Follow me on X/Twitter for exclusive content: https://x.com/Citron_Legacy 😁
Source: https://x.com/elonmusk/status/1055653541317042177
This is a Lora trained on 1 image as a test for my new ANIMA Lora Trainer on Google Colab: https://github.com/citronlegacy/citron-colab-anima-lora-trainer
Obviously 1 image and Google Colab free tier can't make a high quality lora but I wanted to show what we can make with barely anything.
This Lora was made with only 1 image and 400 steps so its a pretty weak lora but it only took about 30 min to make. I need to experiment more with this trainer to optimize training settings.
Link to Dataset: https://github.com/citronlegacy/citron-colab-anima-lora-trainer/tree/main/example_dataset/ElonCatGirl_ANIMA
Training settings:
Steps: 400
Images: 1
Repeats: 40
Epochs: 10
If you make a Lora using my trainer please let me know! I'd love to see what you make!

