Add optional noise_seed to make augmentation deterministic #3275
Conversation
This file contains 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
|
A more proper way is doing it with a generator like this: https://github.com/comfyanonymous/ComfyUI/blob/master/comfy/sample.py#L13 |
|
@comfyanonymous changed as requested. This kind of mandates the seed to be a required, not optional, argument, so I changed accordingly. |
|
@harelc the generator can be None when no seed is supplied and it'll use the "global" RNG. |
|
@asagi4 ok, did as you suggested. |
| RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "LATENT") | ||
| RETURN_NAMES = ("positive", "negative", "latent") | ||
|
|
||
| FUNCTION = "encode" | ||
|
|
||
| CATEGORY = "conditioning/video_models" | ||
|
|
||
| def encode(self, clip_vision, init_image, vae, width, height, video_frames, motion_bucket_id, fps, augmentation_level): | ||
| def encode(self, clip_vision, init_image, vae, width, height, video_frames, motion_bucket_id, | ||
| fps, augmentation_level, noise_seed=None): |
There was a problem hiding this comment.
[minor] this shouldn't have the line break here
| }} | ||
| "augmentation_level": ("FLOAT", {"default": 0.0, "min": 0.0, "max": 10.0, "step": 0.01}), | ||
| }, | ||
| "optional": { "noise_seed": ("INT", {"default": 0, "min": 0, "max": 2**32-1}) |
There was a problem hiding this comment.
the seed max value as seen in eg the KSampler node should be set as 0xffffffffffffffff
mcmonkey4eva
added
Bug
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
As currently implemented, SVD_img2vid_Conditioning has an optional augmentation stage with non-deterministic noising of the conditioning image, which prevents one from reproducing exact results in an SVD pipeline if augmentation is used.
I'm suggesting an optional (change widget to input port to ignore) noise_seed for the augmentation stage.