220 lines
8.7 KiB
Python
220 lines
8.7 KiB
Python
import os
|
|
import sys
|
|
|
|
import numpy as np
|
|
import torch
|
|
from diffusers import FlowMatchEulerDiscreteScheduler
|
|
from PIL import Image
|
|
|
|
current_file_path = os.path.abspath(__file__)
|
|
project_roots = [os.path.dirname(current_file_path), os.path.dirname(os.path.dirname(current_file_path)), os.path.dirname(os.path.dirname(os.path.dirname(current_file_path)))]
|
|
for project_root in project_roots:
|
|
sys.path.insert(0, project_root) if project_root not in sys.path else None
|
|
|
|
from videox_fun.dist import set_multi_gpus_devices, shard_model
|
|
from videox_fun.models import (AutoencoderKLLongCatVideo, AutoTokenizer,
|
|
LongCatVideoTransformer3DModel,
|
|
UMT5EncoderModel)
|
|
from videox_fun.pipeline import LongCatVideoPipeline
|
|
from videox_fun.utils import (FlowDPMSolverMultistepScheduler,
|
|
FlowUniPCMultistepScheduler,
|
|
apply_gpu_memory_mode, merge_lora,
|
|
save_videos_grid, unmerge_lora)
|
|
|
|
# GPU memory mode, which can be chosen in [model_full_load, model_full_load_and_qfloat8, model_cpu_offload, model_cpu_offload_and_qfloat8, model_group_offload, sequential_cpu_offload].
|
|
# model_full_load means that the entire model will be moved to the GPU.
|
|
#
|
|
# model_full_load_and_qfloat8 means that the entire model will be moved to the GPU,
|
|
# and the transformer model has been quantized to float8, which can save more GPU memory.
|
|
#
|
|
# model_cpu_offload means that the entire model will be moved to the CPU after use, which can save some GPU memory.
|
|
#
|
|
# model_cpu_offload_and_qfloat8 indicates that the entire model will be moved to the CPU after use,
|
|
# and the transformer model has been quantized to float8, which can save more GPU memory.
|
|
#
|
|
# model_group_offload transfers internal layer groups between CPU/CUDA,
|
|
# balancing memory efficiency and speed between full-module and leaf-level offloading methods.
|
|
#
|
|
# sequential_cpu_offload means that each layer of the model will be moved to the CPU after use,
|
|
# resulting in slower speeds but saving a large amount of GPU memory.
|
|
GPU_memory_mode = "model_group_offload"
|
|
# Multi GPUs config
|
|
# Please ensure that the product of ulysses_degree and ring_degree equals the number of GPUs used.
|
|
# For example, if you are using 8 GPUs, you can set ulysses_degree = 2 and ring_degree = 4.
|
|
# If you are using 1 GPU, you can set ulysses_degree = 1 and ring_degree = 1.
|
|
ulysses_degree = 1
|
|
ring_degree = 1
|
|
# Use FSDP to save more GPU memory in multi gpus.
|
|
fsdp_dit = False
|
|
fsdp_text_encoder = True
|
|
# Compile will give a speedup in fixed resolution and need a little GPU memory.
|
|
# The compile_dit is not compatible with the fsdp_dit and sequential_cpu_offload.
|
|
compile_dit = False
|
|
|
|
# model path
|
|
model_name = "models/Diffusion_Transformer/LongCat-Video"
|
|
|
|
# Choose the sampler in "Flow", "Flow_Unipc", "Flow_DPM++"
|
|
sampler_name = "Flow"
|
|
|
|
# Load pretrained model if need
|
|
transformer_path = None
|
|
vae_path = None
|
|
lora_path = None
|
|
|
|
# Other params
|
|
sample_size = [832, 480]
|
|
video_length = 81
|
|
fps = 16
|
|
|
|
# Use torch.float16 if GPU does not support torch.bfloat16
|
|
# Some graphics cards, such as v100, 2080ti, do not support torch.bfloat16
|
|
weight_dtype = torch.bfloat16
|
|
# Prompt
|
|
prompt = "1girl, black_hair, brown_eyes, earrings, freckles, grey_background, jewelry, lips, long_hair, looking_at_viewer, nose, piercing, realistic, red_lips, solo, upper_body"
|
|
negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards"
|
|
guidance_scale = 4.0
|
|
seed = 43
|
|
num_inference_steps = 25
|
|
lora_weight = 0.55
|
|
save_path = "samples/longcat-videos-t2v"
|
|
|
|
device = set_multi_gpus_devices(ulysses_degree, ring_degree)
|
|
|
|
transformer = LongCatVideoTransformer3DModel.from_pretrained(
|
|
os.path.join(model_name, "dit"),
|
|
low_cpu_mem_usage=True,
|
|
torch_dtype=weight_dtype, cp_split_hw=[1, 1]
|
|
)
|
|
|
|
if transformer_path is not None:
|
|
print(f"From checkpoint: {transformer_path}")
|
|
if transformer_path.endswith("safetensors"):
|
|
from safetensors.torch import load_file
|
|
state_dict = load_file(transformer_path)
|
|
else:
|
|
state_dict = torch.load(transformer_path, map_location="cpu")
|
|
state_dict = state_dict["state_dict"] if "state_dict" in state_dict else state_dict
|
|
|
|
m, u = transformer.load_state_dict(state_dict, strict=False)
|
|
print(f"missing keys: {len(m)}, unexpected keys: {len(u)}")
|
|
|
|
# Get Vae
|
|
vae = AutoencoderKLLongCatVideo.from_pretrained(
|
|
os.path.join(model_name, "vae"),
|
|
).to(weight_dtype)
|
|
|
|
if vae_path is not None:
|
|
print(f"From checkpoint: {vae_path}")
|
|
if vae_path.endswith("safetensors"):
|
|
from safetensors.torch import load_file
|
|
state_dict = load_file(vae_path)
|
|
else:
|
|
state_dict = torch.load(vae_path, map_location="cpu")
|
|
state_dict = state_dict["state_dict"] if "state_dict" in state_dict else state_dict
|
|
|
|
m, u = vae.load_state_dict(state_dict, strict=False)
|
|
print(f"missing keys: {len(m)}, unexpected keys: {len(u)}")
|
|
|
|
# Get Tokenizer
|
|
tokenizer = AutoTokenizer.from_pretrained(
|
|
os.path.join(model_name, "tokenizer"),
|
|
)
|
|
|
|
# Get Text encoder
|
|
text_encoder = UMT5EncoderModel.from_pretrained(
|
|
os.path.join(model_name, "text_encoder"),
|
|
low_cpu_mem_usage=True,
|
|
torch_dtype=weight_dtype,
|
|
)
|
|
|
|
# Get Scheduler
|
|
Chosen_Scheduler = {
|
|
"Flow": FlowMatchEulerDiscreteScheduler,
|
|
"Flow_Unipc": FlowUniPCMultistepScheduler,
|
|
"Flow_DPM++": FlowDPMSolverMultistepScheduler,
|
|
}[sampler_name]
|
|
scheduler = Chosen_Scheduler.from_pretrained(
|
|
model_name,
|
|
subfolder="scheduler"
|
|
)
|
|
|
|
# Get Pipeline
|
|
pipeline = LongCatVideoPipeline(
|
|
transformer=transformer,
|
|
vae=vae,
|
|
tokenizer=tokenizer,
|
|
text_encoder=text_encoder,
|
|
scheduler=scheduler,
|
|
)
|
|
|
|
if ulysses_degree > 1 or ring_degree > 1:
|
|
from functools import partial
|
|
transformer.enable_multi_gpus_inference()
|
|
if fsdp_dit:
|
|
shard_fn = partial(shard_model, device_id=device, param_dtype=weight_dtype)
|
|
pipeline.transformer = shard_fn(pipeline.transformer)
|
|
print("Add FSDP DIT")
|
|
if fsdp_text_encoder:
|
|
shard_fn = partial(shard_model, device_id=device, param_dtype=weight_dtype, module_to_wrapper=text_encoder.encoder.block)
|
|
pipeline.text_encoder = shard_fn(pipeline.text_encoder)
|
|
print("Add FSDP TEXT ENCODER")
|
|
|
|
if compile_dit:
|
|
for i in range(len(pipeline.transformer.blocks)):
|
|
pipeline.transformer.blocks[i] = torch.compile(pipeline.transformer.blocks[i])
|
|
print("Add Compile")
|
|
|
|
# Quantize (when the mode carries an "_and_<quant>" suffix) and then place the pipeline.
|
|
# The order lives inside the helper: quantization has to happen before the offload hooks
|
|
# are installed.
|
|
apply_gpu_memory_mode(pipeline, GPU_memory_mode, device, weight_dtype)
|
|
|
|
generator = torch.Generator(device=device).manual_seed(seed)
|
|
|
|
if lora_path is not None:
|
|
pipeline = merge_lora(pipeline, lora_path, lora_weight, device=device, dtype=weight_dtype)
|
|
|
|
with torch.no_grad():
|
|
video_length = int((video_length - 1) // vae.scale_factor_temporal * vae.scale_factor_temporal) + 1 if video_length != 1 else 1
|
|
latent_frames = (video_length - 1) // vae.scale_factor_temporal + 1
|
|
|
|
sample = pipeline(
|
|
prompt,
|
|
num_frames = video_length,
|
|
negative_prompt = negative_prompt,
|
|
height = sample_size[0],
|
|
width = sample_size[1],
|
|
generator = generator,
|
|
guidance_scale = guidance_scale,
|
|
num_inference_steps = num_inference_steps,
|
|
).videos
|
|
|
|
if lora_path is not None:
|
|
pipeline = unmerge_lora(pipeline, lora_path, lora_weight, device=device, dtype=weight_dtype)
|
|
|
|
def save_results():
|
|
if not os.path.exists(save_path):
|
|
os.makedirs(save_path, exist_ok=True)
|
|
|
|
index = len([path for path in os.listdir(save_path)]) + 1
|
|
prefix = str(index).zfill(8)
|
|
if video_length == 1:
|
|
video_path = os.path.join(save_path, prefix + ".png")
|
|
|
|
image = sample[0, :, 0]
|
|
image = image.transpose(0, 1).transpose(1, 2)
|
|
image = (image * 255).numpy().astype(np.uint8)
|
|
image = Image.fromarray(image)
|
|
image.save(video_path)
|
|
print(f"Saved image to: {video_path}")
|
|
else:
|
|
video_path = os.path.join(save_path, prefix + ".mp4")
|
|
save_videos_grid(sample, video_path, fps=fps)
|
|
|
|
if ulysses_degree * ring_degree > 1:
|
|
import torch.distributed as dist
|
|
if dist.get_rank() == 0:
|
|
save_results()
|
|
else:
|
|
save_results() |