Add strength input to Differential Diffusion #5709
Closed
+23
−7
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Wouldn't it be better to skip the blending logic when the strength is set to 1.0? |
|
@ltdrdata The blend operation is nearly instantaneous either way (at least at 1024x1024), but you're right, a conditional check is probably smarter. 🙂 Updated the code. |
|
Any reason why this is not merged? |
comfyanonymous
pushed a commit
that referenced
this pull request
Sep 21, 2025
* Update nodes_differential_diffusion.py * Update nodes_differential_diffusion.py * Make strength optional to avoid validation errors when loading old workflows, adjust step --------- Co-authored-by: ThereforeGames <[email protected]>
|
The commits are now in via #9957! Closing this PR 🫡 thanks! |
Thor-ATX
pushed a commit
to asteriafilmco/ComfyUI
that referenced
this pull request
Sep 26, 2025
…e-update * commit '2b7f9a8196304badb5fe58e5c734e4b182ad0fdf': (91 commits) Fix the failing unit test. (comfyanonymous#10037) Make LatentCompositeMasked work with basic video latents. (comfyanonymous#10023) Fix memory leak by properly detaching model finalizer (comfyanonymous#9979) Fix issue with .view() in HuMo. (comfyanonymous#10014) Add new audio nodes (comfyanonymous#9908) Rodin3D - add [Rodin3D Gen-2 generate] api-node (comfyanonymous#9994) ComfyUI version 0.3.60 feat(api-nodes): add wan t2i, t2v, i2v nodes (comfyanonymous#9996) update template to 0.1.86 (comfyanonymous#9998) Fix bug with WanAnimateToVideo. (comfyanonymous#9990) Fix bug with WanAnimateToVideo node. (comfyanonymous#9988) add offset param (comfyanonymous#9977) Support for qwen edit plus model. Use the new TextEncodeQwenImageEditPlus. (comfyanonymous#9986) Set some wan nodes as no longer experimental. (comfyanonymous#9976) Lower wan memory estimation value a bit. (comfyanonymous#9964) Fix LoRA Trainer bugs with FP8 models. (comfyanonymous#9854) [Reviving comfyanonymous#5709] Add strength input to Differential Diffusion (comfyanonymous#9957) Add inputs for character replacement to the WanAnimateToVideo node. (comfyanonymous#9960) Update WanAnimateToVideo to more easily extend videos. (comfyanonymous#9959) fix(seedream4): add flag to ignore error on partial success (comfyanonymous#9952) ...
toxicwind
pushed a commit
to toxicwind/ComfyUI
that referenced
this pull request
Oct 12, 2025
…fusion (comfyanonymous#9957) * Update nodes_differential_diffusion.py * Update nodes_differential_diffusion.py * Make strength optional to avoid validation errors when loading old workflows, adjust step --------- Co-authored-by: ThereforeGames <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Hi,
The Differential Diffusion node from #2876 is awesome for inpainting tasks, but the effect is too strong at times. It is challenging to use when generating a subject that has little in common with the original.
Even at a denoising strength of 100%, Differential Diffusion often overwhelms the prompt. But if we blend the adjusted binary mask with the original, we can find a sweet spot. The example below was performed with Euler/Beta, 4 steps, 100% denoising strength. Model is flux1-dev.sft with distillation LoRAs for speed.
50-75% Differential Diffusion strength feels a lot more usable in practice than 100%. Here's one more comparison if you'll indulge me:
The prompt was "Donald Trump." That guy in the middle looks like he'd be fun at parties, but he's definitely not Trump.