wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-12-21 03:50:50 +08:00
Code Issues Actions 8 Packages Projects Releases Wiki Activity

Check state dict key to auto enable the index_timestep_zero ref method. (#11362)
Some checks are pending
Python Linting / Run Ruff (push) Waiting to run
Details
Python Linting / Run Pylint (push) Waiting to run
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.10, [self-hosted Linux], stable) (push) Waiting to run
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.11, [self-hosted Linux], stable) (push) Waiting to run
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.12, [self-hosted Linux], stable) (push) Waiting to run
Details
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, , linux, 3.11, [self-hosted Linux], nightly) (push) Waiting to run
Details
Execution Tests / test (macos-latest) (push) Waiting to run
Details
Execution Tests / test (ubuntu-latest) (push) Waiting to run
Details
Execution Tests / test (windows-latest) (push) Waiting to run
Details
Test server launches without errors / test (push) Waiting to run
Details
Unit Tests / test (macos-latest) (push) Waiting to run
Details
Unit Tests / test (ubuntu-latest) (push) Waiting to run
Details
Unit Tests / test (windows-2022) (push) Waiting to run
Details

Browse Source
This commit is contained in:
comfyanonymous 2025-12-16 14:03:17 -08:00 committed by GitHub
parent 65e2103b09
commit ffdd53b327
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
comfy/ldm/qwen_image/model.py
View File

@ -363,6 +363,9 @@ class QwenImageTransformer2DModel(nn.Module):
for _ in range(num_layers) for _ in range(num_layers)
]) ])
if self.default_ref_method == "index_timestep_zero":
self.register_buffer("__index_timestep_zero__", torch.tensor([]))
if final_layer: if final_layer:
self.norm_out = LastLayer(self.inner_dim, self.inner_dim, dtype=dtype, device=device, operations=operations) self.norm_out = LastLayer(self.inner_dim, self.inner_dim, dtype=dtype, device=device, operations=operations)
self.proj_out = operations.Linear(self.inner_dim, patch_size * patch_size * self.out_channels, bias=True, dtype=dtype, device=device) self.proj_out = operations.Linear(self.inner_dim, patch_size * patch_size * self.out_channels, bias=True, dtype=dtype, device=device)

4
comfy/model_detection.py
View File

@ -259,7 +259,7 @@ def detect_unet_config(state_dict, key_prefix, metadata=None):
dit_config["nerf_tile_size"] = 512 dit_config["nerf_tile_size"] = 512
dit_config["nerf_final_head_type"] = "conv" if f"{key_prefix}nerf_final_layer_conv.norm.scale" in state_dict_keys else "linear" dit_config["nerf_final_head_type"] = "conv" if f"{key_prefix}nerf_final_layer_conv.norm.scale" in state_dict_keys else "linear"
dit_config["nerf_embedder_dtype"] = torch.float32 dit_config["nerf_embedder_dtype"] = torch.float32
if "__x0__" in state_dict_keys: # x0 pred if "{}__x0__".format(key_prefix) in state_dict_keys: # x0 pred
dit_config["use_x0"] = True dit_config["use_x0"] = True
else: else:
dit_config["use_x0"] = False dit_config["use_x0"] = False
@ -618,6 +618,8 @@ def detect_unet_config(state_dict, key_prefix, metadata=None):
dit_config["image_model"] = "qwen_image" dit_config["image_model"] = "qwen_image"
dit_config["in_channels"] = state_dict['{}img_in.weight'.format(key_prefix)].shape[1] dit_config["in_channels"] = state_dict['{}img_in.weight'.format(key_prefix)].shape[1]
dit_config["num_layers"] = count_blocks(state_dict_keys, '{}transformer_blocks.'.format(key_prefix) + '{}.') dit_config["num_layers"] = count_blocks(state_dict_keys, '{}transformer_blocks.'.format(key_prefix) + '{}.')
if "{}__index_timestep_zero__".format(key_prefix) in state_dict_keys: # 2511
dit_config["default_ref_method"] = "index_timestep_zero"
return dit_config return dit_config
if '{}visual_transformer_blocks.0.cross_attention.key_norm.weight'.format(key_prefix) in state_dict_keys: # Kandinsky 5 if '{}visual_transformer_blocks.0.cross_attention.key_norm.weight'.format(key_prefix) in state_dict_keys: # Kandinsky 5