Dark towering fortress with a huge glowing red eye atop, surrounded by a volcanic mountain range and molten lava flows in a desolate deadlands setting
Close up of an alien creature in fetal position floating inside a stasis tank, depicted with soft shadows and a simple background in realistic anime style.
Portrait of a mature woman with brown hair tied in a wide ponytail, laughing joyfully against a simple light blue sky background with a white contrail above her. She wears a colorful floral print school swimsuit with a white border.
Silhouette of a girl in a school uniform standing on a stone path with strong backlighting and dappled sunlight filtering through surrounding nature.

Prompt Consigliati

score_9, score_8_up, score_8, (ultra realistic, 32k, masterpiece:1.2), medium breasts, (high detailed skin:1.1), ( high quality:1.1), (curvy), cute, eyelashes, blush, looking at viewer

Prompt Negativi Consigliati

score_6, score_5, score_4, busty, ugly face, mutated hands, low res, blurry face, black and white

Parametri Consigliati

samplers

Euler a, DPM++ 2M Karras, DPM++ 2M

steps

30

cfg

7

clip skip

2

resolution

832x1216, 832x1248

Punti Salienti della Versione

I added some suggested prompts in the Trigger but you don't actually need them.

--

You can find some of my training data on several of my Lora posts like this one https://civitai.com/images/8452326

--

Shout out to iJWiTGS8 for helping me learn how to create this style!

--

Trained on: 210 images

Steps: 840

Total Time: 2:36:04

--

[network_arguments]

unet_lr = 0.75

text_encoder_lr = 0.75

network_dim = 32

network_alpha = 32

network_module = "networks.lora"

network_train_unet_only = false

[optimizer_arguments]

learning_rate = 0.75

lr_scheduler = "cosine_with_restarts"

lr_scheduler_num_cycles = 3

lr_warmup_steps = 42

optimizer_type = "Prodigy"

optimizer_args = [ "weight_decay=0.1", "betas=[0.9,0.99]",]

[training_arguments]

pretrained_model_name_or_path = "stablediffusionapi/pony-diffusion-v6-xl"

vae = "stabilityai/sdxl-vae"

max_train_epochs = 10

train_batch_size = 5

seed = 42

max_token_length = 225

xformers = false

sdpa = true

min_snr_gamma = 8.0

lowram = true

no_half_vae = true

gradient_checkpointing = true

gradient_accumulation_steps = 1

max_data_loader_n_workers = 8

persistent_data_loader_workers = true

mixed_precision = "fp16"

full_bf16 = false

cache_latents = true

cache_latents_to_disk = true

cache_text_encoder_outputs = false

min_timestep = 0

max_timestep = 1000

prior_loss_weight = 1.0

[saving_arguments]

save_precision = "fp16"

save_model_as = "safetensors"

save_every_n_epochs = 1

save_last_n_epochs = 10

output_name = "RealisticAnime"

output_dir = "/content/drive/MyDrive/lora_training/output/RealisticAnime"

log_prefix = "RealisticAnime"

logging_dir = "/content/drive/MyDrive/lora_training/log"

Sponsor del Creatore

Help fuel my passion! Even $1 makes a difference. https://ko-fi.com/citronlegacy

New Style: Kawaii Mirai (Cute Future)

In the grim darkness of the far future... In the cheerful light of the far future, there is only Pastel! CatHammer40K! The Empurror Puurtects! 🐈😜

Precedente
NTDMIX - v1.5
Successivo
Dark Side of Light - Rembrandt Lighting

Dettagli del Modello

Tipo di modello

LORA

Modello base

Pony

Versione del modello

Realistic Anime

Hash del modello

8b5dc12fc3

Parole addestrate

(ultra realistic, 32k, masterpiece:1.2), (high detailed skin:1.1), (high quality:1.1),
bokeh, luminescent background,

Creatore

Discussione

Per favore log in per lasciare un commento.

Immagini di CAT - Citron Styles - Realistic Anime

Immagini con anime

Immagini con flat color

Immagini con sketch

Immagini con style

Immagini con toon