Type | |
Stats | 194 2,374 |
Reviews | (61) |
Published | May 8, 2024 |
Base Model | |
Training | Steps: 2,090 |
Usage Tips | Clip Skip: 2 Strength: 1 |
Trigger Words | TheOniDBD, Dead By Daylight, oni, demon, humanoid, red mask, long white hair, grey body, male, muscular, barazoku |
Hash | AutoV2 A4E86030FB |
The Oni from Dead By Daylight. Killer grandpa samurai.
Pony XL version trained on Pony Diffusion V6 XL.
Recommended weight of the LORA itself is 1.0.
Images generated with Pony Real Magic, which is a Tensor.art-exclusive model. Restart best sampler.
main tags:
TheOniDBD, Dead By Daylight, oni, demon, humanoid, red mask, long white hair, grey body, male, muscular, barazoku
armor:
armor, full armor
P.S. be more mindful with the way you prompt with Pony XL models, they break in ways that was never possible in 1.5 models before. Anything from a Clip Skip that isn't 2, one too many weighted tags, or a few tags in the wrong place might end up generating broken pictures, unless that's your thing then congratulations.
{
"ss_output_name": "TheOniDBD",
"ss_sd_model_name": "stablediffusionapi/pony-diffusion-v6-xl",
"ss_network_module": "networks.lora",
"ss_optimizer": "prodigyopt.prodigy.Prodigy(decouple=True,weight_decay=0.05,betas=[0.9, 0.99],d_coef=1,use_bias_correction=True)",
"ss_lr_scheduler": "constant",
"ss_clip_skip": "None",
"ss_network_dim": 8,
"ss_network_alpha": 4,
"ss_epoch": 18,
"ss_num_epochs": 30,
"ss_steps": 2090,
"ss_max_train_steps": 3300,
"ss_learning_rate": 0.75,
"ss_text_encoder_lr": 0.75,
"ss_unet_lr": 0.75,
"ss_noise_offset": 0.0357,
"ss_adaptive_noise_scale": "None",
"ss_min_snr_gamma": 5,
"ss_training_started_at": "2024-05-05T19:08:30.398Z",
"ss_training_finished_at": "2024-05-05T22:04:50.871Z",
"training_time": "2h 56m 20s",
"sshs_model_hash": "6032ca925377333093a3634b9b729c623f1a9dfcf6c9f22ac4f922522fc97802"
}