Skip to content

Include CLIPTextModel parameters in conversion #695

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 1 commit into from
Oct 5, 2022
Merged

Include CLIPTextModel parameters in conversion #695

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
18 changes: 17 additions & 1 deletion scripts/convert_original_stable_diffusion_to_diffusers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -595,6 +595,22 @@ def _copy_layers(hf_layers, pt_layers):
return hf_model


def convert_ldm_clip_checkpoint(checkpoint):
text_model = CLIPTextModel.from_pretrained("openai/clip-vit-large-patch14")

keys = list(checkpoint.keys())

text_model_dict = {}

for key in keys:
if key.startswith("cond_stage_model.transformer"):
text_model_dict[key[len("cond_stage_model.transformer.") :]] = checkpoint[key]

text_model.load_state_dict(text_model_dict)

return text_model


if __name__ == "__main__":
parser = argparse.ArgumentParser()

Expand Down Expand Up @@ -668,7 +684,7 @@ def _copy_layers(hf_layers, pt_layers):
# Convert the text model.
text_model_type = original_config.model.params.cond_stage_config.target.split(".")[-1]
if text_model_type == "FrozenCLIPEmbedder":
text_model = CLIPTextModel.from_pretrained("openai/clip-vit-large-patch14")
text_model = convert_ldm_clip_checkpoint(checkpoint)
tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-large-patch14")
safety_checker = StableDiffusionSafetyChecker.from_pretrained("CompVis/stable-diffusion-safety-checker")
feature_extractor = AutoFeatureExtractor.from_pretrained("CompVis/stable-diffusion-safety-checker")
Expand Down