link to Lora: https://tensor.art/models/806808906744706431/Podoru-Meme-LoRa-e10
I fetched my training images from: https://apps.apple.com/us/app/sankaku-anime-ai-girlfriend/
Pic collage shown here was created using https://gandr.io/
Then I used the built in Tensor Art caption tool to set the prompts
Example:
"padoru 1girl solo long hair smile open mouth simple background hair ornament long sleeves hat white background holding tail full body yellow eyes :d red hair pointy ears hairclip chibi fur trim capelet fangs transparent background blush stickers monster girl slit pupils christmas red headwear santa hat santa costume meme scales sack lamia holding sack miia \(monster musume\)"
Training settings:
base model: NovaXL (as shown as base model in LoRa)
Unet learning rate: 0.0001
Repeat : 20 , Epochs 10
Constant learning rate
Network dim: 64 , Alpha: 32
Loss chart is absurdly low:
And here are some examples of the output from the NovaXL illustrious model:
Very cute!
Thats all for this training guide. Merry Christmas!
/Adcom
