Bug Fix I2V Frame Count Hardcoded to 81 (!!) and Optional Batch Mode #100
+472
−422
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
…out reloading the model. Fixed seed synchronization handling by pre-generating them before the batch.
Look for # 20250226 pftq
Open
|
It seems the issue of generating more than 81 frames still persists. Could the PR or any other fix be merged? Thanks |
|
Yeah I don't know if the dev team ever saw this or will see this, but you can download the fix I did in the fork here: |
|
Thanks! I actually need the same fix in ReCamMaster as well: https://github.com/KwaiVGI/ReCamMaster/blob/main/diffsynth/pipelines/wan_video_recammaster.py |
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Outdated suggestions cannot be applied.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.
It turns out the Image2Video frames were hardcoded at 81! So you couldn't actually change the frame count of the video no matter what. I fixed this as well in the image2video.py file under WanI2V.generate()
First mentioned here: #73
I also added --batch_size parameter to generate multiple videos per run without reloading the model.
Saves a few minutes on reloading the model and having to re-enter the command each time.
The changes are pretty minimal and labeled with "# 20250226 pftq" - most the changes shown by github is just indenting everything else below it for the batch loop.