Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
distill_hunyuan.sh 2.85 KB
Newer Older
hepj's avatar
dit & video  
hepj committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87 
export WANDB_BASE_URL="https://api.wandb.ai"
export WANDB_MODE=online

DATA_DIR=./data
IP=[MASTER NODE IP]

torchrun --nnodes 4 --nproc_per_node 8\
    --node_rank=0 \
    --rdzv_id=456 \
    --rdzv_backend=c10d \
    --rdzv_endpoint=$IP:29500 \
    fastvideo/distill.py\
    --seed 42\
    --pretrained_model_name_or_path $DATA_DIR/hunyuan\
    --dit_model_name_or_path $DATA_DIR/hunyuan/hunyuan-video-t2v-720p/transformers/mp_rank_00_model_states.pt\
    --model_type "hunyuan" \
    --cache_dir "$DATA_DIR/.cache"\
    --data_json_path "$DATA_DIR/HD-Mixkit-Finetune-Hunyuan/videos2caption.json"\
    --validation_prompt_dir "$DATA_DIR/HD-Mixkit-Finetune-Hunyuan/validation"\
    --gradient_checkpointing\
    --train_batch_size=1\
    --num_latent_t 32 \
    --sp_size 2 \
    --train_sp_batch_size 1\
    --dataloader_num_workers 4\
    --gradient_accumulation_steps=1\
    --max_train_steps=320\
    --learning_rate=1e-6\
    --mixed_precision="bf16"\
    --checkpointing_steps=64\
    --validation_steps 64\
    --validation_sampling_steps "2,4,8" \
    --checkpoints_total_limit 3\
    --allow_tf32\
    --ema_start_step 0\
    --cfg 0.0\
    --log_validation\
    --output_dir="$DATA_DIR/outputs/hy_phase1_shift17_bs_16_HD"\
    --tracker_project_name Hunyuan_Distill \
    --num_height 720 \
    --num_width 1280 \
    --num_frames  125 \
    --shift 17 \
    --validation_guidance_scale "1.0" \
    --num_euler_timesteps 50 \
    --multi_phased_distill_schedule "4000-1" \
    --not_apply_cfg_solver 


# If you do not have 32 GPUs and to fit in memory, you can: 1. increase sp_size. 2. reduce num_latent_t
torchrun --nnodes 1 --nproc_per_node 8\
    fastvideo/distill.py\
    --seed 42\
    --pretrained_model_name_or_path $DATA_DIR/hunyuan\
    --dit_model_name_or_path $DATA_DIR/hunyuan/hunyuan-video-t2v-720p/transformers/mp_rank_00_model_states.pt\
    --model_type "hunyuan" \
    --cache_dir "$DATA_DIR/.cache"\
    --data_json_path "$DATA_DIR/HD-Mixkit-Finetune-Hunyuan/videos2caption.json"\
    --validation_prompt_dir "$DATA_DIR/HD-Mixkit-Finetune-Hunyuan/validation"\
    --gradient_checkpointing\
    --train_batch_size=1\
    --num_latent_t 32 \
    --sp_size 2 \
    --train_sp_batch_size 1\
    --dataloader_num_workers 4\
    --gradient_accumulation_steps=1\
    --max_train_steps=320\
    --learning_rate=1e-6\
    --mixed_precision="bf16"\
    --checkpointing_steps=64\
    --validation_steps 64\
    --validation_sampling_steps "2,4,8" \
    --checkpoints_total_limit 3\
    --allow_tf32\
    --ema_start_step 0\
    --cfg 0.0\
    --log_validation\
    --output_dir="$DATA_DIR/outputs/hy_phase1_shift17_bs_16_HD"\
    --tracker_project_name Hunyuan_Distill \
    --num_height 720 \
    --num_width 1280 \
    --num_frames  125 \
    --shift 17 \
    --validation_guidance_scale "1.0" \
    --num_euler_timesteps 50 \
    --multi_phased_distill_schedule "4000-1" \
    --not_apply_cfg_solver