Skip to content

Fix configuring VAE from single file mixin #6950

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

Merged
merged 4 commits into from
Feb 13, 2024
Merged

Fix configuring VAE from single file mixin #6950

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
d68635f
update
DN6 Feb 12, 2024
2d5e9c2
update
DN6 Feb 12, 2024
e7b2032
update
DN6 Feb 12, 2024
57afaff
update
DN6 Feb 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
13 changes: 12 additions & 1 deletion src/diffusers/loaders/autoencoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,6 +92,7 @@ def from_single_file(cls, pretrained_model_link_or_path, **kwargs):
"""

original_config_file = kwargs.pop("original_config_file", None)
config_file = kwargs.pop("config_file", None)
resume_download = kwargs.pop("resume_download", False)
force_download = kwargs.pop("force_download", False)
proxies = kwargs.pop("proxies", None)
Expand All @@ -103,6 +104,13 @@ def from_single_file(cls, pretrained_model_link_or_path, **kwargs):
use_safetensors = kwargs.pop("use_safetensors", True)

class_name = cls.__name__

if (config_file is not None) and (original_config_file is not None):
raise ValueError(
"You cannot pass both `config_file` and `original_config_file` to `from_single_file`. Please use only one of these arguments."
)

original_config_file = original_config_file or config_file
original_config, checkpoint = fetch_ldm_config_and_checkpoint(
pretrained_model_link_or_path=pretrained_model_link_or_path,
class_name=class_name,
Expand All @@ -118,7 +126,10 @@ def from_single_file(cls, pretrained_model_link_or_path, **kwargs):
)

image_size = kwargs.pop("image_size", None)
component = create_diffusers_vae_model_from_ldm(class_name, original_config, checkpoint, image_size=image_size)
scaling_factor = kwargs.pop("scaling_factor", None)
component = create_diffusers_vae_model_from_ldm(
class_name, original_config, checkpoint, image_size=image_size, scaling_factor=scaling_factor
)
vae = component["vae"]
if torch_dtype is not None:
vae = vae.to(torch_dtype)
Expand Down
7 changes: 5 additions & 2 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 @@ -175,6 +175,7 @@
}

LDM_VAE_KEY = "first_stage_model."
LDM_VAE_DEFAULT_SCALING_FACTOR = 0.18215
LDM_UNET_KEY = "model.diffusion_model."
LDM_CONTROLNET_KEY = "control_model."
LDM_CLIP_PREFIX_TO_REMOVE = ["cond_stage_model.transformer.", "conditioner.embedders.0.transformer."]
Expand Down Expand Up @@ -518,7 +519,9 @@ def create_vae_diffusers_config(original_config, image_size, scaling_factor=None
Creates a config for the diffusers based on the config of the LDM model.
"""
vae_params = original_config["model"]["params"]["first_stage_config"]["params"]["ddconfig"]
scaling_factor = scaling_factor or original_config["model"]["params"]["scale_factor"]
scaling_factor = (
scaling_factor or original_config["model"]["params"]["scale_factor"] or LDM_VAE_DEFAULT_SCALING_FACTOR
)

block_out_channels = [vae_params["ch"] * mult for mult in vae_params["ch_mult"]]
down_block_types = ["DownEncoderBlock2D"] * len(block_out_channels)
Expand Down Expand Up @@ -1173,7 +1176,7 @@ def create_diffusers_unet_model_from_ldm(


def create_diffusers_vae_model_from_ldm(
pipeline_class_name, original_config, checkpoint, image_size=None, scaling_factor=0.18125
pipeline_class_name, original_config, checkpoint, image_size=None, scaling_factor=None
):
# import here to avoid circular imports
from ..models import AutoencoderKL
Expand Down