Aesthetic Quality Modifiers - Masterpiece
Training data is a subset of all my manually rated datasets with the quality/aesthetic modifiers, including only the masterpiece tagged images.
ℹ️ LoRA work best when applied to the base models on which they are trained. Please read the About This Version on the appropriate base models, trigger usage, and workflow/training information.
Recommended prompt structure:
Positive prompt (quality tags at the start of prompt):
masterpiece, best quality, very aesthetic, {{tags}}, {{natural language}}Description
Trained on Anima Base 1
Same dataset as v5.0 with a mix of natural language and tag captions.
386 images, all masterpiece tagged images trained in Kirazuri (Anima) model version 2 dataset.
Partitioned and trained at multi-res 1024, 1280, 1536
Trained for 1,413 Steps, 3 Epochs.
Training config:
# trained using diffusion-pipe commit b0aa4f1e03169f3280c8518d37570a448420f8be
# NCCL_P2P_DISABLE="1" NCCL_IB_DISABLE="1" NCCL_CUMEM_ENABLE="0" deepspeed --num_gpus=1 train.py --deepspeed --config anima-lora.toml --i_know_what_i_am_doing
output_dir = '/mnt/d/anima/training_output/anima-base-1-masterpiece-v51'
dataset = 'dataset-anima-masterpiece.toml'
# training settings
epochs = 3
# Per-resolution batch sizes
micro_batch_size_per_gpu = [[1024, 32], [1280, 24], [1536, 16]]
pipeline_stages = 1
gradient_accumulation_steps = 1
gradient_clipping = 1
warmup_steps = 30
lr_scheduler = 'cosine'
# misc settings
save_every_n_epochs = 1
activation_checkpointing = true
#reentrant_activation_checkpointing = true
partition_method = 'parameters'
save_dtype = 'bfloat16'
caching_batch_size = 1
map_num_proc = 8
steps_per_print = 1
compile = true
[model]
type = 'anima'
transformer_path = '/mnt/c/workspace/models/diffusion_models/anima-base-v1.0.safetensors'
vae_path = '/mnt/c/workspace/models/vae/qwen_image_vae.safetensors'
llm_path = '/mnt/c/workspace/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 = 4e-5
betas = [0.9, 0.99]
weight_decay = 0.01
eps = 1e-8resolutions = [1024, 1280, 1536]
enable_ar_bucket = true
min_ar = 0.5
max_ar = 2.0
num_ar_buckets = 9
# Totals
# 386 images
# 16 repeats from captions.json
# 153 images
[[directory]]
path = '/mnt/d/training_data/0_masterpieces_kirazuri/1536x1536'
resolutions = [1024, 1280, 1536]
# 44 images
[[directory]]
path = '/mnt/d/training_data/0_masterpieces_kirazuri/1280x1280'
resolutions = [1024, 1280]
# 189 images
[[directory]]
path = '/mnt/d/training_data/0_masterpieces_kirazuri/1024x1024'
resolutions = [1024]