mirror of
https://github.com/comfyanonymous/ComfyUI.git
synced 2026-02-16 08:22:36 +08:00
292 lines
12 KiB
Python
292 lines
12 KiB
Python
|
|
def assign_to_checkpoint(
|
|
paths, checkpoint, old_checkpoint, additional_replacements=None
|
|
):
|
|
"""
|
|
This does the final conversion step: take locally converted weights and apply a global renaming to them. It splits
|
|
attention layers, and takes into account additional replacements that may arise.
|
|
|
|
Assigns the weights to the new checkpoint.
|
|
"""
|
|
assert isinstance(paths, list), "Paths should be a list of dicts containing 'old' and 'new' keys."
|
|
|
|
for path in paths:
|
|
new_path = path["new"]
|
|
|
|
# Global renaming happens here
|
|
new_path = new_path.replace("middle_block.0", "mid_block.resnets.0")
|
|
new_path = new_path.replace("middle_block.1", "mid_block.attentions.0")
|
|
new_path = new_path.replace("middle_block.2", "mid_block.resnets.1")
|
|
|
|
if additional_replacements is not None:
|
|
for replacement in additional_replacements:
|
|
new_path = new_path.replace(replacement["old"], replacement["new"])
|
|
|
|
# proj_attn.weight has to be converted from conv 1D to linear
|
|
if "proj_attn.weight" in new_path:
|
|
checkpoint[new_path] = old_checkpoint[path["old"]][:, :, 0]
|
|
else:
|
|
checkpoint[new_path] = old_checkpoint[path["old"]]
|
|
|
|
|
|
def conv_attn_to_linear(checkpoint):
|
|
keys = list(checkpoint.keys())
|
|
attn_keys = ["query.weight", "key.weight", "value.weight"]
|
|
for key in keys:
|
|
if ".".join(key.split(".")[-2:]) in attn_keys:
|
|
if checkpoint[key].ndim > 2:
|
|
checkpoint[key] = checkpoint[key][:, :, 0, 0]
|
|
elif "proj_attn.weight" in key:
|
|
if checkpoint[key].ndim > 2:
|
|
checkpoint[key] = checkpoint[key][:, :, 0]
|
|
|
|
|
|
def renew_attention_paths(old_list, n_shave_prefix_segments=0):
|
|
"""
|
|
Updates paths inside attentions to the new naming scheme (local renaming)
|
|
"""
|
|
mapping = []
|
|
for old_item in old_list:
|
|
new_item = old_item
|
|
|
|
# new_item = new_item.replace('norm.weight', 'group_norm.weight')
|
|
# new_item = new_item.replace('norm.bias', 'group_norm.bias')
|
|
|
|
# new_item = new_item.replace('proj_out.weight', 'proj_attn.weight')
|
|
# new_item = new_item.replace('proj_out.bias', 'proj_attn.bias')
|
|
|
|
# new_item = shave_segments(new_item, n_shave_prefix_segments=n_shave_prefix_segments)
|
|
|
|
mapping.append({"old": old_item, "new": new_item})
|
|
|
|
return mapping
|
|
|
|
def shave_segments(path, n_shave_prefix_segments=1):
|
|
"""
|
|
Removes segments. Positive values shave the first segments, negative shave the last segments.
|
|
"""
|
|
if n_shave_prefix_segments >= 0:
|
|
return ".".join(path.split(".")[n_shave_prefix_segments:])
|
|
else:
|
|
return ".".join(path.split(".")[:n_shave_prefix_segments])
|
|
|
|
|
|
def renew_resnet_paths(old_list, n_shave_prefix_segments=0):
|
|
"""
|
|
Updates paths inside resnets to the new naming scheme (local renaming)
|
|
"""
|
|
mapping = []
|
|
for old_item in old_list:
|
|
new_item = old_item.replace("in_layers.0", "norm1")
|
|
new_item = new_item.replace("in_layers.2", "conv1")
|
|
|
|
new_item = new_item.replace("out_layers.0", "norm2")
|
|
new_item = new_item.replace("out_layers.3", "conv2")
|
|
|
|
new_item = new_item.replace("emb_layers.1", "time_emb_proj")
|
|
new_item = new_item.replace("skip_connection", "conv_shortcut")
|
|
|
|
new_item = shave_segments(new_item, n_shave_prefix_segments=n_shave_prefix_segments)
|
|
|
|
mapping.append({"old": old_item, "new": new_item})
|
|
|
|
return mapping
|
|
|
|
def convert_ldm_unet_checkpoint(unet_state_dict, layers_per_block=2, controlnet=False):
|
|
"""
|
|
Takes a state dict and a config, and returns a converted checkpoint.
|
|
"""
|
|
temp = {}
|
|
if controlnet:
|
|
unet_key = "control_model."
|
|
else:
|
|
unet_key = "model.diffusion_model."
|
|
|
|
for key, value in unet_state_dict.items():
|
|
if key.startswith(unet_key):
|
|
key = key.replace(unet_key, "")
|
|
temp[key] = value
|
|
unet_state_dict = temp
|
|
new_checkpoint = {}
|
|
|
|
new_checkpoint["time_embedding.linear_1.weight"] = unet_state_dict["time_embed.0.weight"]
|
|
new_checkpoint["time_embedding.linear_1.bias"] = unet_state_dict["time_embed.0.bias"]
|
|
new_checkpoint["time_embedding.linear_2.weight"] = unet_state_dict["time_embed.2.weight"]
|
|
new_checkpoint["time_embedding.linear_2.bias"] = unet_state_dict["time_embed.2.bias"]
|
|
|
|
new_checkpoint["conv_in.weight"] = unet_state_dict["input_blocks.0.0.weight"]
|
|
new_checkpoint["conv_in.bias"] = unet_state_dict["input_blocks.0.0.bias"]
|
|
if not controlnet:
|
|
new_checkpoint["conv_norm_out.weight"] = unet_state_dict["out.0.weight"]
|
|
new_checkpoint["conv_norm_out.bias"] = unet_state_dict["out.0.bias"]
|
|
new_checkpoint["conv_out.weight"] = unet_state_dict["out.2.weight"]
|
|
new_checkpoint["conv_out.bias"] = unet_state_dict["out.2.bias"]
|
|
|
|
# Retrieves the keys for the input blocks only
|
|
num_input_blocks = len({".".join(layer.split(".")[:2]) for layer in unet_state_dict if "input_blocks" in layer})
|
|
input_blocks = {
|
|
layer_id: [key for key in unet_state_dict if f"input_blocks.{layer_id}" in key]
|
|
for layer_id in range(num_input_blocks)
|
|
}
|
|
|
|
# Retrieves the keys for the middle blocks only
|
|
num_middle_blocks = len({".".join(layer.split(".")[:2]) for layer in unet_state_dict if "middle_block" in layer})
|
|
middle_blocks = {
|
|
layer_id: [key for key in unet_state_dict if f"middle_block.{layer_id}" in key]
|
|
for layer_id in range(num_middle_blocks)
|
|
}
|
|
|
|
# Retrieves the keys for the output blocks only
|
|
num_output_blocks = len({".".join(layer.split(".")[:2]) for layer in unet_state_dict if "output_blocks" in layer})
|
|
output_blocks = {
|
|
layer_id: [key for key in unet_state_dict if f"output_blocks.{layer_id}" in key]
|
|
for layer_id in range(num_output_blocks)
|
|
}
|
|
|
|
for i in range(1, num_input_blocks):
|
|
block_id = (i - 1) // (layers_per_block + 1)
|
|
layer_in_block_id = (i - 1) % (layers_per_block + 1)
|
|
|
|
resnets = [
|
|
key for key in input_blocks[i] if f"input_blocks.{i}.0" in key and f"input_blocks.{i}.0.op" not in key
|
|
]
|
|
attentions = [key for key in input_blocks[i] if f"input_blocks.{i}.1" in key]
|
|
|
|
if f"input_blocks.{i}.0.op.weight" in unet_state_dict:
|
|
new_checkpoint[f"down_blocks.{block_id}.downsamplers.0.conv.weight"] = unet_state_dict.pop(
|
|
f"input_blocks.{i}.0.op.weight"
|
|
)
|
|
new_checkpoint[f"down_blocks.{block_id}.downsamplers.0.conv.bias"] = unet_state_dict.pop(
|
|
f"input_blocks.{i}.0.op.bias"
|
|
)
|
|
|
|
paths = renew_resnet_paths(resnets)
|
|
meta_path = {"old": f"input_blocks.{i}.0", "new": f"down_blocks.{block_id}.resnets.{layer_in_block_id}"}
|
|
assign_to_checkpoint(
|
|
paths, new_checkpoint, unet_state_dict, additional_replacements=[meta_path]
|
|
)
|
|
|
|
if len(attentions):
|
|
paths = renew_attention_paths(attentions)
|
|
meta_path = {"old": f"input_blocks.{i}.1", "new": f"down_blocks.{block_id}.attentions.{layer_in_block_id}"}
|
|
assign_to_checkpoint(
|
|
paths, new_checkpoint, unet_state_dict, additional_replacements=[meta_path]
|
|
)
|
|
|
|
resnet_0 = middle_blocks[0]
|
|
attentions = middle_blocks[1]
|
|
resnet_1 = middle_blocks[2]
|
|
|
|
resnet_0_paths = renew_resnet_paths(resnet_0)
|
|
assign_to_checkpoint(resnet_0_paths, new_checkpoint, unet_state_dict)
|
|
|
|
resnet_1_paths = renew_resnet_paths(resnet_1)
|
|
assign_to_checkpoint(resnet_1_paths, new_checkpoint, unet_state_dict)
|
|
|
|
attentions_paths = renew_attention_paths(attentions)
|
|
meta_path = {"old": "middle_block.1", "new": "mid_block.attentions.0"}
|
|
assign_to_checkpoint(
|
|
attentions_paths, new_checkpoint, unet_state_dict, additional_replacements=[meta_path]
|
|
)
|
|
|
|
for i in range(num_output_blocks):
|
|
block_id = i // (layers_per_block + 1)
|
|
layer_in_block_id = i % (layers_per_block + 1)
|
|
output_block_layers = [shave_segments(name, 2) for name in output_blocks[i]]
|
|
output_block_list = {}
|
|
|
|
for layer in output_block_layers:
|
|
layer_id, layer_name = layer.split(".")[0], shave_segments(layer, 1)
|
|
if layer_id in output_block_list:
|
|
output_block_list[layer_id].append(layer_name)
|
|
else:
|
|
output_block_list[layer_id] = [layer_name]
|
|
|
|
if len(output_block_list) > 1:
|
|
resnets = [key for key in output_blocks[i] if f"output_blocks.{i}.0" in key]
|
|
attentions = [key for key in output_blocks[i] if f"output_blocks.{i}.1" in key]
|
|
|
|
resnet_0_paths = renew_resnet_paths(resnets)
|
|
paths = renew_resnet_paths(resnets)
|
|
|
|
meta_path = {"old": f"output_blocks.{i}.0", "new": f"up_blocks.{block_id}.resnets.{layer_in_block_id}"}
|
|
assign_to_checkpoint(
|
|
paths, new_checkpoint, unet_state_dict, additional_replacements=[meta_path]
|
|
)
|
|
|
|
output_block_list = {k: sorted(v) for k, v in output_block_list.items()}
|
|
if ["conv.bias", "conv.weight"] in output_block_list.values():
|
|
index = list(output_block_list.values()).index(["conv.bias", "conv.weight"])
|
|
new_checkpoint[f"up_blocks.{block_id}.upsamplers.0.conv.weight"] = unet_state_dict[
|
|
f"output_blocks.{i}.{index}.conv.weight"
|
|
]
|
|
new_checkpoint[f"up_blocks.{block_id}.upsamplers.0.conv.bias"] = unet_state_dict[
|
|
f"output_blocks.{i}.{index}.conv.bias"
|
|
]
|
|
|
|
# Clear attentions as they have been attributed above.
|
|
if len(attentions) == 2:
|
|
attentions = []
|
|
|
|
if len(attentions):
|
|
paths = renew_attention_paths(attentions)
|
|
meta_path = {
|
|
"old": f"output_blocks.{i}.1",
|
|
"new": f"up_blocks.{block_id}.attentions.{layer_in_block_id}",
|
|
}
|
|
assign_to_checkpoint(
|
|
paths, new_checkpoint, unet_state_dict, additional_replacements=[meta_path]
|
|
)
|
|
else:
|
|
resnet_0_paths = renew_resnet_paths(output_block_layers, n_shave_prefix_segments=1)
|
|
for path in resnet_0_paths:
|
|
old_path = ".".join(["output_blocks", str(i), path["old"]])
|
|
new_path = ".".join(["up_blocks", str(block_id), "resnets", str(layer_in_block_id), path["new"]])
|
|
|
|
new_checkpoint[new_path] = unet_state_dict[old_path]
|
|
|
|
if controlnet:
|
|
# conditioning embedding
|
|
|
|
orig_index = 0
|
|
|
|
new_checkpoint["controlnet_cond_embedding.conv_in.weight"] = unet_state_dict.pop(
|
|
f"input_hint_block.{orig_index}.weight"
|
|
)
|
|
new_checkpoint["controlnet_cond_embedding.conv_in.bias"] = unet_state_dict.pop(
|
|
f"input_hint_block.{orig_index}.bias"
|
|
)
|
|
|
|
orig_index += 2
|
|
|
|
diffusers_index = 0
|
|
|
|
while diffusers_index < 6:
|
|
new_checkpoint[f"controlnet_cond_embedding.blocks.{diffusers_index}.weight"] = unet_state_dict.pop(
|
|
f"input_hint_block.{orig_index}.weight"
|
|
)
|
|
new_checkpoint[f"controlnet_cond_embedding.blocks.{diffusers_index}.bias"] = unet_state_dict.pop(
|
|
f"input_hint_block.{orig_index}.bias"
|
|
)
|
|
diffusers_index += 1
|
|
orig_index += 2
|
|
|
|
new_checkpoint["controlnet_cond_embedding.conv_out.weight"] = unet_state_dict.pop(
|
|
f"input_hint_block.{orig_index}.weight"
|
|
)
|
|
new_checkpoint["controlnet_cond_embedding.conv_out.bias"] = unet_state_dict.pop(
|
|
f"input_hint_block.{orig_index}.bias"
|
|
)
|
|
|
|
# down blocks
|
|
for i in range(num_input_blocks):
|
|
new_checkpoint[f"controlnet_down_blocks.{i}.weight"] = unet_state_dict.pop(f"zero_convs.{i}.0.weight")
|
|
new_checkpoint[f"controlnet_down_blocks.{i}.bias"] = unet_state_dict.pop(f"zero_convs.{i}.0.bias")
|
|
|
|
# mid block
|
|
new_checkpoint["controlnet_mid_block.weight"] = unet_state_dict.pop("middle_block_out.0.weight")
|
|
new_checkpoint["controlnet_mid_block.bias"] = unet_state_dict.pop("middle_block_out.0.bias")
|
|
|
|
|
|
return new_checkpoint
|