Type | |
Stats | 792 |
Reviews | (127) |
Published | Jul 8, 2023 |
Base Model | |
Training | Epochs: 29 |
Trigger Words | mixplin |
Hash | AutoV2 8B0ECDF505 |
If you enjoyed this model, why don't you check out my other works? I put a lot of effort into correctly recreating artist styles and making the occasional character LoRA.😊
This model was trained for NAI/AOM3 using the collab/guide by holostrawberry [Guide] Make your own Loras, easy and free - colabs | Stable Diffusion Other | Civitai
About the artist:
Patreon: Mixplin | creating spicy illustrations | Patreon
Twitter: Mixplin (@mixplin) / Twitter
This one worked out really well. Having few images with weird anatomy or textboxes means the world to the algorithm.
Mixplin is a pure NSFW artist and unsurprisingly this lora tends to minimize clothing if not otherwise specified. They make a lot of femboy and futanari content which I mostly left out of the dataset. So it kinda works if prompted but stays out otherwise.
Weights & Prompts
LoCon:
Use a weight of 1.0, adjust to taste.
LoRA:
A weight of 1 works when used by itself. For most character lora I used 0.75 which is pretty stable. The model doesn't need a keyword. Don't ask me how that happened. I don't have a clue.
While this is an nsfw lora, don't hesitate to try it with other prompts. It's always fun to see what kind of effect it has on other images. I have attached a comparison of a simple landscape prompt with and without the model.
Please leave a review if you enjoyed this model or have problems with it. I'd also be interested in how the model behaves with other base checkpoints, so why don't you give it a try and throw some images down below! 👇