned specifically for photographic material, so I suggest using the following negative prompt:
(anime hentai illustration 3d render drawing:0.6)
This will dramatically reduce the impact of the illustrative content in the model without removing it completely, which gives results similar to what 2.0 Beta will have (when photo-specific fine-tuning is complete).
Works best with LMS Karras, 4-7 CFG, 12-36 steps.