Readme
This model doesn't have a readme.
Kohya Training for XL models (Updated 1 year, 8 months ago)
pip install replicate
REPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
import replicate
Run alexgenovese/train-sdxl-kohya using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"alexgenovese/train-sdxl-kohya:a0b4df0a15173f25b6d55072a3ba4ea21b332c774c13bde0a0dcf18a4e20c980",
input={
"seed": 98796,
"unet_lr": 1,
"clip_skip": 1,
"batch_size": 1,
"resolution": "1024",
"keep_tokens": 0,
"network_dim": 32,
"output_name": "new_model_name",
"lr_scheduler": "cosine",
"noise_offset": 0,
"learning_rate": 4,
"network_alpha": 16,
"save_model_as": "safetensors",
"network_module": "networks.lora",
"optimizer_type": "Lion",
"lr_warmup_steps": 0,
"max_bucket_reso": 1024,
"min_bucket_reso": 256,
"text_encoder_lr": 1,
"train_unet_only": False,
"max_train_epoches": 20,
"save_every_n_epochs": 5,
"lr_scheduler_num_cycles": 1,
"train_text_encoder_only": False,
"pretrained_model_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
"persistent_data_loader_workers": True
}
)
print(output)
To learn more, take a look at the guide on getting started with Python.
No output yet! Press "Submit" to start a prediction.
This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.
This model doesn't have a readme.