Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Kolors UNet2DConditionModel from_single_file #10215

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Kolors UNet2DConditionModel from_single_file #10215

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
594ed8b
Kolors UNet from_single_file
hlky Dec 13, 2024
e0b71fb
convert_ldm_unet_checkpoint is_diffusers
hlky Dec 13, 2024
ecaf1db
make
hlky Dec 13, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions src/diffusers/loaders/single_file_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -100,6 +100,7 @@
],
"autoencoder-dc": "decoder.stages.1.op_list.0.main.conv.conv.bias",
"autoencoder-dc-sana": "encoder.project_in.conv.bias",
"kolors": "down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_k.weight",
}

DIFFUSERS_DEFAULT_PIPELINE_PATHS = {
Expand Down Expand Up @@ -151,6 +152,7 @@
"autoencoder-dc-f64c128": {"pretrained_model_name_or_path": "mit-han-lab/dc-ae-f64c128-mix-1.0-diffusers"},
"autoencoder-dc-f32c32": {"pretrained_model_name_or_path": "mit-han-lab/dc-ae-f32c32-mix-1.0-diffusers"},
"autoencoder-dc-f32c32-sana": {"pretrained_model_name_or_path": "mit-han-lab/dc-ae-f32c32-sana-1.0-diffusers"},
"kolors": {"pretrained_model_name_or_path": "Kwai-Kolors/Kolors-diffusers"},
}

# Use to configure model sample size when original config is provided
Expand Down Expand Up @@ -597,6 +599,9 @@ def infer_diffusers_model_type(checkpoint):
else:
model_type = "autoencoder-dc-f128c512"

elif CHECKPOINT_KEY_NAMES["kolors"] in checkpoint and checkpoint[CHECKPOINT_KEY_NAMES["kolors"]].shape[-1] == 2048:
model_type = "kolors"

else:
model_type = "v1"

Expand Down Expand Up @@ -961,6 +966,9 @@ def convert_ldm_unet_checkpoint(checkpoint, config, extract_ema=False, **kwargs)
"""
Takes a state dict and a config, and returns a converted checkpoint.
"""
is_diffusers = "time_embedding.linear_1.weight" in checkpoint
if is_diffusers:
return checkpoint
# extract state_dict for UNet
unet_state_dict = {}
keys = list(checkpoint.keys())
Expand Down
Loading