Skip to content

Add latents_mean and latents_std to SDXLLongPromptWeightingPipeline #11034

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 2 commits into from
Mar 31, 2025
Merged

Add latents_mean and latents_std to SDXLLongPromptWeightingPipeline #11034

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ee3f297
Add `latents_mean` and `latents_std` to `SDXLLongPromptWeightingPipel…
hlky Mar 11, 2025
93ba6a8
Merge branch 'main' into lpw-stable-diffusion-xl-fix
hlky Mar 31, 2025
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
19 changes: 17 additions & 2 deletions examples/community/lpw_stable_diffusion_xl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1773,7 +1773,7 @@ def denoising_value_valid(dnv):
f"Incorrect configuration settings! The config of `pipeline.unet`: {self.unet.config} expects"
f" {self.unet.config.in_channels} but received `num_channels_latents`: {num_channels_latents} +"
f" `num_channels_mask`: {num_channels_mask} + `num_channels_masked_image`: {num_channels_masked_image}"
f" = {num_channels_latents+num_channels_masked_image+num_channels_mask}. Please verify the config of"
f" = {num_channels_latents + num_channels_masked_image + num_channels_mask}. Please verify the config of"
" `pipeline.unet` or your `mask_image` or `image` input."
)
elif num_channels_unet != 4:
Expand Down Expand Up @@ -1924,7 +1924,22 @@ def denoising_value_valid(dnv):
self.upcast_vae()
latents = latents.to(next(iter(self.vae.post_quant_conv.parameters())).dtype)

image = self.vae.decode(latents / self.vae.config.scaling_factor, return_dict=False)[0]
# unscale/denormalize the latents
# denormalize with the mean and std if available and not None
has_latents_mean = hasattr(self.vae.config, "latents_mean") and self.vae.config.latents_mean is not None
has_latents_std = hasattr(self.vae.config, "latents_std") and self.vae.config.latents_std is not None
if has_latents_mean and has_latents_std:
latents_mean = (
torch.tensor(self.vae.config.latents_mean).view(1, 4, 1, 1).to(latents.device, latents.dtype)
)
latents_std = (
torch.tensor(self.vae.config.latents_std).view(1, 4, 1, 1).to(latents.device, latents.dtype)
)
latents = latents * latents_std / self.vae.config.scaling_factor + latents_mean
else:
latents = latents / self.vae.config.scaling_factor

image = self.vae.decode(latents, return_dict=False)[0]

# cast back to fp16 if needed
if needs_upcasting:
Expand Down
Loading