Skip to content

Tag Krea 2 text encoder outputs as denoiser_input_fields #14925

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
yiyixuxu merged 1 commit into from
Oct 2, 2026
Merged

Tag Krea 2 text encoder outputs as denoiser_input_fields #14925

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
6 changes: 6 additions & 0 deletions src/diffusers/modular_pipelines/krea2/encoders.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,21 +110,25 @@ def intermediate_outputs(self) -> list[OutputParam]:
OutputParam(
name="prompt_embeds",
type_hint=torch.Tensor,
kwargs_type="denoiser_input_fields",
description="Per-prompt stacked text features (B, text_seq_len, num_text_layers, text_hidden_dim).",
),
OutputParam(
name="prompt_embeds_mask",
type_hint=torch.Tensor,
kwargs_type="denoiser_input_fields",
description="Per-prompt boolean text mask (B, text_seq_len).",
),
OutputParam(
name="negative_prompt_embeds",
type_hint=torch.Tensor,
kwargs_type="denoiser_input_fields",
description="Per-prompt negative text features (only when guidance is enabled).",
),
OutputParam(
name="negative_prompt_embeds_mask",
type_hint=torch.Tensor,
kwargs_type="denoiser_input_fields",
description="Per-prompt negative text mask (only when guidance is enabled).",
),
]
Expand Down Expand Up @@ -254,11 +258,13 @@ def intermediate_outputs(self) -> list[OutputParam]:
OutputParam(
name="prompt_embeds",
type_hint=torch.Tensor,
kwargs_type="denoiser_input_fields",
description="Per-prompt stacked text features (B, text_seq_len, num_text_layers, text_hidden_dim).",
),
OutputParam(
name="prompt_embeds_mask",
type_hint=torch.Tensor,
kwargs_type="denoiser_input_fields",
description="Per-prompt boolean text mask (B, text_seq_len).",
),
]
Expand Down
Loading