nodes/aigc-apps-VideoX-Fun
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update one-forcing and causal forcing params

Browse Source
This commit is contained in:
bubbliiiing
2026-10-30 16:33:15 +08:00
parent a15b293128
commit f00a7d480e
17 changed files with 4866 additions and 86 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/wan2.1_self_forcing/README_TRAIN_DISTILL.md
+62 -24
View File
@@ -179,6 +179,7 @@ The difference between DeepSpeed-Zero-2 and FSDP lies in whether to shard model
```bash
export MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-1.3B/"
export REAL_SCORE_MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-14B"
export DATASET_NAME="datasets/X-Fun-Videos-Demo/"
export DATASET_META_NAME="datasets/X-Fun-Videos-Demo/metadata_add_width_height.json"
# NCCL_IB_DISABLE=1 and NCCL_P2P_DISABLE=1 are used in multi nodes without RDMA.
@@ -189,6 +190,7 @@ NCCL_DEBUG=INFO
accelerate launch --use_deepspeed --deepspeed_config_file config/zero_stage2_config.json --deepspeed_multinode_launcher standard scripts/wan2.1_self_forcing/train_distill.py \
--config_path="config/wan2.1/wan_civitai.yaml" \
--pretrained_model_name_or_path=$MODEL_NAME \
--real_score_model_name_or_path=$REAL_SCORE_MODEL_NAME \
--train_data_dir=$DATASET_NAME \
--train_data_meta=$DATASET_META_NAME \
--image_sample_size=640 \
@@ -204,21 +206,26 @@ accelerate launch --use_deepspeed --deepspeed_config_file config/zero_stage2_con
--num_train_epochs=100 \
--checkpointing_steps=50 \
--learning_rate=2e-06 \
--learning_rate_critic=2e-06 \
--learning_rate_critic=4.0e-07 \
--lr_scheduler="constant_with_warmup" \
--lr_warmup_steps=100 \
--seed=42 \
--output_dir="output_dir_wan2.1_self_forcing_distill" \
--gradient_checkpointing \
--mixed_precision="bf16" \
--adam_weight_decay=3e-2 \
--fsdp_reduce_fp32 \
--adam_weight_decay=0.0 \
--adam_beta1=0.0 \
--adam_beta2=0.999 \
--adam_epsilon=1e-10 \
--vae_mini_batch=1 \
--max_grad_norm=0.05 \
--max_grad_norm=10.0 \
--random_hw_adapt \
--training_with_video_token_length \
--enable_bucket \
--uniform_sampling \
--denoising_step_indices_list 1000 750 500 250 \
--real_guidance_scale=4.0 \
--score_timestep_clamp \
--use_kv_cache_training \
--num_frame_per_block=3 \
--train_mode="normal" \
@@ -247,17 +254,19 @@ accelerate launch --use_deepspeed --deepspeed_config_file config/zero_stage2_con
| `--num_train_epochs` | Number of training epochs | 100 |
| `--checkpointing_steps` | Save checkpoint every N steps | 50 |
| `--learning_rate` | Initial learning rate (generator) | 2e-06 |
| `--learning_rate_critic` | Initial learning rate (critic) | 2e-06 |
| `--learning_rate_critic` | Initial learning rate (critic) | 4.0e-07 |
| `--lr_scheduler` | Learning rate scheduler | `constant_with_warmup` |
| `--lr_warmup_steps` | Learning rate warmup steps | 100 |
| `--seed` | Random seed | 42 |
| `--output_dir` | Output directory | `output_dir_wan2.1_self_forcing_distill` |
| `--gradient_checkpointing` | Enable gradient checkpointing | - |
| `--mixed_precision` | Mixed precision: `fp16/bf16` | `bf16` |
| `--adam_weight_decay` | AdamW weight decay | 3e-2 |
| `--adam_weight_decay` | AdamW weight decay | 0.0 |
| `--adam_beta1` | AdamW beta1 | 0.0 |
| `--adam_beta2` | AdamW beta2 | 0.999 |
| `--adam_epsilon` | AdamW epsilon | 1e-10 |
| `--vae_mini_batch` | VAE encoding mini-batch size | 1 |
| `--max_grad_norm` | Gradient clipping threshold | 0.05 |
| `--max_grad_norm` | Gradient clipping threshold | 10.0 |
| `--fsdp_reduce_fp32` | Optional: reduce gradients in fp32 under FSDP mixed precision (default reduces in bf16) | - |
| `--enable_bucket` | Enable bucket training, no cropping, group by resolution | - |
| `--random_hw_adapt` | Auto-scale images/videos to random sizes in `[min_size, max_size]` range | - |
@@ -277,7 +286,7 @@ accelerate launch --use_deepspeed --deepspeed_config_file config/zero_stage2_con
|-----|------|-------|
| `--denoising_step_indices_list` | Denoising step indices list (core distillation parameter) | `1000 750 500 250` |
| `--randomize_step_indices` | Randomize the denoising timestep indices during training | - |
| `--real_guidance_scale` | Real guidance scale for scoring | 6.0 |
| `--real_guidance_scale` | Real guidance scale for scoring | 4.0 |
| `--score_timestep_clamp` | Optional: clamp DMD/critic timesteps to `[0.02, 0.98] * num_train_timesteps` | - |
| `--fake_guidance_scale` | Fake guidance scale for scoring | 0.0 |
| `--gen_update_interval` | Generator update interval | 5 |
@@ -365,6 +374,7 @@ You can configure validation parameters to periodically generate test videos dur
```bash
export MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-1.3B/"
export REAL_SCORE_MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-14B"
export DATASET_NAME="datasets/X-Fun-Videos-Demo/"
export DATASET_META_NAME="datasets/X-Fun-Videos-Demo/metadata_add_width_height.json"
# NCCL_IB_DISABLE=1 and NCCL_P2P_DISABLE=1 are used in multi nodes without RDMA.
@@ -375,6 +385,7 @@ NCCL_DEBUG=INFO
accelerate launch --mixed_precision="bf16" --use_fsdp --fsdp_auto_wrap_policy TRANSFORMER_BASED_WRAP --fsdp_transformer_layer_cls_to_wrap=CasualWanAttentionBlock --fsdp_sharding_strategy "FULL_SHARD" --fsdp_state_dict_type=SHARDED_STATE_DICT --fsdp_backward_prefetch "BACKWARD_PRE" --fsdp_cpu_ram_efficient_loading False scripts/wan2.1_self_forcing/train_distill.py \
--config_path="config/wan2.1/wan_civitai.yaml" \
--pretrained_model_name_or_path=$MODEL_NAME \
--real_score_model_name_or_path=$REAL_SCORE_MODEL_NAME \
--train_data_dir=$DATASET_NAME \
--train_data_meta=$DATASET_META_NAME \
--image_sample_size=640 \
@@ -390,21 +401,26 @@ accelerate launch --mixed_precision="bf16" --use_fsdp --fsdp_auto_wrap_policy TR
--num_train_epochs=100 \
--checkpointing_steps=50 \
--learning_rate=2e-06 \
--learning_rate_critic=2e-06 \
--learning_rate_critic=4.0e-07 \
--lr_scheduler="constant_with_warmup" \
--lr_warmup_steps=100 \
--seed=42 \
--output_dir="output_dir_wan2.1_self_forcing_distill" \
--gradient_checkpointing \
--mixed_precision="bf16" \
--adam_weight_decay=3e-2 \
--fsdp_reduce_fp32 \
--adam_weight_decay=0.0 \
--adam_beta1=0.0 \
--adam_beta2=0.999 \
--adam_epsilon=1e-10 \
--vae_mini_batch=1 \
--max_grad_norm=0.05 \
--max_grad_norm=10.0 \
--random_hw_adapt \
--training_with_video_token_length \
--enable_bucket \
--uniform_sampling \
--denoising_step_indices_list 1000 750 500 250 \
--real_guidance_scale=4.0 \
--score_timestep_clamp \
--use_kv_cache_training \
--num_frame_per_block=3 \
--train_mode="normal" \
@@ -427,6 +443,7 @@ python scripts/zero_to_bf16.py output_dir/checkpoint-{our-num-steps} output_dir/
Training shell command is as follows:
```bash
export MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-1.3B/"
export REAL_SCORE_MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-14B"
export DATASET_NAME="datasets/X-Fun-Videos-Demo/"
export DATASET_META_NAME="datasets/X-Fun-Videos-Demo/metadata_add_width_height.json"
# NCCL_IB_DISABLE=1 and NCCL_P2P_DISABLE=1 are used in multi nodes without RDMA.
@@ -437,6 +454,7 @@ NCCL_DEBUG=INFO
accelerate launch --zero_stage 3 --zero3_save_16bit_model true --zero3_init_flag true --use_deepspeed --deepspeed_config_file config/zero_stage3_config.json --deepspeed_multinode_launcher standard scripts/wan2.1_self_forcing/train_distill.py \
--config_path="config/wan2.1/wan_civitai.yaml" \
--pretrained_model_name_or_path=$MODEL_NAME \
--real_score_model_name_or_path=$REAL_SCORE_MODEL_NAME \
--train_data_dir=$DATASET_NAME \
--train_data_meta=$DATASET_META_NAME \
--image_sample_size=640 \
@@ -452,21 +470,26 @@ accelerate launch --zero_stage 3 --zero3_save_16bit_model true --zero3_init_flag
--num_train_epochs=100 \
--checkpointing_steps=50 \
--learning_rate=2e-06 \
--learning_rate_critic=2e-06 \
--learning_rate_critic=4.0e-07 \
--lr_scheduler="constant_with_warmup" \
--lr_warmup_steps=100 \
--seed=42 \
--output_dir="output_dir_wan2.1_self_forcing_distill" \
--gradient_checkpointing \
--mixed_precision="bf16" \
--adam_weight_decay=3e-2 \
--fsdp_reduce_fp32 \
--adam_weight_decay=0.0 \
--adam_beta1=0.0 \
--adam_beta2=0.999 \
--adam_epsilon=1e-10 \
--vae_mini_batch=1 \
--max_grad_norm=0.05 \
--max_grad_norm=10.0 \
--random_hw_adapt \
--training_with_video_token_length \
--enable_bucket \
--uniform_sampling \
--denoising_step_indices_list 1000 750 500 250 \
--real_guidance_scale=4.0 \
--score_timestep_clamp \
--use_kv_cache_training \
--num_frame_per_block=3 \
--train_mode="normal" \
@@ -481,6 +504,7 @@ accelerate launch --zero_stage 3 --zero3_save_16bit_model true --zero3_init_flag
```bash
export MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-1.3B/"
export REAL_SCORE_MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-14B"
export DATASET_NAME="datasets/X-Fun-Videos-Demo/"
export DATASET_META_NAME="datasets/X-Fun-Videos-Demo/metadata_add_width_height.json"
# NCCL_IB_DISABLE=1 and NCCL_P2P_DISABLE=1 are used in multi nodes without RDMA.
@@ -491,6 +515,7 @@ NCCL_DEBUG=INFO
accelerate launch --mixed_precision="bf16" scripts/wan2.1_self_forcing/train_distill.py \
--config_path="config/wan2.1/wan_civitai.yaml" \
--pretrained_model_name_or_path=$MODEL_NAME \
--real_score_model_name_or_path=$REAL_SCORE_MODEL_NAME \
--train_data_dir=$DATASET_NAME \
--train_data_meta=$DATASET_META_NAME \
--image_sample_size=640 \
@@ -506,21 +531,26 @@ accelerate launch --mixed_precision="bf16" scripts/wan2.1_self_forcing/train_dis
--num_train_epochs=100 \
--checkpointing_steps=50 \
--learning_rate=2e-06 \
--learning_rate_critic=2e-06 \
--learning_rate_critic=4.0e-07 \
--lr_scheduler="constant_with_warmup" \
--lr_warmup_steps=100 \
--seed=42 \
--output_dir="output_dir_wan2.1_self_forcing_distill" \
--gradient_checkpointing \
--mixed_precision="bf16" \
--adam_weight_decay=3e-2 \
--fsdp_reduce_fp32 \
--adam_weight_decay=0.0 \
--adam_beta1=0.0 \
--adam_beta2=0.999 \
--adam_epsilon=1e-10 \
--vae_mini_batch=1 \
--max_grad_norm=0.05 \
--max_grad_norm=10.0 \
--random_hw_adapt \
--training_with_video_token_length \
--enable_bucket \
--uniform_sampling \
--denoising_step_indices_list 1000 750 500 250 \
--real_guidance_scale=4.0 \
--score_timestep_clamp \
--use_kv_cache_training \
--num_frame_per_block=3 \
--train_mode="normal" \
@@ -540,6 +570,7 @@ Assuming 2 machines, each with 8 GPUs:
**Machine 0 (Master)**:
```bash
export MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-1.3B/"
export REAL_SCORE_MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-14B"
export DATASET_NAME="datasets/X-Fun-Videos-Demo/"
export DATASET_META_NAME="datasets/X-Fun-Videos-Demo/metadata_add_width_height.json"
export MASTER_ADDR="192.168.1.100" # Master machine IP
@@ -555,6 +586,7 @@ NCCL_DEBUG=INFO
accelerate launch --mixed_precision="bf16" --main_process_ip=$MASTER_ADDR --main_process_port=$MASTER_PORT --num_machines=$WORLD_SIZE --num_processes=$NUM_PROCESS --machine_rank=$RANK --use_deepspeed --deepspeed_config_file config/zero_stage2_config.json --deepspeed_multinode_launcher standard scripts/wan2.1_self_forcing/train_distill.py \
--config_path="config/wan2.1/wan_civitai.yaml" \
--pretrained_model_name_or_path=$MODEL_NAME \
--real_score_model_name_or_path=$REAL_SCORE_MODEL_NAME \
--train_data_dir=$DATASET_NAME \
--train_data_meta=$DATASET_META_NAME \
--image_sample_size=640 \
@@ -570,21 +602,26 @@ accelerate launch --mixed_precision="bf16" --main_process_ip=$MASTER_ADDR --main
--num_train_epochs=100 \
--checkpointing_steps=50 \
--learning_rate=2e-06 \
--learning_rate_critic=2e-06 \
--learning_rate_critic=4.0e-07 \
--lr_scheduler="constant_with_warmup" \
--lr_warmup_steps=100 \
--seed=42 \
--output_dir="output_dir_wan2.1_self_forcing_distill" \
--gradient_checkpointing \
--mixed_precision="bf16" \
--adam_weight_decay=3e-2 \
--fsdp_reduce_fp32 \
--adam_weight_decay=0.0 \
--adam_beta1=0.0 \
--adam_beta2=0.999 \
--adam_epsilon=1e-10 \
--vae_mini_batch=1 \
--max_grad_norm=0.05 \
--max_grad_norm=10.0 \
--random_hw_adapt \
--training_with_video_token_length \
--enable_bucket \
--uniform_sampling \
--denoising_step_indices_list 1000 750 500 250 \
--real_guidance_scale=4.0 \
--score_timestep_clamp \
--use_kv_cache_training \
--num_frame_per_block=3 \
--train_mode="normal" \
@@ -596,6 +633,7 @@ accelerate launch --mixed_precision="bf16" --main_process_ip=$MASTER_ADDR --main
**Machine 1 (Worker)**:
```bash
export MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-1.3B/"
export REAL_SCORE_MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-14B"
export DATASET_NAME="datasets/X-Fun-Videos-Demo/"
export DATASET_META_NAME="datasets/X-Fun-Videos-Demo/metadata_add_width_height.json"
export MASTER_ADDR="192.168.1.100" # Same as Master
scripts/wan2.1_self_forcing/README_TRAIN_DISTILL_zh-CN.md
+62 -24
View File
@@ -180,6 +180,7 @@ hf download gdhe17/Self-Forcing --local-dir models/Diffusion_Transformer/Self-Fo
```bash
export MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-1.3B/"
export REAL_SCORE_MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-14B"
export DATASET_NAME="datasets/X-Fun-Videos-Demo/"
export DATASET_META_NAME="datasets/X-Fun-Videos-Demo/metadata_add_width_height.json"
# NCCL_IB_DISABLE=1 and NCCL_P2P_DISABLE=1 are used in multi nodes without RDMA.
@@ -190,6 +191,7 @@ NCCL_DEBUG=INFO
accelerate launch --use_deepspeed --deepspeed_config_file config/zero_stage2_config.json --deepspeed_multinode_launcher standard scripts/wan2.1_self_forcing/train_distill.py \
--config_path="config/wan2.1/wan_civitai.yaml" \
--pretrained_model_name_or_path=$MODEL_NAME \
--real_score_model_name_or_path=$REAL_SCORE_MODEL_NAME \
--train_data_dir=$DATASET_NAME \
--train_data_meta=$DATASET_META_NAME \
--image_sample_size=640 \
@@ -205,21 +207,26 @@ accelerate launch --use_deepspeed --deepspeed_config_file config/zero_stage2_con
--num_train_epochs=100 \
--checkpointing_steps=50 \
--learning_rate=2e-06 \
--learning_rate_critic=2e-06 \
--learning_rate_critic=4.0e-07 \
--lr_scheduler="constant_with_warmup" \
--lr_warmup_steps=100 \
--seed=42 \
--output_dir="output_dir_wan2.1_self_forcing_distill" \
--gradient_checkpointing \
--mixed_precision="bf16" \
--adam_weight_decay=3e-2 \
--fsdp_reduce_fp32 \
--adam_weight_decay=0.0 \
--adam_beta1=0.0 \
--adam_beta2=0.999 \
--adam_epsilon=1e-10 \
--vae_mini_batch=1 \
--max_grad_norm=0.05 \
--max_grad_norm=10.0 \
--random_hw_adapt \
--training_with_video_token_length \
--enable_bucket \
--uniform_sampling \
--denoising_step_indices_list 1000 750 500 250 \
--real_guidance_scale=4.0 \
--score_timestep_clamp \
--use_kv_cache_training \
--num_frame_per_block=3 \
--train_mode="normal" \
@@ -248,17 +255,19 @@ accelerate launch --use_deepspeed --deepspeed_config_file config/zero_stage2_con
| `--num_train_epochs` | 训练 epoch 数 | 100 |
| `--checkpointing_steps` | 每 N 步保存 checkpoint | 50 |
| `--learning_rate` | 初始学习率（生成器） | 2e-06 |
| `--learning_rate_critic` | 初始学习率（判别器） | 2e-06 |
| `--learning_rate_critic` | 初始学习率（判别器） | 4.0e-07 |
| `--lr_scheduler` | 学习率调度器 | `constant_with_warmup` |
| `--lr_warmup_steps` | 学习率预热步数 | 100 |
| `--seed` | 随机种子 | 42 |
| `--output_dir` | 输出目录 | `output_dir_wan2.1_self_forcing_distill` |
| `--gradient_checkpointing` | 激活重计算 | - |
| `--mixed_precision` | 混合精度：`fp16/bf16` | `bf16` |
| `--adam_weight_decay` | AdamW 权重衰减 | 3e-2 |
| `--adam_weight_decay` | AdamW 权重衰减 | 0.0 |
| `--adam_beta1` | AdamW beta1 | 0.0 |
| `--adam_beta2` | AdamW beta2 | 0.999 |
| `--adam_epsilon` | AdamW epsilon 值 | 1e-10 |
| `--vae_mini_batch` | VAE 编码时的迷你批次大小 | 1 |
| `--max_grad_norm` | 梯度裁剪阈值 | 0.05 |
| `--max_grad_norm` | 梯度裁剪阈值 | 10.0 |
| `--fsdp_reduce_fp32` | 可选：FSDP 混精下梯度以 fp32 做跨卡 reduce（默认 bf16） | - |
| `--enable_bucket` | 启用分桶训练，不裁剪图片/视频，按分辨率分组训练 | - |
| `--random_hw_adapt` | 自动缩放图片/视频到 `[min_size, max_size]` 范围内的随机尺寸 | - |
@@ -278,7 +287,7 @@ accelerate launch --use_deepspeed --deepspeed_config_file config/zero_stage2_con
|-----|------|-------|
| `--denoising_step_indices_list` | 去噪步骤列表（蒸馏核心参数） | `1000 750 500 250` |
| `--randomize_step_indices` | 训练时随机化去噪 timestep 索引 | - |
| `--real_guidance_scale` | 用于评分的真实 guidance scale | 6.0 |
| `--real_guidance_scale` | 用于评分的真实 guidance scale | 4.0 |
| `--score_timestep_clamp` | 可选：将 DMD/critic 的 timestep 截断到 `[0.02, 0.98] * num_train_timesteps` | - |
| `--fake_guidance_scale` | 用于评分的虚拟 guidance scale | 0.0 |
| `--gen_update_interval` | 生成器更新间隔 | 5 |
@@ -366,6 +375,7 @@ accelerate launch --use_deepspeed --deepspeed_config_file config/zero_stage2_con
```bash
export MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-1.3B/"
export REAL_SCORE_MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-14B"
export DATASET_NAME="datasets/X-Fun-Videos-Demo/"
export DATASET_META_NAME="datasets/X-Fun-Videos-Demo/metadata_add_width_height.json"
# NCCL_IB_DISABLE=1 and NCCL_P2P_DISABLE=1 are used in multi nodes without RDMA.
@@ -376,6 +386,7 @@ NCCL_DEBUG=INFO
accelerate launch --mixed_precision="bf16" --use_fsdp --fsdp_auto_wrap_policy TRANSFORMER_BASED_WRAP --fsdp_transformer_layer_cls_to_wrap=CasualWanAttentionBlock --fsdp_sharding_strategy "FULL_SHARD" --fsdp_state_dict_type=SHARDED_STATE_DICT --fsdp_backward_prefetch "BACKWARD_PRE" --fsdp_cpu_ram_efficient_loading False scripts/wan2.1_self_forcing/train_distill.py \
--config_path="config/wan2.1/wan_civitai.yaml" \
--pretrained_model_name_or_path=$MODEL_NAME \
--real_score_model_name_or_path=$REAL_SCORE_MODEL_NAME \
--train_data_dir=$DATASET_NAME \
--train_data_meta=$DATASET_META_NAME \
--image_sample_size=640 \
@@ -391,21 +402,26 @@ accelerate launch --mixed_precision="bf16" --use_fsdp --fsdp_auto_wrap_policy TR
--num_train_epochs=100 \
--checkpointing_steps=50 \
--learning_rate=2e-06 \
--learning_rate_critic=2e-06 \
--learning_rate_critic=4.0e-07 \
--lr_scheduler="constant_with_warmup" \
--lr_warmup_steps=100 \
--seed=42 \
--output_dir="output_dir_wan2.1_self_forcing_distill" \
--gradient_checkpointing \
--mixed_precision="bf16" \
--adam_weight_decay=3e-2 \
--fsdp_reduce_fp32 \
--adam_weight_decay=0.0 \
--adam_beta1=0.0 \
--adam_beta2=0.999 \
--adam_epsilon=1e-10 \
--vae_mini_batch=1 \
--max_grad_norm=0.05 \
--max_grad_norm=10.0 \
--random_hw_adapt \
--training_with_video_token_length \
--enable_bucket \
--uniform_sampling \
--denoising_step_indices_list 1000 750 500 250 \
--real_guidance_scale=4.0 \
--score_timestep_clamp \
--use_kv_cache_training \
--num_frame_per_block=3 \
--train_mode="normal" \
@@ -428,6 +444,7 @@ python scripts/zero_to_bf16.py output_dir/checkpoint-{our-num-steps} output_dir/
训练 shell 命令如下：
```bash
export MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-1.3B/"
export REAL_SCORE_MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-14B"
export DATASET_NAME="datasets/X-Fun-Videos-Demo/"
export DATASET_META_NAME="datasets/X-Fun-Videos-Demo/metadata_add_width_height.json"
# NCCL_IB_DISABLE=1 and NCCL_P2P_DISABLE=1 are used in multi nodes without RDMA.
@@ -438,6 +455,7 @@ NCCL_DEBUG=INFO
accelerate launch --zero_stage 3 --zero3_save_16bit_model true --zero3_init_flag true --use_deepspeed --deepspeed_config_file config/zero_stage3_config.json --deepspeed_multinode_launcher standard scripts/wan2.1_self_forcing/train_distill.py \
--config_path="config/wan2.1/wan_civitai.yaml" \
--pretrained_model_name_or_path=$MODEL_NAME \
--real_score_model_name_or_path=$REAL_SCORE_MODEL_NAME \
--train_data_dir=$DATASET_NAME \
--train_data_meta=$DATASET_META_NAME \
--image_sample_size=640 \
@@ -453,21 +471,26 @@ accelerate launch --zero_stage 3 --zero3_save_16bit_model true --zero3_init_flag
--num_train_epochs=100 \
--checkpointing_steps=50 \
--learning_rate=2e-06 \
--learning_rate_critic=2e-06 \
--learning_rate_critic=4.0e-07 \
--lr_scheduler="constant_with_warmup" \
--lr_warmup_steps=100 \
--seed=42 \
--output_dir="output_dir_wan2.1_self_forcing_distill" \
--gradient_checkpointing \
--mixed_precision="bf16" \
--adam_weight_decay=3e-2 \
--fsdp_reduce_fp32 \
--adam_weight_decay=0.0 \
--adam_beta1=0.0 \
--adam_beta2=0.999 \
--adam_epsilon=1e-10 \
--vae_mini_batch=1 \
--max_grad_norm=0.05 \
--max_grad_norm=10.0 \
--random_hw_adapt \
--training_with_video_token_length \
--enable_bucket \
--uniform_sampling \
--denoising_step_indices_list 1000 750 500 250 \
--real_guidance_scale=4.0 \
--score_timestep_clamp \
--use_kv_cache_training \
--num_frame_per_block=3 \
--train_mode="normal" \
@@ -482,6 +505,7 @@ accelerate launch --zero_stage 3 --zero3_save_16bit_model true --zero3_init_flag
```bash
export MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-1.3B/"
export REAL_SCORE_MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-14B"
export DATASET_NAME="datasets/X-Fun-Videos-Demo/"
export DATASET_META_NAME="datasets/X-Fun-Videos-Demo/metadata_add_width_height.json"
# NCCL_IB_DISABLE=1 and NCCL_P2P_DISABLE=1 are used in multi nodes without RDMA.
@@ -492,6 +516,7 @@ NCCL_DEBUG=INFO
accelerate launch --mixed_precision="bf16" scripts/wan2.1_self_forcing/train_distill.py \
--config_path="config/wan2.1/wan_civitai.yaml" \
--pretrained_model_name_or_path=$MODEL_NAME \
--real_score_model_name_or_path=$REAL_SCORE_MODEL_NAME \
--train_data_dir=$DATASET_NAME \
--train_data_meta=$DATASET_META_NAME \
--image_sample_size=640 \
@@ -507,21 +532,26 @@ accelerate launch --mixed_precision="bf16" scripts/wan2.1_self_forcing/train_dis
--num_train_epochs=100 \
--checkpointing_steps=50 \
--learning_rate=2e-06 \
--learning_rate_critic=2e-06 \
--learning_rate_critic=4.0e-07 \
--lr_scheduler="constant_with_warmup" \
--lr_warmup_steps=100 \
--seed=42 \
--output_dir="output_dir_wan2.1_self_forcing_distill" \
--gradient_checkpointing \
--mixed_precision="bf16" \
--adam_weight_decay=3e-2 \
--fsdp_reduce_fp32 \
--adam_weight_decay=0.0 \
--adam_beta1=0.0 \
--adam_beta2=0.999 \
--adam_epsilon=1e-10 \
--vae_mini_batch=1 \
--max_grad_norm=0.05 \
--max_grad_norm=10.0 \
--random_hw_adapt \
--training_with_video_token_length \
--enable_bucket \
--uniform_sampling \
--denoising_step_indices_list 1000 750 500 250 \
--real_guidance_scale=4.0 \
--score_timestep_clamp \
--use_kv_cache_training \
--num_frame_per_block=3 \
--train_mode="normal" \
@@ -541,6 +571,7 @@ accelerate launch --mixed_precision="bf16" scripts/wan2.1_self_forcing/train_dis
**机器 0（Master）**：
```bash
export MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-1.3B/"
export REAL_SCORE_MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-14B"
export DATASET_NAME="datasets/X-Fun-Videos-Demo/"
export DATASET_META_NAME="datasets/X-Fun-Videos-Demo/metadata_add_width_height.json"
export MASTER_ADDR="192.168.1.100" # Master 机器 IP
@@ -556,6 +587,7 @@ NCCL_DEBUG=INFO
accelerate launch --mixed_precision="bf16" --main_process_ip=$MASTER_ADDR --main_process_port=$MASTER_PORT --num_machines=$WORLD_SIZE --num_processes=$NUM_PROCESS --machine_rank=$RANK --use_deepspeed --deepspeed_config_file config/zero_stage2_config.json --deepspeed_multinode_launcher standard scripts/wan2.1_self_forcing/train_distill.py \
--config_path="config/wan2.1/wan_civitai.yaml" \
--pretrained_model_name_or_path=$MODEL_NAME \
--real_score_model_name_or_path=$REAL_SCORE_MODEL_NAME \
--train_data_dir=$DATASET_NAME \
--train_data_meta=$DATASET_META_NAME \
--image_sample_size=640 \
@@ -571,21 +603,26 @@ accelerate launch --mixed_precision="bf16" --main_process_ip=$MASTER_ADDR --main
--num_train_epochs=100 \
--checkpointing_steps=50 \
--learning_rate=2e-06 \
--learning_rate_critic=2e-06 \
--learning_rate_critic=4.0e-07 \
--lr_scheduler="constant_with_warmup" \
--lr_warmup_steps=100 \
--seed=42 \
--output_dir="output_dir_wan2.1_self_forcing_distill" \
--gradient_checkpointing \
--mixed_precision="bf16" \
--adam_weight_decay=3e-2 \
--fsdp_reduce_fp32 \
--adam_weight_decay=0.0 \
--adam_beta1=0.0 \
--adam_beta2=0.999 \
--adam_epsilon=1e-10 \
--vae_mini_batch=1 \
--max_grad_norm=0.05 \
--max_grad_norm=10.0 \
--random_hw_adapt \
--training_with_video_token_length \
--enable_bucket \
--uniform_sampling \
--denoising_step_indices_list 1000 750 500 250 \
--real_guidance_scale=4.0 \
--score_timestep_clamp \
--use_kv_cache_training \
--num_frame_per_block=3 \
--train_mode="normal" \
@@ -597,6 +634,7 @@ accelerate launch --mixed_precision="bf16" --main_process_ip=$MASTER_ADDR --main
**机器 1（Worker）**：
```bash
export MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-1.3B/"
export REAL_SCORE_MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-14B"
export DATASET_NAME="datasets/X-Fun-Videos-Demo/"
export DATASET_META_NAME="datasets/X-Fun-Videos-Demo/metadata_add_width_height.json"
export MASTER_ADDR="192.168.1.100" # 与 Master 相同
scripts/wan2.1_self_forcing/train_distill.sh
+11 -4
View File
@@ -1,4 +1,5 @@
export MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-1.3B/"
export REAL_SCORE_MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-14B"
export DATASET_NAME="datasets/internal_datasets/"
export DATASET_META_NAME="datasets/internal_datasets/metadata.json"
# NCCL_IB_DISABLE=1 and NCCL_P2P_DISABLE=1 are used in multi nodes without RDMA.
@@ -9,6 +10,7 @@ NCCL_DEBUG=INFO
accelerate launch --mixed_precision="bf16" scripts/wan2.1_self_forcing/train_distill.py \
--config_path="config/wan2.1/wan_civitai.yaml" \
--pretrained_model_name_or_path=$MODEL_NAME \
--real_score_model_name_or_path=$REAL_SCORE_MODEL_NAME \
--train_data_dir=$DATASET_NAME \
--train_data_meta=$DATASET_META_NAME \
--image_sample_size=640 \
@@ -24,21 +26,26 @@ accelerate launch --mixed_precision="bf16" scripts/wan2.1_self_forcing/train_dis
--num_train_epochs=100 \
--checkpointing_steps=50 \
--learning_rate=2e-06 \
--learning_rate_critic=2e-06 \
--learning_rate_critic=4.0e-07 \
--lr_scheduler="constant_with_warmup" \
--lr_warmup_steps=100 \
--seed=42 \
--output_dir="output_dir_wan2.1_self_forcing_distill" \
--gradient_checkpointing \
--mixed_precision="bf16" \
--adam_weight_decay=3e-2 \
--fsdp_reduce_fp32 \
--adam_weight_decay=0.0 \
--adam_beta1=0.0 \
--adam_beta2=0.999 \
--adam_epsilon=1e-10 \
--vae_mini_batch=1 \
--max_grad_norm=0.05 \
--max_grad_norm=10.0 \
--random_hw_adapt \
--training_with_video_token_length \
--enable_bucket \
--uniform_sampling \
--denoising_step_indices_list 1000 750 500 250 \
--real_guidance_scale=4.0 \
--score_timestep_clamp \
--use_kv_cache_training \
--num_frame_per_block=3 \
--train_mode="normal" \