-
Notifications
You must be signed in to change notification settings - Fork 202
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.
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
IndexError: list index out of range #30
Comments
Did you change the DDIM step? Changing the DDIM step might cause this issue. Line 529 in 8650dea
|
In the webUI I might've changed the steps, yes. If there are specific requirements for that and not being able to change it, that should be stated. There seems to be too many settings that should be "hard baked" into the process, removing the sliders (if they aren't created as variables that change the underlying math so it works anyways). Please reconsider how this is implemented, i.e, maybe make a check for integers and if not, put that out as a error. I do understand this is very new so I hope it can be made more flexible in the future - I'll come back to this one when it is ready! |
We have fixed it. We add a constraint to ensure the steps to be a multiple of 20. Lines 703 to 707 in 7cc5914
|
Awesome news! :) I'll update ASAP! |
We would like to provide more flexible options for users to try. However, this may introduce some unexpected conflict. Hope this update will solve your |
I've changed the maximum of steps = 120 and set the steps = 120 and got the same error. How to "run all" when setting the steps = 120 or more? |
@Jerx2y the mask is generated here. Lines 540 to 545 in a348e0a
You can check the length of the mask ( |
I get the same error as another user but with different error lines. After "Run 1st Key Frame" which works well, I get my style.
Then running "Run Key Frames" gives:
Traceback (most recent call last):
File "c:\python\lib\site-packages\gradio\queueing.py", line 388, in call_prediction
output = await route_utils.call_process_api(
File "c:\python\lib\site-packages\gradio\route_utils.py", line 219, in call_process_api
output = await app.get_blocks().process_api(
File "c:\python\lib\site-packages\gradio\blocks.py", line 1437, in process_api
result = await self.call_function(
File "c:\python\lib\site-packages\gradio\blocks.py", line 1109, in call_function
prediction = await anyio.to_thread.run_sync(
File "c:\python\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "c:\python\lib\site-packages\anyio_backends_asyncio.py", line 877, in run_sync_in_worker_thread
return await future
File "c:\python\lib\site-packages\anyio_backends_asyncio.py", line 807, in run
result = context.run(func, *args)
File "c:\python\lib\site-packages\gradio\utils.py", line 641, in wrapper
response = f(*args, **kwargs)
File "c:\python\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "C:\Users\Oliver\Documents\Github\Rerender_A_Video\webUI.py", line 550, in process2
samples, _ = ddim_v_sampler.sample(
File "c:\python\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "C:\Users\Oliver\Documents\Github\Rerender_A_Video\src\ddim_v_hacked.py", line 212, in sample
samples, intermediates = self.ddim_sampling(
File "c:\python\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "C:\Users\Oliver\Documents\Github\Rerender_A_Video\src\ddim_v_hacked.py", line 312, in ddim_sampling
weight = mask[i]
IndexError: list index out of range
And then I read something about dividing doing some frame math myself, but I don't know the formula/equation I should use for that.
The text was updated successfully, but these errors were encountered: