pip3 install nemo-automodel

docker pull nvcr.io/nvidia/nemo-automodel:26.02.00
docker run --gpus all -it --rm --shm-size=8g nvcr.io/nvidia/nemo-automodel:26.02.00

/cache/
├── 512x512/                      # Resolution bucket
│   ├── <hash1>.meta              # VAE latents + text embeddings
│   ├── <hash2>.meta
│   └── ...
├── 832x480/                      # Another resolution bucket
│   └── ...
├── metadata.json                 # Global config (processor, model, total items)
└── metadata_shard_0000.json      # Per-sample metadata (paths, resolutions, captions)

torchrun --nproc-per-node=8 examples/diffusion/finetune/finetune.py \
  -c examples/diffusion/finetune/wan2_1_t2v_flow.yaml \
  --optim.learning_rate 1e-5 \
  --step_scheduler.num_epochs 50

seed: 42

# ── Experiment tracking (optional) ──────────────────────────────────────────
# Weights & Biases integration for logging metrics, losses, and learning rates.
# Set mode: "disabled" to turn off.
wandb:
  project: wan-t2v-flow-matching
  mode: online
  name: wan2_1_t2v_fm

# ── Model ───────────────────────────────────────────────────────────────────
# pretrained_model_name_or_path: any Hugging Face model ID or local path.
# mode: "finetune" loads pretrained weights; "pretrain" trains from scratch.
model:
  pretrained_model_name_or_path: Wan-AI/Wan2.1-T2V-1.3B-Diffusers
  mode: finetune

# ── Training schedule ───────────────────────────────────────────────────────
# global_batch_size: effective batch across all GPUs.
# Gradient accumulation is computed automatically: global / (local × num_gpus).
step_scheduler:
  global_batch_size: 8
  local_batch_size: 1
  ckpt_every_steps: 1000     # Save a checkpoint every N steps
  num_epochs: 100
  log_every: 2               # Log metrics every N steps

# ── Data ────────────────────────────────────────────────────────────────────
# _target_: the dataloader factory function.
#   Use build_video_multiresolution_dataloader for video models (Wan, HunyuanVideo).
#   Use build_text_to_image_multiresolution_dataloader for image models (FLUX).
# model_type: "wan" or "hunyuan" (selects the correct latent format).
# base_resolution: target resolution for multiresolution bucketing.
data:
  dataloader:
    _target_: nemo_automodel.components.datasets.diffusion.build_video_multiresolution_dataloader
    cache_dir: PATH_TO_YOUR_DATA
    model_type: wan
    base_resolution: [512, 512]
    dynamic_batch_size: false  # When true, adjusts batch per bucket to maintain constant memory
    shuffle: true
    drop_last: false
    num_workers: 0

# ── Optimizer ───────────────────────────────────────────────────────────────
# learning_rate: 5e-6 is a good starting point for fine-tuning.
# Adjust weight_decay and betas for your dataset.
optim:
  learning_rate: 5e-6
  optimizer:
    weight_decay: 0.01
    betas: [0.9, 0.999]

# ── Learning rate scheduler ─────────────────────────────────────────────────
# Supports cosine, linear, and constant schedules.
lr_scheduler:
  lr_decay_style: cosine
  lr_warmup_steps: 0
  min_lr: 1e-6

# ── Flow matching ───────────────────────────────────────────────────────────
# adapter_type: model-specific adapter — must match the model:
#   "simple" for Wan 2.1, "flux" for FLUX.1-dev, "hunyuan" for HunyuanVideo.
# timestep_sampling: "uniform" for Wan, "logit_normal" for FLUX and HunyuanVideo.
# flow_shift: shifts the flow schedule (model-dependent).
# i2v_prob: probability of image-to-video conditioning during training (video models).
flow_matching:
  adapter_type: "simple"
  adapter_kwargs: {}
  timestep_sampling: "uniform"
  logit_mean: 0.0
  logit_std: 1.0
  flow_shift: 3.0
  num_train_timesteps: 1000
  i2v_prob: 0.3
  use_loss_weighting: true

# ── FSDP2 distributed training ──────────────────────────────────────────────
# dp_size: number of GPUs for data parallelism (typically = total GPUs on node).
# tp_size, cp_size, pp_size: tensor, context, and pipeline parallelism.
#   For most fine-tuning, dp_size is all you need; leave others at 1.
fsdp:
  tp_size: 1
  cp_size: 1
  pp_size: 1
  dp_replicate_size: 1
  dp_size: 8

# ── Checkpointing ──────────────────────────────────────────────────────────
# checkpoint_dir: where to save checkpoints (use a persistent path with Docker).
# restore_from: path to resume training from a previous checkpoint.
checkpoint:
  enabled: true
  checkpoint_dir: PATH_TO_YOUR_CKPT_DIR
  model_save_format: torch_save
  save_consolidated: false
  restore_from: null