Type | |
Stats | 201 178 |
Reviews | (15) |
Published | Feb 20, 2024 |
Base Model | |
Training | Steps: 20,000 Epochs: 2 |
Usage Tips | Clip Skip: 1 Strength: 1 |
Hash | AutoV2 55C324DF5D |
What it is
This is a LORA that use in text2img to get better asian countries flags
It's best at weights under <1.2 with accompanying keywords.
The data set is a collection free pics
If you like my work please support me on KoFi and Patreon
Dataset available on my patreon
Installation:
Download the file
Place it in models\Lora folder (webui)
Usage:
You can also add it to the prompt by clicking "lora" tab in automatic1111:
You can also type it into the prompt, but it will not work if you make a single typo.
ex <lora:asiaflags01:1>
The SD1.5 model requires the SD1.5 base
Adjust the weights. 0.5 - 1.2
This version of the model is not perfect, as it can generate images for flags accurately but does not accept many changes in the images, affecting the image quality, especially if you try to add other elements to the images besides the flag. It also produces distorted faces. I will try to train a better version in the future.