Spaces:
Running
Running
File size: 7,347 Bytes
3964763 ddacd23 3964763 ddacd23 3964763 ddacd23 3964763 ddacd23 3964763 ddacd23 3964763 ddacd23 3964763 ddacd23 3964763 ddacd23 3964763 ddacd23 3964763 ddacd23 3964763 ddacd23 3964763 ddacd23 3964763 ddacd23 3964763 ddacd23 3964763 ddacd23 |
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 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 |
def generate(args):
rank = int(os.getenv("RANK", 0))
world_size = int(os.getenv("WORLD_SIZE", 1))
local_rank = int(os.getenv("LOCAL_RANK", 0))
# Set device: use CPU if specified, else use GPU based on rank
if args.t5_cpu or args.dit_fsdp: # Use CPU if specified in arguments
device = torch.device("cpu")
logging.info("Using CPU for model inference.")
else:
device = local_rank
torch.cuda.set_device(local_rank) # Ensure proper device assignment if using GPU
logging.info(f"Using GPU: {device}")
_init_logging(rank)
# Distributed setup
if world_size > 1:
dist.init_process_group(
backend="nccl",
init_method="env://",
rank=rank,
world_size=world_size)
else:
assert not (
args.t5_fsdp or args.dit_fsdp
), f"t5_fsdp and dit_fsdp are not supported in non-distributed environments."
if args.ulysses_size > 1 or args.ring_size > 1:
assert args.ulysses_size * args.ring_size == world_size, f"The number of ulysses_size and ring_size should be equal to the world size."
from xfuser.core.distributed import (initialize_model_parallel,
init_distributed_environment)
init_distributed_environment(
rank=dist.get_rank(), world_size=dist.get_world_size())
initialize_model_parallel(
sequence_parallel_degree=dist.get_world_size(),
ring_degree=args.ring_size,
ulysses_degree=args.ulysses_size,
)
# Handle prompt extension if needed
if args.use_prompt_extend:
if args.prompt_extend_method == "dashscope":
prompt_expander = DashScopePromptExpander(
model_name=args.prompt_extend_model, is_vl="i2v" in args.task)
elif args.prompt_extend_method == "local_qwen":
prompt_expander = QwenPromptExpander(
model_name=args.prompt_extend_model,
is_vl="i2v" in args.task,
device=rank)
else:
raise NotImplementedError(f"Unsupported prompt_extend_method: {args.prompt_extend_method}")
cfg = WAN_CONFIGS[args.task]
logging.info(f"Generation job args: {args}")
logging.info(f"Generation model config: {cfg}")
# Broadcast base seed across distributed workers
if dist.is_initialized():
base_seed = [args.base_seed] if rank == 0 else [None]
dist.broadcast_object_list(base_seed, src=0)
args.base_seed = base_seed[0]
# Set prompt and task details
if "t2v" in args.task or "t2i" in args.task:
if args.prompt is None:
args.prompt = EXAMPLE_PROMPT[args.task]["prompt"]
logging.info(f"Input prompt: {args.prompt}")
if args.use_prompt_extend:
logging.info("Extending prompt ...")
if rank == 0:
prompt_output = prompt_expander(
args.prompt,
tar_lang=args.prompt_extend_target_lang,
seed=args.base_seed)
if prompt_output.status == False:
logging.info(f"Prompt extension failed: {prompt_output.message}")
input_prompt = args.prompt
else:
input_prompt = prompt_output.prompt
else:
input_prompt = [None]
if dist.is_initialized():
dist.broadcast_object_list(input_prompt, src=0)
args.prompt = input_prompt[0]
logging.info(f"Extended prompt: {args.prompt}")
logging.info("Creating WanT2V pipeline.")
wan_t2v = wan.WanT2V(
config=cfg,
checkpoint_dir=args.ckpt_dir,
device_id=device,
rank=rank,
t5_fsdp=args.t5_fsdp,
dit_fsdp=args.dit_fsdp,
use_usp=(args.ulysses_size > 1 or args.ring_size > 1),
t5_cpu=args.t5_cpu,
)
logging.info(f"Generating {'image' if 't2i' in args.task else 'video'} ...")
video = wan_t2v.generate(
args.prompt,
size=SIZE_CONFIGS[args.size],
frame_num=args.frame_num,
shift=args.sample_shift,
sample_solver=args.sample_solver,
sampling_steps=args.sample_steps,
guide_scale=args.sample_guide_scale,
seed=args.base_seed,
offload_model=args.offload_model)
else: # image-to-video
if args.prompt is None:
args.prompt = EXAMPLE_PROMPT[args.task]["prompt"]
if args.image is None:
args.image = EXAMPLE_PROMPT[args.task]["image"]
logging.info(f"Input prompt: {args.prompt}")
logging.info(f"Input image: {args.image}")
img = Image.open(args.image).convert("RGB")
if args.use_prompt_extend:
logging.info("Extending prompt ...")
if rank == 0:
prompt_output = prompt_expander(
args.prompt,
tar_lang=args.prompt_extend_target_lang,
image=img,
seed=args.base_seed)
if prompt_output.status == False:
logging.info(f"Prompt extension failed: {prompt_output.message}")
input_prompt = args.prompt
else:
input_prompt = prompt_output.prompt
else:
input_prompt = [None]
if dist.is_initialized():
dist.broadcast_object_list(input_prompt, src=0)
args.prompt = input_prompt[0]
logging.info(f"Extended prompt: {args.prompt}")
logging.info("Creating WanI2V pipeline.")
wan_i2v = wan.WanI2V(
config=cfg,
checkpoint_dir=args.ckpt_dir,
device_id=device,
rank=rank,
t5_fsdp=args.t5_fsdp,
dit_fsdp=args.dit_fsdp,
use_usp=(args.ulysses_size > 1 or args.ring_size > 1),
t5_cpu=args.t5_cpu,
)
logging.info("Generating video ...")
video = wan_i2v.generate(
args.prompt,
img,
max_area=MAX_AREA_CONFIGS[args.size],
frame_num=args.frame_num,
shift=args.sample_shift,
sample_solver=args.sample_solver,
sampling_steps=args.sample_steps,
guide_scale=args.sample_guide_scale,
seed=args.base_seed,
offload_model=args.offload_model)
# Save the output video or image
if rank == 0:
if args.save_file is None:
formatted_time = datetime.now().strftime("%Y%m%d_%H%M%S")
formatted_prompt = args.prompt.replace(" ", "_").replace("/", "_")[:50]
suffix = '.png' if "t2i" in args.task else '.mp4'
args.save_file = f"{args.task}_{args.size}_{args.ulysses_size}_{args.ring_size}_{formatted_prompt}_{formatted_time}" + suffix
if "t2i" in args.task:
logging.info(f"Saving generated image to {args.save_file}")
cache_image(tensor=video.squeeze(1)[None], save_file=args.save_file, nrow=1, normalize=True)
else:
logging.info(f"Saving generated video to {args.save_file}")
cache_video(tensor=video, save_file=args.save_file)
|