models/CAT - Citron Styles - Realistic Anime

CAT - Citron Styles - Realistic Anime

|
8/2/2025
|
5:20:01 AM
| Discussion|
0
Dark black tower known as Saurons Tower with a huge glowing red eye at the top, surrounded by a volcanic mountain range with flowing molten lava and cratered deadlands beneath a fiery red sky.
Close-up of a small alien monster in fetal position floating inside a stasis tank with soft shadows and a simple background.
Portrait of a mature woman with brown hair in a wide ponytail, laughing joyfully against a clear blue sky with a visible contrail, wearing a colorful floral print school swimsuit.
Silhouette of a girl with long hair wearing a school uniform, standing on a stone pathway surrounded by nature, backlit by bright dappled sunlight with bokeh effects.

Recommended Prompts

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

Recommended Negative Prompts

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

Recommended Parameters

samplers

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

steps

30

cfg

7

clip skip

2

resolution

832x1216, 832x1248

Version Highlights

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"

Creator Sponsors

Previous
Vibrantly Sharp style - Vibrantly Dark style v.4
Next
Grunge typography - v1.0

Model Details

Model type

LORA

Base model

Pony

Model version

Realistic Anime

Model hash

8b5dc12fc3

Trained words

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

Discussion

Please log in to leave a comment.