| Please consider joining my Patreon! Advanced SD tutorials, explanations, exclusive embeddings, adult-art, from a female content creator (me!) patreon.com/theally | |
| A THIRD version?! | |
| Yup! But my first NSFW 🔞 focused release. Sure, it does good SFW portraits, and other content, but it excels at the naughty stuff. It also contains the amazing Noise Offset code/process, so it produces EXCELLENT darkness - true darkness, which hasn't really been consistently possible until now. Lots of great contrast, deep shadows, etc. It's very grim and moody. | |
| What's in it? | |
| I've taken my Ally's Mix II: Churned, cut in a dash of my favourite model, ReV Animated, then taken the result of that + Noise Offset - SD 1.5. | |
| STOP AND READ, LoRA FANS! | |
| This is mixed with the OG Noise Offset model by Nicholas Guttenberg at Crosslabs | |
| You cannot - CANNOT - extract a LoRA from this model and get similar results to the model. The noise offset does not extract. You have to train the noise offset in, or cut it in with a difference merge. | |
| If you extract this model to LoRA, it will look like shit, and kids will point and laugh at you in the street. | |
| I am making a LoRA from this model, the correct way, ty 💗 | |
| Recreating my sample images?! | |
| Some of my sample images are created with ControlNet, to get poses and compositions from my previous generations - you'll never be able to reproduce those. Others, it's possible, but some do use Patron exclusive embeddings. The sample images are meant to show what's possible with a model. I do have a tutorial on Patreon on recreating my images, the common settings I use, etc. |