This LoRa was trained with 203 images, which were cleaned of text.
All examples were processed using only Face Adetailer.
Regarding the trigger word:
The first word is mandatory for the LoRA to function; the others are additions to assist the model in achieving higher fidelity. Use the tags mentioned in the details section rather than the ones in this description, as these are provided merely as examples.
There are two types of recommended tags:
Style: Including tags like "Realistic", "Painterly", or "Sketch" in the prompt is highly recommended, as they help the LoRA fine-tune the style more effectively.
Concept/Situational: Tags such as "belly", "skindentation", or "plump" are used to replicate the artist's specific anatomy. However, they are NOT mandatory; if you omit them, you will still capture the artist's overall style.
Want to know how to get the most out of this LoRA? Check out this article!
Style Blending: "Create" new styles by mixing style LoRAs | Civitai
Please, if you think the style doesn’t match or if there are mistakes, let me know — I’ll be more than happy to review it.
Do you have a style request?
Leave it in the comments and I’ll make sure to write it down.
If you like the style, support the artist on their official social media:
If the artist requests it, this LoRa will be removed.
Made it this far?
If you like the model, let me know! Comments, feedback, suggestions, even insults—everything’s welcome.
Also, feel free to explore my model library — I’ve got many LoRAs in various styles that you might enjoy.
And if you’d like to support me, you can do so on Ko-fi. Even the smallest contribution means a lot and truly motivates me to keep making models and tools for the community.
Description
FAQ
Comments (6)
If you don't mind sharing, how do you create your LoRA's?
Sorry, but I'm too busy this week to explain it to you.
I can tell you that I use TensorArt to train LoRA. You can use a LoRA metadata Viewer page to see the settings I use.
I also have several articles talking about training and tools.
@Mexes Thanks!!
I really like this LoRA style, but when I try to generate images, it doesn’t work well and I can’t get consistent results. Do you have any tips for fine-tuning it? For reference, I’m a beginner.
The sample images have all the metadata with the settings, so you can remix them to get a solid foundation.
Some checkpoints work better than others with LoRAs. I recommend using Plant Milk - Walnut, as it's the most user-friendly one I've seen with LoRA styles.
@Mexes Thank you! I’ve actually been reading your previous posts and already downloaded and started using the Plant Milk – Walnut checkpoint. I followed your advice, and I’m quite satisfied with the results so far. From here on, it’s really up to my own efforts.