Skip to content

feat(z-image): add add_noise option to Z-Image Denoise #8739

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
Pfannkuchensack merged 7 commits into from
Jan 6, 2026
+20 −3
Merged

feat(z-image): add add_noise option to Z-Image Denoise #8739

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
11c8f12
feat(z-image): add `add_noise` option to Z-Image Denoise
Pfannkuchensack Jan 5, 2026
b2eeccd
Fix typegen
Pfannkuchensack Jan 5, 2026
70d4d16
Merge branch 'main' into feat/z-image-add-noise-option
Pfannkuchensack Jan 5, 2026
243afe8
Merge branch 'main' into feat/z-image-add-noise-option
Pfannkuchensack Jan 5, 2026
576a428
Fix typegen
Pfannkuchensack Jan 5, 2026
187d39a
Merge branch 'feat/z-image-add-noise-option' of https://github.com/Pf…
Pfannkuchensack Jan 5, 2026
8d45088
Fix typegen
Pfannkuchensack Jan 5, 2026
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
11 changes: 8 additions & 3 deletions invokeai/app/invocations/z_image_denoise.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,7 @@
title="Denoise - Z-Image",
tags=["image", "z-image"],
category="image",
version="1.3.0",
version="1.4.0",
classification=Classification.Prototype,
)
class ZImageDenoiseInvocation(BaseInvocation):
Expand All @@ -69,6 +69,7 @@ class ZImageDenoiseInvocation(BaseInvocation):
)
denoising_start: float = InputField(default=0.0, ge=0, le=1, description=FieldDescriptions.denoising_start)
denoising_end: float = InputField(default=1.0, ge=0, le=1, description=FieldDescriptions.denoising_end)
add_noise: bool = InputField(default=True, description="Add noise based on denoising start.")
transformer: TransformerField = InputField(
description=FieldDescriptions.z_image_model, input=Input.Connection, title="Transformer"
)
Expand Down Expand Up @@ -347,8 +348,12 @@ def _run_diffusion(self, context: InvocationContext) -> torch.Tensor:

# Prepare input latent image
if init_latents is not None:
s_0 = sigmas[0]
latents = s_0 * noise + (1.0 - s_0) * init_latents
if self.add_noise:
# Noise the init_latents by the appropriate amount for the first timestep.
s_0 = sigmas[0]
latents = s_0 * noise + (1.0 - s_0) * init_latents
else:
latents = init_latents
else:
if self.denoising_start > 1e-5:
raise ValueError("denoising_start should be 0 when initial latents are not provided.")
Expand Down
12 changes: 12 additions & 0 deletions invokeai/frontend/web/src/services/api/schema.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25587,6 +25587,12 @@ export type components = {
* @default 1
*/
denoising_end?: number;
/**
* Add Noise
* @description Add noise based on denoising start.
* @default true
*/
add_noise?: boolean;
/**
* Transformer
* @description Z-Image model (Transformer) to load
Expand Down Expand Up @@ -25708,6 +25714,12 @@ export type components = {
* @default 1
*/
denoising_end?: number;
/**
* Add Noise
* @description Add noise based on denoising start.
* @default true
*/
add_noise?: boolean;
/**
* Transformer
* @description Z-Image model (Transformer) to load
Expand Down