Type | |
Stats | 416 1,837 |
Reviews | (57) |
Published | May 1, 2024 |
Base Model | |
Usage Tips | Strength: 0.9 |
Training Images | Download |
Hash | AutoV2 C97709D0B9 |
A colorful style that makes chibis similar to the works of the artist renren_(ah_renren)
How to use
While there is no trigger I highly recommend using the tag "chibi". It'll work without it but you'll likely get a fairly generic 2D style, albeit a bit more colorful.
The dataset consisted entirely of "1girl" shots against a "white background"/"simple background" so you either want to prompt that or specify another backdrop.
The characters were fairly varied with everything with touhous, kemonomimis and standard issue girls so most tags should work well. For more prompt tips please see the sample images or uploaded zip with training tags.
MISC
Trained on Pony SDXL at 1024 resolution with a dataset of 56 images upscaled from 512px.
All sample images are raw txt2img upscales, no inpainting or helper embeddings used, e.g - your outputs should look better with more than minimum effort.
The training was done on a small subset of the artists 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.