Spaces:
Running on Zero
Running on Zero
File size: 2,693 Bytes
c94e874 | 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 | #
# For licensing see accompanying LICENSE file.
# Copyright (C) 2026 Apple Inc. All Rights Reserved.
#
"""Checkpoint loading for Wan backbones, FastFrames generators and their add-on networks."""
from __future__ import annotations
import json
from pathlib import Path
import torch
from .wan.causal_model import CausalWanModel
from .wan.model import WAN_CONFIGS, WanModel
__all__ = ["load_state_dict", "build_wan", "load_wan_base"]
_PREFIXES = ("model._fsdp_wrapped_module.", "_fsdp_wrapped_module.", "model.")
def load_state_dict(path, key=None):
"""Tensor state from ``.safetensors`` (a file, or the ``.safetensors.index.json`` of a sharded
file) or a torch pickle (optionally nested under ``key``)."""
path = Path(path)
if path.name.endswith(".safetensors.index.json"):
from safetensors.torch import load_file
state = {}
for name in sorted(set(json.loads(path.read_text())["weight_map"].values())):
state.update(load_file(str(path.parent / name)))
elif path.suffix == ".safetensors":
from safetensors.torch import load_file
state = load_file(str(path))
else:
state = torch.load(path, map_location="cpu", mmap=True, weights_only=True)
if key is not None:
state = state[key]
return {_strip(k): v for k, v in state.items()}
def _strip(name):
for prefix in _PREFIXES:
if name.startswith(prefix):
return name[len(prefix):]
return name
def build_wan(name, state_dict, *, causal=True, dtype=torch.bfloat16, device="cuda"):
"""Instantiate a (causal) Wan2.1 transformer without materialising random weights."""
cls = CausalWanModel if causal else WanModel
with torch.device("meta"):
model = cls(WAN_CONFIGS[name])
model.load_state_dict(state_dict, strict=True, assign=True)
return model.to(device=device, dtype=dtype).eval().requires_grad_(False)
def load_wan_base(wan_dir, *, causal=False, dtype=torch.bfloat16, device="cuda"):
"""Load the released Wan2.1 weights (``diffusion_pytorch_model*.safetensors``)."""
from safetensors.torch import load_file
wan_dir = Path(wan_dir)
index = wan_dir / "diffusion_pytorch_model.safetensors.index.json"
files = (sorted(set(json.loads(index.read_text())["weight_map"].values())) if index.exists()
else ["diffusion_pytorch_model.safetensors"])
state = {}
for name in files:
state.update(load_file(str(wan_dir / name)))
config = json.loads((wan_dir / "config.json").read_text())
name = "Wan2.1-T2V-14B" if config["dim"] == 5120 else "Wan2.1-T2V-1.3B"
return build_wan(name, state, causal=causal, dtype=dtype, device=device)
|