Trained on Anima Preview 3 Base

Training config:

# trained using diffusion-pipe commit 6e95020cad0b3cd7dcb93ce42b358669051bf6d2

output_dir = '/mnt/d/anima/training_output/nijigen'

dataset = 'dataset-anima.toml'

# training settings
epochs = 1000
# Per-resolution batch sizes
# micro_batch_size_per_gpu = [[512, 32], [1024, 32], [1536, 16]]
micro_batch_size_per_gpu = 16
pipeline_stages = 1
gradient_accumulation_steps = 1
gradient_clipping = 1
warmup_steps = 100

# misc settings
save_every_n_epochs = 1
#save_every_n_steps = 1000
#save_every_n_examples = 4096000
#checkpoint_every_n_epochs = 1
#checkpoint_every_n_minutes = 120
activation_checkpointing = true
#reentrant_activation_checkpointing = true

partition_method = 'parameters'
# partition_method = 'manual'
# partition_split = [10]

save_dtype = 'bfloat16'
caching_batch_size = 1
map_num_proc = 8
steps_per_print = 1
compile = true

[model]
type = 'anima'
transformer_path = '/ComfyUI/models/diffusion_models/anima-preview3-base.safetensors'
vae_path = '/ComfyUI/models/vae/qwen_image_vae.safetensors'
llm_path = '/ComfyUI_windows_portable/ComfyUI/models/text_encoders/qwen_3_06b_base.safetensors'
dtype = 'bfloat16'
#cache_text_embeddings = false
llm_adapter_lr = 0
#timestep_sample_method = 'uniform'
#flux_shift = true
#multiscale_loss_weight = 0.5
sigmoid_scale = 1.3

[adapter]
type = 'lora'
rank = 32
dtype = 'bfloat16'

[optimizer]
type = 'adamw_optimi'
lr = 2e-5
betas = [0.9, 0.99]
weight_decay = 0.01
eps = 1e-8

resolutions = [512, 1024, 1536]

enable_ar_bucket = true
min_ar = 0.5
max_ar = 2.0
num_ar_buckets = 9

[[directory]]
path = '/mnt/d/training_data/images_niji_captions'
repeats = 8