![Lvi style - Tomboys and Tanlines Edition [Pony XL]版本v1.0 (ID: 625481)](https://image.1111down.com/xG1nkqKTMzGDvpLrqFT7WA/487ba4eb-1002-4418-bfa2-1e35206ab424/width=450/18752334.jpeg)
Click "Generate". Receive tomboy. Simple as.
How to use
Prompt as usual, tags that work well are "tanlines", "swimsuit", "short hair", "skintight" and general tomboy tropes. The "tomboy" tag in Pony XL is very strong and might emphasize the "boy" a bit too much when used depending on your preferences.
A lot of the images consisted of happy smiles with eyes closed so unless you specify an eye color, direction to look or similar that's what they often default too. There's also a couple of group shots so remember to use "solo" for single character gens just to be safe.
For more specific prompt tips please see the sample image or the uploaded zip with training tags.
MISC
Dataset of 48 images, most manually cleaned and processed, trained at 1024 resolution on Pony XL.
All sample images are raw txt2img upscaled, no helper embeddings/negatives used. E.g. - things should look even better if you do.
The training was done on a small subset of images, as such the output of this LoRA is not an accurate representation neither in quality or style of the source material. Go support the artist if you want the good stuff.
描述:
Initial release
训练词语:
名称: Lvi-PonyXL-1024px.safetensors
大小 (KB): 111757
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
名称: LviTrainingTags.zip
大小 (KB): 5
类型: Training Data
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success