Skip to content

[Fix bugs] pipeline_controlnet_sd_xl.py #6653

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
sayakpaul merged 2 commits into from
Jan 24, 2024
Merged

[Fix bugs] pipeline_controlnet_sd_xl.py #6653

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2542cd1
Update pipeline_controlnet_sd_xl.py
haofanwang Jan 21, 2024
149e9f6
Update pipeline_controlnet_xs_sd_xl.py
haofanwang Jan 22, 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
5 changes: 0 additions & 5 deletions examples/research_projects/controlnetxs/pipeline_controlnet_xs_sd_xl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1041,11 +1041,6 @@ def __call__(
step_idx = i // getattr(self.scheduler, "order", 1)
callback(step_idx, t, latents)

# manually for max memory savings
if self.vae.dtype == torch.float16 and self.vae.config.force_upcast:
self.upcast_vae()
latents = latents.to(next(iter(self.vae.post_quant_conv.parameters())).dtype)

if not output_type == "latent":
# make sure the VAE is in float32 mode, as it overflows in float16
needs_upcasting = self.vae.dtype == torch.float16 and self.vae.config.force_upcast
Expand Down
5 changes: 0 additions & 5 deletions src/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1404,11 +1404,6 @@ def __call__(
step_idx = i // getattr(self.scheduler, "order", 1)
callback(step_idx, t, latents)

# manually for max memory savings
if self.vae.dtype == torch.float16 and self.vae.config.force_upcast:
self.upcast_vae()
latents = latents.to(next(iter(self.vae.post_quant_conv.parameters())).dtype)

if not output_type == "latent":
# make sure the VAE is in float32 mode, as it overflows in float16
needs_upcasting = self.vae.dtype == torch.float16 and self.vae.config.force_upcast
Expand Down