Type | |
Stats | 1,636 |
Reviews | (274) |
Published | Apr 19, 2023 |
Base Model | |
Training | Steps: 25 Epochs: 15 |
Trigger Words | wearing flowers dress |
Hash | AutoV2 DF1820AD58 |
Get early access to build and test build, be able to try all epochs and test them by yourself on Patreon or contact me for support on Discord
Training settings:
35 images, 25 steps, 15 epochs, you find many epochs (with test images using plot xy script) on my Patreon while supporting me.
Recommended settings:
Make sure you are aware on the usage instructions of LORA
Sampler: DPM++ SDE Karras (Recommended for best quality, you may try other samplers)
CFG Scale : 5 to 9
LORA weight for txt2img: reccomended 0.2-0.7
Keys: wearing flowers dress, wearing colorful dress
Adviced Image Size: 512x768
This model is kinda hard to use, it's very important to start your prompt with something like "1 woman wearing flowers dress", don't place the keyword at the end of the prompt or you might not get what you want.
Also, i've tryied without my model and this keyword, many times it works even without the model, but the result is not the same. to give you a few examples, i made some xyz plot to show the same prompt with different weights on my model, you can find them in the images list.
You just need to practice and experience this model on your own, if you find a good prompt or you have any good advice i invite you to post and comment to give other people the chance to use it in the right way.
If you'd like to support my efforts and have access to early and bleeding edge builds, please think about joining my Patreon: https://www.patreon.com/betterCuteAsians