theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-22 16:50:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

camera

Browse Source
This commit is contained in:
CD22104
2025-06-11 17:24:09 +08:00
parent 6e977e1181
commit b1afff1728
133 changed files with 954 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

53
diffsynth/models/wan_video_dit.py
View File

@@ -5,6 +5,10 @@ import math
from typing import Tuple, Optional
from einops import rearrange
from .utils import hash_state_dict_keys
from dchen.camera_adapter import SimpleAdapter
try:
import flash_attn_interface
FLASH_ATTN_3_AVAILABLE = True
@@ -273,6 +277,8 @@ class WanModel(torch.nn.Module):
has_image_input: bool,
has_image_pos_emb: bool = False,
has_ref_conv: bool = False,
add_control_adapter: bool = False,
in_dim_control_adapter: int = 24,
):
super().__init__()
self.dim = dim
@@ -309,8 +315,17 @@ class WanModel(torch.nn.Module):
self.has_image_pos_emb = has_image_pos_emb
self.has_ref_conv = has_ref_conv
def patchify(self, x: torch.Tensor):
if add_control_adapter:
self.control_adapter = SimpleAdapter(in_dim_control_adapter, dim, kernel_size=patch_size[1:], stride=patch_size[1:])
else:
self.control_adapter = None
def patchify(self, x: torch.Tensor, control_camera_latents_input: torch.Tensor = None):
x = self.patch_embedding(x)
if self.control_adapter is not None and control_camera_latents_input is not None:
y_camera = self.control_adapter(control_camera_latents_input)
x = [u + v for u, v in zip(x, y_camera)]
x = x[0].unsqueeze(0)
grid_size = x.shape[2:]
x = rearrange(x, 'b c f h w -> b (f h w) c').contiguous()
return x, grid_size # x, grid_size: (f, h, w)
@@ -612,6 +627,42 @@ class WanModelStateDictConverter:
"eps": 1e-6,
"has_ref_conv": True
}
elif hash_state_dict_keys(state_dict) == "ac6a5aa74f4a0aab6f64eb9a72f19901":
# 1.3B PAI control-camera v1.1
config = {
"has_image_input": True,
"patch_size": [1, 2, 2],
"in_dim": 32,
"dim": 1536,
"ffn_dim": 8960,
"freq_dim": 256,
"text_dim": 4096,
"out_dim": 16,
"num_heads": 12,
"num_layers": 30,
"eps": 1e-6,
"has_ref_conv": False,
"add_control_adapter": True,
"in_dim_control_adapter": 24,
}
elif hash_state_dict_keys(state_dict) == "b61c605c2adbd23124d152ed28e049ae":
# 14B PAI control-camera v1.1
config = {
"has_image_input": True,
"patch_size": [1, 2, 2],
"in_dim": 32,
"dim": 5120,
"ffn_dim": 13824,
"freq_dim": 256,
"text_dim": 4096,
"out_dim": 16,
"num_heads": 40,
"num_layers": 40,
"eps": 1e-6,
"has_ref_conv": False,
"add_control_adapter": True,
"in_dim_control_adapter": 24,
}
else:
config = {}
return state_dict, config