## Model description
This model trained based on Stable Diffusion 1.5 model to create isometric cities, venues, etc more precisely.

## Intended uses & limitations
Do not use for commercial purposes.

## Training procedure
Trained on a WSL2 Ubuntu machine with DreamBooth.

### Training hyperparameters
The following hyperparameters were used during training:
  --with_prior_preservation --prior_loss_weight=1.0 \
  --instance_prompt="an illustration of an isometric city, digital art, highly detailed" \
  --class_prompt="isometric city" \
  --resolution=512 \
  --train_batch_size=1 \
  --mixed_precision="fp16" \
  --gradient_accumulation_steps=1 --gradient_checkpointing \
  --use_8bit_adam \
  --learning_rate=5e-6 \
  --lr_scheduler="constant" \
  --lr_warmup_steps=0 \
  --num_class_images=50 \
  --max_train_steps=1500

### Training results

![00021.jpg](https://s3.amazonaws.com/moonup/production/uploads/1667942059199-6305d083df993a789e61126d.jpeg)
![00022.jpg](https://s3.amazonaws.com/moonup/production/uploads/1667942060129-6305d083df993a789e61126d.jpeg)
![00023.jpg](https://s3.amazonaws.com/moonup/production/uploads/1667942059810-6305d083df993a789e61126d.jpeg)
![00024.jpg](https://s3.amazonaws.com/moonup/production/uploads/1667942060647-6305d083df993a789e61126d.jpeg)
![00025.jpg](https://s3.amazonaws.com/moonup/production/uploads/1667942059778-6305d083df993a789e61126d.jpeg)