Skip to content

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

Remove useless code.

comfyanonymous14ca5f5a10ba
diff --git a/comfy/diffusers_convert.py b/comfy/diffusers_convert.py
index 26e8d96d5..fb9495348 100644
--- a/comfy/diffusers_convert.py
+++ b/comfy/diffusers_convert.py
@@ -4,105 +4,6 @@ import logging
# conversion code from https://github.com/huggingface/diffusers/blob/main/scripts/convert_diffusers_to_original_stable_diffusion.py
-# =================#
-# UNet Conversion #
-# =================#
-
-unet_conversion_map = [
- # (stable-diffusion, HF Diffusers)
- ("time_embed.0.weight", "time_embedding.linear_1.weight"),
- ("time_embed.0.bias", "time_embedding.linear_1.bias"),
- ("time_embed.2.weight", "time_embedding.linear_2.weight"),
- ("time_embed.2.bias", "time_embedding.linear_2.bias"),
- ("input_blocks.0.0.weight", "conv_in.weight"),
- ("input_blocks.0.0.bias", "conv_in.bias"),
- ("out.0.weight", "conv_norm_out.weight"),
- ("out.0.bias", "conv_norm_out.bias"),
- ("out.2.weight", "conv_out.weight"),
- ("out.2.bias", "conv_out.bias"),
-]
-
-unet_conversion_map_resnet = [
- # (stable-diffusion, HF Diffusers)
- ("in_layers.0", "norm1"),
- ("in_layers.2", "conv1"),
- ("out_layers.0", "norm2"),
- ("out_layers.3", "conv2"),
- ("emb_layers.1", "time_emb_proj"),
- ("skip_connection", "conv_shortcut"),
-]
-
-unet_conversion_map_layer = []
-# hardcoded number of downblocks and resnets/attentions...
-# would need smarter logic for other networks.
-for i in range(4):
- # loop over downblocks/upblocks
-
- for j in range(2):
- # loop over resnets/attentions for downblocks
- hf_down_res_prefix = f"down_blocks.{i}.resnets.{j}."
- sd_down_res_prefix = f"input_blocks.{3 * i + j + 1}.0."
- unet_conversion_map_layer.append((sd_down_res_prefix, hf_down_res_prefix))
-
- if i < 3:
- # no attention layers in down_blocks.3
- hf_down_atn_prefix = f"down_blocks.{i}.attentions.{j}."
- sd_down_atn_prefix = f"input_blocks.{3 * i + j + 1}.1."
- unet_conversion_map_layer.append((sd_down_atn_prefix, hf_down_atn_prefix))
-
- for j in range(3):
- # loop over resnets/attentions for upblocks
- hf_up_res_prefix = f"up_blocks.{i}.resnets.{j}."
- sd_up_res_prefix = f"output_blocks.{3 * i + j}.0."
- unet_conversion_map_layer.append((sd_up_res_prefix, hf_up_res_prefix))
-
- if i > 0:
- # no attention layers in up_blocks.0
- hf_up_atn_prefix = f"up_blocks.{i}.attentions.{j}."
- sd_up_atn_prefix = f"output_blocks.{3 * i + j}.1."
- unet_conversion_map_layer.append((sd_up_atn_prefix, hf_up_atn_prefix))
-
- if i < 3:
- # no downsample in down_blocks.3
- hf_downsample_prefix = f"down_blocks.{i}.downsamplers.0.conv."
- sd_downsample_prefix = f"input_blocks.{3 * (i + 1)}.0.op."
- unet_conversion_map_layer.append((sd_downsample_prefix, hf_downsample_prefix))
-
- # no upsample in up_blocks.3
- hf_upsample_prefix = f"up_blocks.{i}.upsamplers.0."
- sd_upsample_prefix = f"output_blocks.{3 * i + 2}.{1 if i == 0 else 2}."
- unet_conversion_map_layer.append((sd_upsample_prefix, hf_upsample_prefix))
-
-hf_mid_atn_prefix = "mid_block.attentions.0."
-sd_mid_atn_prefix = "middle_block.1."
-unet_conversion_map_layer.append((sd_mid_atn_prefix, hf_mid_atn_prefix))
-
-for j in range(2):
- hf_mid_res_prefix = f"mid_block.resnets.{j}."
- sd_mid_res_prefix = f"middle_block.{2 * j}."
- unet_conversion_map_layer.append((sd_mid_res_prefix, hf_mid_res_prefix))
-
-
-def convert_unet_state_dict(unet_state_dict):
- # buyer beware: this is a *brittle* function,
- # and correct output requires that all of these pieces interact in
- # the exact order in which I have arranged them.
- mapping = {k: k for k in unet_state_dict.keys()}
- for sd_name, hf_name in unet_conversion_map:
- mapping[hf_name] = sd_name
- for k, v in mapping.items():
- if "resnets" in k:
- for sd_part, hf_part in unet_conversion_map_resnet:
- v = v.replace(hf_part, sd_part)
- mapping[k] = v
- for k, v in mapping.items():
- for sd_part, hf_part in unet_conversion_map_layer:
- v = v.replace(hf_part, sd_part)
- mapping[k] = v
- new_state_dict = {v: unet_state_dict[k] for k, v in mapping.items()}
- return new_state_dict
-
-
# ================#
# VAE Conversion #
# ================#
@@ -213,6 +114,7 @@ textenc_pattern = re.compile("|".join(protected.keys()))
# Ordering is from https://github.com/pytorch/pytorch/blob/master/test/cpp/api/modules.cpp
code2idx = {"q": 0, "k": 1, "v": 2}
+
# This function exists because at the time of writing torch.cat can't do fp8 with cuda
def cat_tensors(tensors):
x = 0
@@ -229,6 +131,7 @@ def cat_tensors(tensors):
return out
+
def convert_text_enc_state_dict_v20(text_enc_dict, prefix=""):
new_state_dict = {}
capture_qkv_weight = {}
@@ -284,5 +187,3 @@ def convert_text_enc_state_dict_v20(text_enc_dict, prefix=""):
def convert_text_enc_state_dict(text_enc_dict):
return text_enc_dict
-
-