wildwindfeng
commented
6 months ago Same issue here. After upgrade animateDiff today with Webui1.8 Old version was working fine
Closed xerun closed 6 months ago
wildwindfeng
commented
6 months ago Same issue here. After upgrade animateDiff today with Webui1.8 Old version was working fine
continue-revolution
commented
6 months ago someone please paste a screenshot of your adetailer. setup I don't know how to use it and I don't use it.
xerun
commented
6 months ago Hello, below is the setup, you just need to enable the adetailer, nothing else need to be changed in adetailer.
Sarimae
commented
6 months ago Same Issue here
zetteron
commented
6 months ago same issue
turugi-ni
commented
6 months ago I have the same problem.In addition, it generates images larger than 512 x 512.Use multiple Lora.Use upscaler extensions such as latent-upscale. multidiffusion-upscaler.Enter a large number in Number of frames. Probably more than 10 seconds.The error content varies, but finally it becomes RuntimeError: CUDA error: device-side assert triggered.My graphics board is nvida rtx 4060ti vram 16GB, so the image generation speed is slow, but I think I have enough vram.
gregreardon
commented
6 months ago same issue, even after todays update. How to replicate.
2024-03-07 20:47:05,755 - AnimateDiff - INFO - Saving output formats: MP4 2024-03-07 20:47:05,755 - AnimateDiff - INFO - AnimateDiff process end.
0: 640x448 1 face, 1425.0ms
Speed: 14.7ms preprocess, 1425.0ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 448)
0%| | 0/9 [00:00<?, ?it/s]2024-03-07 20:47:10,476 - AnimateDiff - INFO - inner model forward hooked
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [64,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [65,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [66,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [67,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [68,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [69,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [70,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [71,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [72,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [73,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [74,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [75,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [76,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [77,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [78,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [79,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [80,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [81,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [82,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [83,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [84,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [85,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [86,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [87,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [88,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [89,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [90,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [91,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [92,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [93,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [94,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [116,0,0], thread: [95,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [96,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [97,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [98,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [99,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [100,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [101,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [102,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [103,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [104,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [105,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [106,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [107,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [108,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [109,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [110,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [111,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [112,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [113,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [114,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [115,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [116,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [117,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [118,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [119,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [120,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [121,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [122,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [123,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [124,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [125,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [126,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [176,0,0], thread: [127,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed.
0%| | 0/9 [00:00<?, ?it/s]
Exception in thread MemMon:
Traceback (most recent call last):
File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
self.run()
File "/storage/stable-diffusion/stable-diffusion-webui/modules/memmon.py", line 53, in run
free, total = self.cuda_mem_get_info()
File "/storage/stable-diffusion/stable-diffusion-webui/modules/memmon.py", line 34, in cuda_mem_get_info
return torch.cuda.mem_get_info(index)
File "/usr/local/lib/python3.10/dist-packages/torch/cuda/memory.py", line 655, in mem_get_info
return torch.cuda.cudart().cudaMemGetInfo(device)
RuntimeError: CUDA error: device-side assert triggered
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
** Error running postprocess_image: /storage/stable-diffusion/stable-diffusion-webui/extensions/adetailer/scripts/!adetailer.py Traceback (most recent call last): File "/storage/stable-diffusion/stable-diffusion-webui/modules/scripts.py", line 856, in postprocess_image script.postprocess_image(p, pp, script_args) File "/storage/stable-diffusion/stable-diffusion-webui/extensions/adetailer/adetailer/traceback.py", line 159, in wrapper raise error from None RuntimeError: ╭──────────────────────────────────────────────────────────────────────────╮ │ System info │ │ ┏━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓ │ │ ┃ ┃ Value ┃ │ │ ┡━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩ │ │ │ Platform │ Linux-5.19.0-45-generic-x86_64-with-glibc2.31 │ │ │ │ Python │ 3.10.10 (main, Feb 8 2023, 14:50:01) [GCC 9.4.0] │ │ │ │ Version │ v1.8.0 │ │ │ │ Commit │ bef51aed032c0aaa5cfd80445bc4cf0d85b408b5 │ │ │ │ Commandline │ ['webui.py', '--xformers', '--medvram', │ │ │ │ │ '--disable-safe-unpickle', '--share', '--gradio-auth', │ │ │ │ │ 'me:me', '--enable-insecure-extension-access'] │ │ │ │ Libraries │ {'torch': '2.2.0', 'torchvision': '0.17.0', │ │ │ │ │ 'ultralytics': '8.1.24', 'mediapipe': '0.10.11'} │ │ │ └─────────────┴────────────────────────────────────────────────────────┘ │ │ Inputs │ │ ┏━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓ │ │ ┃ ┃ Value ┃ │ │ ┡━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩ │ │ │
favortel
commented
6 months ago same issue, change stable diffusion webui to 1.7.0 , sd-webui-animatediff to [v1.13.1], will fix everything
amida168
commented
6 months ago I have the same problem. After struggling to get it to work again, I ended up using ReActor to swap the face. I found that it's actually working better with ReActor. The face is more consistent now.
continue-revolution
commented
6 months ago I have reproduced this problem on my end. There are at least 2 problems with adetailer -
It seems that adetailer might not be a good fit even if I find some way to resolve this issue, because adetailer process images sequentially one-by-one, which means that AnimateDiff can only see 1 image at a time, and the output must have no consistency at all. Even if I manage to find some way to fix it (which I will), I would not expect the performance to be satisfactory at all.
I would like to collect some feedback from you guys while I am trying to fix it, or find an alternative such as refactoring my segment anything extension.
xerun
commented
6 months ago Yes mainly for face detail.
Below is an example without adetailer created on March 15, 2024
Below is an example with adetailer created on Feb 18, 2024 (before it broke)
continue-revolution
commented
6 months ago @xerun good thing: seems that adetailer did preserve temporal consistency; bad thing: there seems to be no difference at all between your 2 examples
wildwindfeng
commented
6 months ago @xerun good thing: seems that adetailer did preserve temporal consistency; bad thing: there seems to be no difference at all between your 2 examples
Actually there will be the huge difference when face is small in the picture. Smaller faces tend to be distorted before adetailer, after apply adetailer, face will be far more better
amida168
commented
6 months ago I used it to swap face and detail improvement. By default, the consistency is bad. I had to decrease the denoising strength to get better consistency.
I tried to insert my file, but it's too big.
continue-revolution
commented
6 months ago I have fixed the adetailer issue. There will be a bunch of warning on your terminal. If you believe that using adetailer is a good practice, please ignore those warnings.
amida168
commented
6 months ago Yes, it's working again. Thank you!
Is there an existing issue for this?
Have you read FAQ on README?
What happened?
When I enable Adetailer and run animateDiff after it finish generating the fames when it try to use Adetailer to fix the face the below error is shown and the entire webui is not functional anymore. I need to restart the application to make it work again.
Steps to reproduce the problem
What should have happened?
I should have generated the animation with face fixed.
Commit where the problem happens
• webui: v1.8.0 • python: 3.10.6 • torch: 2.1.2+cu121 • xformers: 0.0.23.post1 • gradio: 3.41.2 • checkpoint: 7c819b6d13
What browsers do you use to access the UI ?
No response
Command Line Arguments
Console logs
Additional information
No response