This model was fine-tuned using 4-bit QLoRa, following the instructions in https://huggingface.co/blog/lora. The training script and training log are included.

I used a Amazon EC2 g4dn.xlarge instance (1xT4 GPU), with the Deep Learning AMI for PyTorch. Training time was about 6 hours. On-demand price is about $3, which can easily be reduced to about $1 with EC2 Spot Instances.

LoRA text2image fine-tuning - juliensimon/stable-diffusion-v1-5-pokemon-lora

These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were fine-tuned on the lambdalabs/pokemon-blip-captions dataset. You can find some example images in the following.