nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[v0] Remove V0 code (#621)

Browse Source
This commit is contained in:
William Lin
2025-07-15 22:05:16 -07:00
committed by GitHub
parent b79d1fc15b
commit 576c214f28
119 changed files with 86 additions and 23605 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/dataset_preparation/generate_validation_json.py
+63
View File
@@ -0,0 +1,63 @@
import argparse
import json
import os
import random
def generate_merged_validation_json(input_dir, output_file):
# read in video2caption.json
with open(os.path.join(input_dir, "video2caption_replace.json"), "r") as f:
video2caption = json.load(f)
# count how many elements are in the list
num_elements = len(video2caption)
print(f"Number of elements in video2caption.json: {num_elements}")
# randomly sample 64 elements from the list
sampled_elements = random.sample(video2caption, 64)
# Transform sampled elements into validation.json format
validation_data = []
for element in sampled_elements:
assert element.get("cap") is not None, f"Caption is None for element: {element}"
validation_entry = {
"caption": element["cap"],
"video_path": element.get("path", ""),
"num_inference_steps": 40,
"height": 480,
"width": 832,
"num_frames": 77
}
validation_data.append(validation_entry)
# Create the final validation structure
validation_json = {
"data": validation_data
}
# Write the validation JSON to the output file
with open(output_file, "w") as f:
json.dump(validation_json, f, indent=2)
print(f"Generated validation JSON with {len(validation_data)} entries and saved to {output_file}")
def main():
parser = argparse.ArgumentParser()
# dataset_type: "mixkit"
parser.add_argument("--dataset_type", choices=["merged"], required=True)
parser.add_argument("--input_dir", type=str, required=True)
parser.add_argument("--output_file", type=str, required=True)
parser.add_argument("--num_elements", type=int, default=64)
parser.add_argument("--num_frames", type=int, default=77)
parser.add_argument("--height", type=int, default=480)
parser.add_argument("--width", type=int, default=832)
parser.add_argument("--num_inference_steps", type=int, default=40)
args = parser.parse_args()
if args.dataset_type == "merged":
generate_merged_validation_json(args.input_dir, args.output_file)
if __name__ == "__main__":
main()
scripts/distill/distill_hunyuan.sh
-87
View File
@@ -1,87 +0,0 @@
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
scripts/distill/distill_mochi.sh
-38
View File
@@ -1,38 +0,0 @@
export WANDB_BASE_URL="https://api.wandb.ai"
export WANDB_MODE=online
torchrun --nnodes 1 --nproc_per_node 4 \
fastvideo/distill.py \
--seed 42 \
--pretrained_model_name_or_path data/mochi \
--model_type "mochi" \
--cache_dir data/.cache \
--data_json_path data/Merge-30k-Data/video2caption.json \
--validation_prompt_dir data/Image-Vid-Finetune-Mochi/validation \
--gradient_checkpointing \
--train_batch_size=1 \
--num_latent_t 28 \
--sp_size 4 \
--train_sp_batch_size 2 \
--dataloader_num_workers 4 \
--gradient_accumulation_steps=1 \
--max_train_steps=4000 \
--learning_rate=1e-6 \
--mixed_precision=bf16 \
--checkpointing_steps=64 \
--validation_steps 1 \
--validation_sampling_steps 8 \
--checkpoints_total_limit 3 \
--allow_tf32 \
--ema_start_step 0 \
--cfg 0.0 \
--log_validation \
--output_dir="data/outputs/lq_euler_50_thres0.1_lrg_0.75_phase1_lr1e-6_repro" \
--tracker_project_name PCM \
--num_frames 163 \
--scheduler_type pcm_linear_quadratic \
--validation_guidance_scale 0.5,1.5,2.5 \
--num_euler_timesteps 50 \
--linear_quadratic_threshold 0.1 \
--linear_range 0.75 \
--multi_phased_distill_schedule 4000-1
scripts/distill/distill_wan.sh
-39
View File
@@ -1,39 +0,0 @@
#https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B-Diffusers/tree/main
DATA_DIR=./data
torchrun --nnodes 1 --nproc_per_node 8\
fastvideo/distill.py\
--seed 42\
--pretrained_model_name_or_path $DATA_DIR/wan\
--model_type "wan" \
--cache_dir "$DATA_DIR/.cache"\
--data_json_path "$DATA_DIR/Image-Vid-Finetune-Wan/videos2caption.json"\
--validation_prompt_dir "$DATA_DIR/Image-Vid-Finetune-Wan/validation"\
--gradient_checkpointing\
--train_batch_size=1\
--num_latent_t 32 \
--sp_size 1 \
--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 "8" \
--checkpoints_total_limit 3\
--allow_tf32\
--ema_start_step 0\
--cfg 5.0\
--log_validation\
--output_dir="$DATA_DIR/outputs/wan"\
--tracker_project_name Wan_PCM \
--num_height 480 \
--num_width 832 \
--num_frames 81 \
--shift 3 \
--validation_guidance_scale "1.0" \
--num_euler_timesteps 50 \
--multi_phased_distill_schedule "4000-1" \
--not_apply_cfg_solver
scripts/finetune/v0/finetune_hunyuan.sh
-38
View File
@@ -1,38 +0,0 @@
export WANDB_BASE_URL="https://api.wandb.ai"
export WANDB_MODE=online
torchrun --nnodes 1 --nproc_per_node 8 \
fastvideo/train.py \
--seed 42 \
--pretrained_model_name_or_path data/hunyuan \
--dit_model_name_or_path data/hunyuan/hunyuan-video-t2v-720p/transformers/mp_rank_00_model_states.pt\
--model_type "hunyuan" \
--cache_dir data/.cache \
--data_json_path data/Image-Vid-Finetune-HunYuan/videos2caption.json \
--validation_prompt_dir data/Image-Vid-Finetune-HunYuan/validation \
--gradient_checkpointing \
--train_batch_size=1 \
--num_latent_t 32 \
--sp_size 4 \
--train_sp_batch_size 1 \
--dataloader_num_workers 4 \
--gradient_accumulation_steps=1 \
--max_train_steps=2000 \
--learning_rate=1e-5 \
--mixed_precision=bf16 \
--checkpointing_steps=200 \
--validation_steps 100 \
--validation_sampling_steps 50 \
--checkpoints_total_limit 3 \
--allow_tf32 \
--ema_start_step 0 \
--cfg 0.0 \
--ema_decay 0.999 \
--log_validation \
--output_dir=data/outputs/HSH-Taylor-Finetune-Hunyuan \
--tracker_project_name HSH-Taylor-Finetune-Hunyuan \
--num_frames 125 \
--num_height 720 \
--num_width 1280 \
--shift 7 \
--validation_guidance_scale "1.0" \
scripts/finetune/v0/finetune_hunyuan_hf_lora.sh
-37
View File
@@ -1,37 +0,0 @@
export WANDB_BASE_URL="https://api.wandb.ai"
export WANDB_MODE=online
torchrun --nnodes 1 --nproc_per_node 4 --master_port 29903 \
fastvideo/train.py \
--seed 1024 \
--pretrained_model_name_or_path data/hunyuan_diffusers \
--model_type hunyuan_hf \
--cache_dir data/.cache \
--data_json_path data/Black-Myth-Wukong/videos2caption.json \
--validation_prompt_dir data/Black-Myth-Wukong/validation \
--gradient_checkpointing \
--train_batch_size 1 \
--num_latent_t 32 \
--sp_size 4 \
--train_sp_batch_size 1 \
--dataloader_num_workers 4 \
--gradient_accumulation_steps 4 \
--max_train_steps 6000 \
--learning_rate 8e-5 \
--mixed_precision bf16 \
--checkpointing_steps 500 \
--validation_steps 100 \
--validation_sampling_steps 50 \
--checkpoints_total_limit 3 \
--allow_tf32 \
--ema_start_step 0 \
--cfg 0.0 \
--ema_decay 0.999 \
--log_validation \
--output_dir data/outputs/Hunyuan-lora-finetuning-Black-Myth-Wukong \
--tracker_project_name Hunyuan-lora-finetuning-Black-Myth-Wukong \
--num_frames 125 \
--validation_guidance_scale "1.0" \
--shift 7 \
--use_lora \
--lora_rank 32 \
--lora_alpha 32
scripts/finetune/v0/finetune_mochi.sh
-32
View File
@@ -1,32 +0,0 @@
export WANDB_BASE_URL="https://api.wandb.ai"
export WANDB_MODE=online
torchrun --nnodes 1 --nproc_per_node 4 \
fastvideo/train.py \
--seed 42 \
--pretrained_model_name_or_path data/mochi \
--cache_dir data/.cache \
--data_json_path data/Mochi-Black-Myth/videos2caption.json \
--validation_prompt_dir data/Mochi-Black-Myth/validation \
--gradient_checkpointing \
--train_batch_size=1 \
--num_latent_t 16 \
--sp_size 1 \
--train_sp_batch_size 1 \
--dataloader_num_workers 4 \
--gradient_accumulation_steps=1 \
--max_train_steps=2000 \
--learning_rate=5e-6 \
--mixed_precision=bf16 \
--checkpointing_steps=200 \
--validation_steps 100 \
--validation_sampling_steps 64 \
--checkpoints_total_limit 3 \
--allow_tf32 \
--ema_start_step 0 \
--cfg 0.0 \
--ema_decay 0.999 \
--log_validation \
--output_dir=data/outputs/Black-Myth-Finetune \
--tracker_project_name Black-Myth-Finetune \
--num_frames 93
scripts/finetune/v0/finetune_mochi_lora.sh
-37
View File
@@ -1,37 +0,0 @@
export WANDB_BASE_URL="https://api.wandb.ai"
export WANDB_MODE=online
torchrun --nnodes 1 --nproc_per_node 2 \
fastvideo/train.py \
--seed 42 \
--pretrained_model_name_or_path data/mochi \
--cache_dir data/.cache \
--data_json_path data/Mochi-Black-Myth/videos2caption.json \
--validation_prompt_dir data/Mochi-Black-Myth/validation \
--gradient_checkpointing \
--train_batch_size 1 \
--num_latent_t 14 \
--sp_size 2 \
--train_sp_batch_size 1 \
--dataloader_num_workers 1 \
--gradient_accumulation_steps 2 \
--max_train_steps 2000 \
--learning_rate 5e-6 \
--mixed_precision bf16 \
--checkpointing_steps 200 \
--validation_steps 100 \
--validation_sampling_steps 64 \
--checkpoints_total_limit 3 \
--allow_tf32 \
--ema_start_step 0 \
--cfg 0.0 \
--ema_decay 0.999 \
--log_validation \
--output_dir=data/outputs/Black-Myth-Lora-FT \
--tracker_project_name Black-Myth-Lora-Finetune \
--num_frames 91 \
--lora_rank 128 \
--lora_alpha 256 \
--master_weight_type "bf16" \
--use_lora \
--use_cpu_offload
scripts/finetune/v0/finetune_mochi_lora_mix.sh
-37
View File
@@ -1,37 +0,0 @@
export WANDB_BASE_URL="https://api.wandb.ai"
export WANDB_MODE=online
CUDA_VISIBLE_DEVICES=5 torchrun --nnodes 1 --nproc_per_node 1 \
fastvideo/train.py \
--seed 42 \
--pretrained_model_name_or_path data/mochi \
--cache_dir data/.cache \
--data_json_path data/Image-Vid-Finetune-Mochi/videos2caption.json \
--validation_prompt_dir data/Image-Vid-Finetune-Mochi/validation \
--gradient_checkpointing \
--train_batch_size=1 \
--num_latent_t 14 \
--sp_size 1 \
--train_sp_batch_size 1 \
--dataloader_num_workers 1 \
--gradient_accumulation_steps=1 \
--max_train_steps=2000 \
--learning_rate=5e-6 \
--mixed_precision=bf16 \
--checkpointing_steps=200 \
--validation_steps 100 \
--validation_sampling_steps 64 \
--checkpoints_total_limit 3 \
--allow_tf32 \
--ema_start_step 0 \
--cfg 0.0 \
--ema_decay 0.999 \
--log_validation \
--output_dir=data/outputs/HSH-Taylor-Finetune-Lora \
--tracker_project_name HSH-Taylor-Finetune-Lora \
--num_frames 91 \
--group_frame \
--lora_rank 128 \
--lora_alpha 256 \
--master_weight_type "bf16" \
--use_lora
scripts/inference/v0/inference_hunyuan.sh
-40
View File
@@ -1,40 +0,0 @@
#!/bin/bash
num_gpus=4
export MODEL_BASE=data/FastHunyuan
torchrun --nnodes=1 --nproc_per_node=$num_gpus --master_port 29503 \
fastvideo/sample/sample_t2v_hunyuan.py \
--height 720 \
--width 1280 \
--num_frames 125 \
--num_inference_steps 6 \
--guidance_scale 1 \
--embedded_cfg_scale 6 \
--flow_shift 17 \
--flow-reverse \
--prompt ./assets/prompt.txt \
--seed 1024 \
--output_path outputs_video/hunyuan/vae_sp/ \
--model_path $MODEL_BASE \
--dit-weight ${MODEL_BASE}/hunyuan-video-t2v-720p/transformers/mp_rank_00_model_states.pt \
--vae-sp
# Inference original Hunyuan
num_gpus=4
export MODEL_BASE=data/hunyuan
torchrun --nnodes=1 --nproc_per_node=$num_gpus --master_port 29503 \
fastvideo/sample/sample_t2v_hunyuan.py \
--height 720 \
--width 1280 \
--num_frames 125 \
--num_inference_steps 50 \
--guidance_scale 1 \
--embedded_cfg_scale 6 \
--flow_shift 7 \
--flow-reverse \
--prompt ./assets/prompt.txt \
--seed 1024 \
--output_path outputs_video/hunyuan/vae_sp/ \
--model_path $MODEL_BASE \
--dit-weight ${MODEL_BASE}/hunyuan-video-t2v-720p/transformers/mp_rank_00_model_states.pt \
--vae-sp
scripts/inference/v0/inference_hunyuan_STA.sh
-49
View File
@@ -1,49 +0,0 @@
#!/bin/bash
# Inference with STA + Teacache
num_gpus=1 # currently it should be a factor of 30
mask_strategy_file_path=assets/mask_strategy_hunyuan.json
export MODEL_BASE=data/hunyuan
rel_l1_thresh=0.15
CUDA_VISIBLE_DEVICES=0,1,2,3 torchrun --nnodes=1 --nproc_per_node=$num_gpus --master_port 29603 \
fastvideo/sample/sample_t2v_hunyuan_STA.py \
--height 768 \
--width 1280 \
--num_frames 117 \
--num_inference_steps 50 \
--guidance_scale 1 \
--embedded_cfg_scale 6 \
--flow_shift 7 \
--flow-reverse \
--prompt ./assets/prompt.txt \
--seed 12345 \
--output_path outputs_video/hunyuan_STA/ \
--model_path $MODEL_BASE \
--mask_strategy_file_path $mask_strategy_file_path \
--rel_l1_thresh $rel_l1_thresh \
--dit-weight ${MODEL_BASE}/hunyuan-video-t2v-720p/transformers/mp_rank_00_model_states.pt \
--vae-sp \
--enable_teacache
# Inference with STA only
num_gpus=1
mask_strategy_file_path=assets/mask_strategy_hunyuan.json
export MODEL_BASE=data/hunyuan
CUDA_VISIBLE_DEVICES=1 torchrun --nnodes=1 --nproc_per_node=$num_gpus --master_port 29603 \
fastvideo/sample/sample_t2v_hunyuan_STA.py \
--height 768 \
--width 1280 \
--num_frames 117 \
--num_inference_steps 50 \
--guidance_scale 1 \
--embedded_cfg_scale 6 \
--flow_shift 7 \
--flow-reverse \
--prompt ./assets/prompt.txt \
--seed 12345 \
--output_path outputs_video/hunyuan_STA/ \
--model_path $MODEL_BASE \
--mask_strategy_file_path $mask_strategy_file_path \
--dit-weight ${MODEL_BASE}/hunyuan-video-t2v-720p/transformers/mp_rank_00_model_states.pt \
--vae-sp \
--enable_torch_compile
scripts/inference/v0/inference_hunyuan_hf.sh
-15
View File
@@ -1,15 +0,0 @@
#!/bin/bash
num_gpus=4
torchrun --nnodes=1 --nproc_per_node=$num_gpus --master_port 29503 \
fastvideo/sample/sample_t2v_hunyuan_hf.py \
--model_path ~/data/hunyuan_diffusers/ \
--prompt_path "assets/prompt.txt" \
--num_frames 125 \
--height 720 \
--width 1280 \
--num_inference_steps 50 \
--output_path outputs_video/hunyuan_hf/ \
--seed 1024 \
scripts/inference/v0/inference_hunyuan_hf_quantization.sh
-19
View File
@@ -1,19 +0,0 @@
#!/bin/bash
num_gpus=1
export MODEL_BASE="data/FastHunyuan-diffusers"
torchrun --nnodes=1 --nproc_per_node=$num_gpus --master_port 12345 \
fastvideo/sample/sample_t2v_hunyuan_hf.py \
--height 720 \
--width 1280 \
--num_frames 45 \
--num_inference_steps 6 \
--guidance_scale 1 \
--embedded_cfg_scale 6 \
--flow_shift 17 \
--prompt ./assets/prompt.txt \
--seed 1024 \
--output_path outputs_video/hunyuan_quant/nf4/ \
--model_path $MODEL_BASE \
--quantization "nf4" \
--cpu_offload
scripts/inference/v0/inference_mochi_hf.sh
-18
View File
@@ -1,18 +0,0 @@
#!/bin/bash
num_gpus=4
torchrun --nnodes=1 --nproc_per_node=$num_gpus --master_port 29503 \
fastvideo/sample/sample_t2v_mochi.py \
--model_path data/FastMochi-diffusers \
--prompt_path "assets/prompt.txt" \
--num_frames 163 \
--height 480 \
--width 848 \
--num_inference_steps 8 \
--guidance_scale 1.5 \
--output_path outputs_video/mochi_hf/ \
--seed 1024 \
--scheduler_type "pcm_linear_quadratic" \
--linear_threshold 0.1 \
--linear_range 0.75
scripts/inference/v0/inference_stepvideo.sh
-19
View File
@@ -1,19 +0,0 @@
#!/bin/bash
# You better have two terminal, one for the remote server, and one for DiT
CUDA_VISIBLE_DEVICES=7 python fastvideo/sample/call_remote_server_stepvideo.py --model_dir data/stepvideo-t2v/ &
parallel=4
url='127.0.0.1'
model_dir=data/stepvideo-t2v
torchrun --nproc_per_node $parallel fastvideo/sample/sample_t2v_stepvideo.py \
--model_dir $model_dir \
--vae_url $url \
--caption_url $url \
--prompt assets/prompt.txt \
--infer_steps 50 \
--width 768 \
--height 768 \
--num_frames 204 \
--cfg_scale 9.0 \
--save_path outputs/ \
--time_shift 13.0
scripts/inference/v0/inference_stepvideo_STA.sh
-25
View File
@@ -1,25 +0,0 @@
#!/bin/bash
# Inference with STA + Teacache
# You better have two terminal, one for the remote server, and one for DiT
# remove enable_teacache to disable Teacache
CUDA_VISIBLE_DEVICES=7 python fastvideo/sample/call_remote_server_stepvideo.py --model_dir data/stepvideo-t2v/ &
parallel=4
url='127.0.0.1'
model_dir=data/stepvideo-t2v
mask_strategy_file_path=assets/mask_strategy_stepvideo.json
rel_l1_thresh=0.23
torchrun --nproc_per_node $parallel fastvideo/sample/sample_t2v_stepvideo_STA.py \
--model_dir $model_dir \
--vae_url $url \
--caption_url $url \
--prompt "A rocket blasting off from the launch pad, accelerating rapidly into the sky." \
--infer_steps 50 \
--width 768 \
--height 768 \
--num_frames 204 \
--cfg_scale 9.0 \
--save_path outputs/ \
--time_shift 13.0 \
--rel_l1_thresh $rel_l1_thresh \
--enable_teacache \
--mask_strategy_file_path $mask_strategy_file_path
scripts/preprocess/v0/preprocess_hunyuan_data.sh
-33
View File
@@ -1,33 +0,0 @@
# export WANDB_MODE="offline"
GPU_NUM=1 # 2,4,8
MODEL_PATH="data/hunyuan"
MODEL_TYPE="hunyuan"
DATA_MERGE_PATH="data/Image-Vid-Finetune-Src/merge.txt"
OUTPUT_DIR="data/Image-Vid-Finetune-HunYuan"
VALIDATION_PATH="assets/prompt.txt"
torchrun --nproc_per_node=$GPU_NUM \
fastvideo/data_preprocess/preprocess_vae_latents.py \
--model_path $MODEL_PATH \
--data_merge_path $DATA_MERGE_PATH \
--train_batch_size=1 \
--max_height=480 \
--max_width=848 \
--num_frames=93 \
--dataloader_num_workers 1 \
--output_dir=$OUTPUT_DIR \
--model_type $MODEL_TYPE \
--train_fps 24
torchrun --nproc_per_node=$GPU_NUM \
fastvideo/data_preprocess/preprocess_text_embeddings.py \
--model_type $MODEL_TYPE \
--model_path $MODEL_PATH \
--output_dir=$OUTPUT_DIR
torchrun --nproc_per_node=1 \
fastvideo/data_preprocess/preprocess_validation_text_embeddings.py \
--model_type $MODEL_TYPE \
--model_path $MODEL_PATH \
--output_dir=$OUTPUT_DIR \
--validation_prompt_txt $VALIDATION_PATH
scripts/preprocess/v0/preprocess_mochi_data.sh
-33
View File
@@ -1,33 +0,0 @@
# export WANDB_MODE="offline"
GPU_NUM=1 # 2,4,8
MODEL_PATH="data/FastMochi-diffusers"
MODEL_TYPE="mochi"
DATA_MERGE_PATH="data/Image-Vid-Finetune-Src/merge.txt"
OUTPUT_DIR="data/Image-Vid-Finetune-Mochi"
VALIDATION_PATH="assets/prompt.txt"
torchrun --nproc_per_node=$GPU_NUM \
fastvideo/data_preprocess/preprocess_vae_latents.py \
--model_path $MODEL_PATH \
--data_merge_path $DATA_MERGE_PATH \
--train_batch_size=1 \
--max_height=480 \
--max_width=848 \
--num_frames=93 \
--dataloader_num_workers 1 \
--output_dir=$OUTPUT_DIR \
--model_type $MODEL_TYPE \
--train_fps 24
torchrun --nproc_per_node=$GPU_NUM \
fastvideo/data_preprocess/preprocess_text_embeddings.py \
--model_type $MODEL_TYPE \
--model_path $MODEL_PATH \
--output_dir=$OUTPUT_DIR
torchrun --nproc_per_node=1 \
fastvideo/data_preprocess/preprocess_validation_text_embeddings.py \
--model_type $MODEL_TYPE \
--model_path $MODEL_PATH \
--output_dir=$OUTPUT_DIR \
--validation_prompt_txt $VALIDATION_PATH
scripts/preprocess/v0/preprocess_wan_data.sh
-33
View File
@@ -1,33 +0,0 @@
# export WANDB_MODE="offline"
GPU_NUM=1 # 2,4,8
MODEL_PATH="data/wan-diffusers"
MODEL_TYPE="wan"
DATA_MERGE_PATH="data/Image-Vid-Finetune-Src/merge.txt"
OUTPUT_DIR="data/Image-Vid-Finetune-Wan"
VALIDATION_PATH="assets/prompt.txt"
torchrun --nproc_per_node=$GPU_NUM \
fastvideo/data_preprocess/preprocess_vae_latents.py \
--model_path $MODEL_PATH \
--data_merge_path $DATA_MERGE_PATH \
--train_batch_size=1 \
--max_height=480 \
--max_width=848 \
--num_frames=81 \
--dataloader_num_workers 1 \
--output_dir=$OUTPUT_DIR \
--model_type $MODEL_TYPE \
--train_fps 24
torchrun --nproc_per_node=$GPU_NUM \
fastvideo/data_preprocess/preprocess_text_embeddings.py \
--model_type $MODEL_TYPE \
--model_path $MODEL_PATH \
--output_dir=$OUTPUT_DIR
torchrun --nproc_per_node=1 \
fastvideo/data_preprocess/preprocess_validation_text_embeddings.py \
--model_type $MODEL_TYPE \
--model_path $MODEL_PATH \
--output_dir=$OUTPUT_DIR \
--validation_prompt_txt $VALIDATION_PATH