[Bug]: Frame Interpolation does not work with TensorRT

[Eugeniusz-Gienek]

Have you read the latest version of the FAQ?

• I have visited the FAQ page right now and my issue is not present there

Is there an existing issue for this?

• I have searched the existing issues and checked the recent builds/commits of both this extension and the webui

Are you using the latest version of the Deforum extension?

• I have Deforum updated to the lastest version and I still have the issue.

What happened?

When trying to generate the frames with TensorRT mode on (which as known speeds up things dramatically) all modes but Frame Intetpolation work. When using frame interpolation the error is as follows after a couple of iterations:

`Error: 'The size of tensor a (2) must match the size of tensor b (3) at non-singleton dimension 0'. Before reporting, please check your schedules/ init values. Full error message is in your terminal/ cli.

Time taken: 10.2 sec.

A: 0.94 GB, R: 1.12 GB, Sys: 3.0/15.6924 GB (19.3%)`

Steps to reproduce the problem

1. Go to Keyframes tab
2. Select "Interpolation"
3. Go to Promts tab
4. Fill the Prompts json field
5. Hit generate
6. Get error

What should have happened/how would you fix it?

Well, it should work - using the TensorRT Unet

Torch version

2.1.2+cu121

On which platform are you launching the webui with the extension?

Local PC setup (Linux)

Deforum settings

deforum_settings_1.txt

Webui core settings

ui-config.json

Console logs

user@aiserver ~ $ /home/user/sd/webui.sh

################################################################
Install script for stable-diffusion + Web UI                                               Tested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.
################################################################

################################################################
Running on user user                                                                      ################################################################
################################################################
Repo already cloned, using it as install directory                                         ################################################################

################################################################
Create and activate python venv                                                            ################################################################

################################################################
Launching launch.py...                                                                     ################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/usr/lib64/libtcmalloc_minimal.so.4
Python 3.11.9 (main, Jul 12 2024, 09:28:10) [GCC 13.2.1 20240210]
Version: v1.9.4
Commit hash: feee37d75f1b168768014e4634dcb156ee649c05
Running installer for:  /home/user/sd/extensions/sd-webui-segment-anything ; path_installer:  /home/user/sd/extensions/sd-webui-segment-anything/install.py ; python:  /home/user/sd/venv/bin/python3.11                                                                      Running installer for:  /home/user/sd/extensions/Stable-Diffusion-WebUI-TensorRT ; path_installer:  /home/user/sd/extensions/Stable-Diffusion-WebUI-TensorRT/install.py ; python:  /home/user/sd/venv/bin/python3.11
Checking TensorRT...
TensorRT is installed. Checking version...
Running installer for:  /home/user/sd/extensions/stable-diffusion-webui-images-browser ; path_installer:  /home/user/sd/extensions/stable-diffusion-webui-images-browser/install.py ; python:  /home/user/sd/venv/bin/python3.11
################################################################                           Repo already cloned, using it as install directory
################################################################                           ################################################################
Create and activate python venv                                                            ################################################################
################################################################
Launching launch.py...                                                                     ################################################################
glibc version is 2.39                                                                      Check TCMalloc: libtcmalloc_minimal.so.4                                                   libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/usr/lib64/libtcmalloc_minimal.so.4                                                                                Python 3.11.9 (main, Jul 12 2024, 09:28:10) [GCC 13.2.1 20240210]
Version: v1.9.4
Commit hash: feee37d75f1b168768014e4634dcb156ee649c05
Running installer for:  /home/user/sd/extensions/sd-webui-segment-anything ; path_installer:  /home/user/sd/extensions/sd-webui-segment-anything/install.py ; python:  /home/user/sd/venv/bin/python3.11
Running installer for:  /home/user/sd/extensions/Stable-Diffusion-WebUI-TensorRT ; path_installer:  /home/user/sd/extensions/Stable-Diffusion-WebUI-TensorRT/install.py ; python:  /home/user/sd/venv/bin/python3.11
Checking TensorRT...
TensorRT is installed. Checking version...                                                 Running installer for:  /home/user/sd/extensions/stable-diffusion-webui-images-browser ; path_installer:  /home/user/sd/extensions/stable-diffusion-webui-images-browser/install.py ; python:  /home/user/sd/venv/bin/python3.11
Running installer for:  /home/user/sd/extensions/deforum-for-automatic1111-webui ; path_installer:  /home/user/sd/extensions/deforum-for-automatic1111-webui/install.py ; python:  /home/user/sd/venv/bin/python3.11
Running installer for:  /home/user/sd/extensions/sd-webui-controlnet ; path_installer:  /home/user/sd/extensions/sd-webui-controlnet/install.py ; python:  /home/user/sd/venv/bin/python3.11
Installing sd-webui-controlnet requirement: changing opencv-python version from 4.10.0.84 to 4.8.0
ControlNet init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.                                                              Running installer for:  /home/user/sd/extensions/adetailer ; path_installer:  /home/user/sd/extensions/adetailer/install.py ; python:  /home/user/sd/venv/bin/python3.11
Running installer for:  /home/user/sd/extensions/sd-civitai-browser-plus ; path_installer:  /home/user/sd/extensions/sd-civitai-browser-plus/install.py ; python:  /home/user/sd/venv/bin/python3.11
Launching Web UI with arguments: --listen --port 7860 --enable-insecure-extension-access --skip-version-check --disable-safe-unpickle --xformers
[-] ADetailer initialized. version: 24.6.0, num models: 22
CivitAI Browser+: Aria2 RPC started
ControlNet preprocessor location: /home/user/sd/extensions/sd-webui-controlnet/annotator/downloads
2024-07-28 11:26:23,944 - ControlNet - INFO - ControlNet v1.1.455
Loading weights [32baa6e527] from /home/user/sd/models/Stable-diffusion/cyberrealistic_v50.safetensors                                                                               Creating model from config: /home/user/sd/configs/v1-inference.yaml
Applying attention optimization: xformers... done.
TensorRT is installed. Checking version...                                                 Running installer for:  /home/user/sd/extensions/stable-diffusion-webui-images-browser ; path_installer:  /home/user/sd/extensions/stable-diffusion-webui-images-browser/install.py ; python:  /home/user/sd/venv/bin/python3.11
Running installer for:  /home/user/sd/extensions/deforum-for-automatic1111-webui ; path_installer:  /home/user/sd/extensions/deforum-for-automatic1111-webui/install.py ; python:  /home/user/sd/venv/bin/python3.11
Running installer for:  /home/user/sd/extensions/sd-webui-controlnet ; path_installer:  /home/user/sd/extensions/sd-webui-controlnet/install.py ; python:  /home/user/sd/venv/bin/python3.11
Installing sd-webui-controlnet requirement: changing opencv-python version from 4.10.0.84 to 4.8.0
ControlNet init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.                                                              Running installer for:  /home/user/sd/extensions/adetailer ; path_installer:  /home/user/sd/extensions/adetailer/install.py ; python:  /home/user/sd/venv/bin/python3.11
Running installer for:  /home/user/sd/extensions/sd-civitai-browser-plus ; path_installer:  /home/user/sd/extensions/sd-civitai-browser-plus/install.py ; python:  /home/user/sd/venv/bin/python3.11
Launching Web UI with arguments: --listen --port 7860 --enable-insecure-extension-access --skip-version-check --disable-safe-unpickle --xformers
[-] ADetailer initialized. version: 24.6.0, num models: 22
CivitAI Browser+: Aria2 RPC started
ControlNet preprocessor location: /home/user/sd/extensions/sd-webui-controlnet/annotator/downloads
2024-07-28 11:26:23,944 - ControlNet - INFO - ControlNet v1.1.455
Loading weights [32baa6e527] from /home/user/sd/models/Stable-diffusion/cyberrealistic_v50.safetensors                                                                               Creating model from config: /home/user/sd/configs/v1-inference.yaml
Applying attention optimization: xformers... done.
Model loaded in 1.4s (load weights from disk: 0.3s, create model: 0.4s, apply weights to model: 0.4s, calculate empty prompt: 0.1s).
2024-07-28 11:26:26,102 - ControlNet - INFO - ControlNet UI callback registered.
No config file found for sharp_focus. You can generate it in the LoRA tab.
No config file found for passionate. You can generate it in the LoRA tab.
LoRA age is not a safetensor. This might cause issues when exporting to TensorRT.                             Please ensure that the correct base model is selected when exporting.
No config file found for wide_angle. You can generate it in the LoRA tab.
No config file found for blue_eye_color. You can generate it in the LoRA tab.
No config file found for very_very_very_cute. You can generate it in the LoRA tab.
No config file found for makeup. You can generate it in the LoRA tab.                      No config file found for blonde_hair. You can generate it in the LoRA tab.                 No config file found for elf. You can generate it in the LoRA tab.                         LoRA SkinnyVoluptousSliderXL is not a safetensor. This might cause issues when exporting to TensorRT.                                                                                                    Please ensure that the correct base model is selected when exporting.   No config file found for view_from_above. You can generate it in the LoRA tab.             No config file found for eyes. You can generate it in the LoRA tab.
No config file found for asleep. You can generate it in the LoRA tab.
No config file found for view_from_behind. You can generate it in the LoRA tab.
*Deforum ControlNet support: enabled*
Loading general settings...
reading custom settings from /home/user/sd/deforum_settings.txt
Running on local URL:  http://0.0.0.0:7860
To create a public link, set `share=True` in `launch()`.
Startup time: 17.8s (prepare environment: 5.2s, import torch: 2.9s, import gradio: 0.8s, setup paths: 1.8s, initialize shared: 0.2s, other imports: 0.6s, load scripts: 2.2s, create ui: 3.7s, gradio launch: 0.5s).
reading custom settings from /home/user/sd/deforum_settings_1.txt
started run_deforum
times_to_run: 1
Deforum extension for auto1111 webui
Git commit: 5d63a339
Starting job task(rjpggttiu1h8wfs)-0...
Saving interpolation animation frames to /home/user/sd/outputs/img2img-images/Deforum_20240728112659
Generating interpolated prompts for all frames
Interpolation frame: 0/120
Seed: 1867956710
Prompt: (beautiful:1.5) finnish (25 years old:1.5) (woman) in a hotel room, (beautiful face:1.2), (blue dress), best quality, high detail, mature, playful, full body, blue eyes, platinum blonde hair, (modern:1.8), (slender:1.7), (v shape body:1.6), (wide shoulders:1.8), (standing near the bed:1.5),  (looking at viewer:1.2) --neg (worst quality:1.5), (low quality:1.5), lowres, drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, tiling, mutated, poorly drawn eyes, poorly drawn face, (monochrome:1.1), (grayscale), multiple views, comic,  (((bad anatomy))),  (((deformed))), (((disfigured))), watermark, multiple_views, missing fingers
╭─────┬───╮
│Steps│CFG│
├─────┼───┤
│ 50  │5.0│
╰─────┴───╯
Activating unet: [TRT] cyberrealistic_v50
Loading TensorRT engine: /home/user/sd/models/Unet-trt/cyberrealistic_v50_743cb7c1_cc89_sample=2x4x64x64-timesteps=2-encoder_hidden_states=2x77x768.trt

Loaded Profile: 0
        sample = [(2, 4, 64, 64), (2, 4, 64, 64), (2, 4, 64, 64)]
        timesteps = [(2,), (2,), (2,)]
        encoder_hidden_states = [(2, 77, 768), (2, 77, 768), (2, 77, 768)]
        latent = [(2, 4, 64, 64), (2, 4, 64, 64), (2, 4, 64, 64)]

100%|██████████████████████████████████████████████████████| 50/50 [00:08<00:00,  5.72it/s]Interpolation frame: 1/120                               | 49/1112 [00:08<02:38,  6.72it/s]Seed: 1867956711
Prompt: ((beautiful:1.5) finnish (25 years old:1.5) (woman) in a hotel room, (beautiful face:1.2), (blue dress), best quality, high detail, mature, playful, full body, blue eyes, platinum blonde hair, (modern:1.8), (slender:1.7), (v shape body:1.6), (wide shoulders:1.8), (standing near the bed:1.5),  (looking at viewer:1.2) ):0.9666666666666667 AND  ((beautiful:1.5) finnish (25 years old:1.5) (woman) in a hotel room, (beautiful face:1.2), (blue dress), best quality, high detail, mature, playful, full body, blue eyes, platinum blonde hair, (modern:1.8), (slender:1.7), (v shape body:1.6), (wide shoulders:1.8), (standing near the bed:1.5),  (winking:1.2) ):0.03333333333333333 --neg  ( (worst quality:1.5), (low quality:1.5), lowres, drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, tiling, mutated, poorly drawn eyes, poorly drawn face, (monochrome:1.1), (grayscale), multiple views, comic,  (((bad anatomy))),  (((deformed))), (((disfigured))), watermark, multiple_views, missing fingers):0.9666666666666667 AND  ( (worst quality:1.5), (low quality:1.5), lowres, drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, tiling, mutated, poorly drawn eyes, poorly drawn face, (monochrome:1.1), (grayscale), multiple views, comic,  (((bad anatomy))),  (((deformed))), (((disfigured))), watermark, multiple_views, missing fingers):0.03333333333333333
╭─────┬───╮
│Steps│CFG│
├─────┼───┤
│ 50  │5.0│
╰─────┴───╯
  0%|                                                               | 0/50 [00:00<?, ?it/s][E] 3: [executionContext.cpp::validateInputBindings::2045] Error Code 3: API Usage Error (Parameter check failed at: runtime/api/executionContext.cpp::validateInputBindings::2045, condition: profileMaxDims.d[i] >= dimensions.d[i]. Supplied binding dimension [3,4,64,64] for bindings[0] exceed min ~ max range at index 0, maximum dimension in profile is 2, minimum dimension in profile is 2, but supplied dimension is 3.
    )
[E] 3: [executionContext.cpp::validateInputBindings::2045] Error Code 3: API Usage Error (Parameter check failed at: runtime/api/executionContext.cpp::validateInputBindings::2045, condition: profileMaxDims.d[i] >= dimensions.d[i]. Supplied binding dimension [3] for bindings[1] exceed min ~ max range at index 0, maximum dimension in profile is 2, minimum dimension in profile is 2, but supplied dimension is 3.
    )
[E] 3: [executionContext.cpp::validateInputBindings::2045] Error Code 3: API Usage Error (Parameter check failed at: runtime/api/executionContext.cpp::validateInputBindings::2045, condition: profileMaxDims.d[i] >= dimensions.d[i]. Supplied binding dimension [3,231,768] for bindings[2] exceed min ~ max range at index 0, maximum dimension in profile is 2, minimum dimension in profile is 2, but supplied dimension is 3.
    )
  0%|                                                               | 0/50 [00:00<?, ?it/s]WARNING:deforum_helpers.opts_overrider:Error during batch execution: <class 'RuntimeError'> - The size of tensor a (2) must match the size of tensor b (3) at non-singleton dimension 0

*START OF TRACEBACK*
Traceback (most recent call last):
  File "/home/user/sd/extensions/deforum-for-automatic1111-webui/scripts/deforum_helpers/run_deforum.py", line 120, in run_deforum
    render_interpolation(args, anim_args, video_args, parseq_args, loop_args, controlnet_args, root)
  File "/home/user/sd/extensions/deforum-for-automatic1111-webui/scripts/deforum_helpers/render_modes.py", line 165, in render_interpolation
    image = generate(args, keys, anim_args, loop_args, controlnet_args, root, parseq_adapter, frame_idx, sampler_name=scheduled_sampler_name)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/sd/extensions/deforum-for-automatic1111-webui/scripts/deforum_helpers/generate.py", line 78, in generate
    return generate_inner(args, keys, anim_args, loop_args, controlnet_args, root, parseq_adapter, frame, sampler_name, scheduler_name)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/sd/extensions/deforum-for-automatic1111-webui/scripts/deforum_helpers/generate.py", line 249, in generate_inner
    processed = processing.process_images(p_txt)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/sd/modules/processing.py", line 845, in process_images
    res = process_images_inner(p)
          ^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/sd/extensions/sd-webui-controlnet/scripts/batch_hijack.py", line 59, in processing_process_images_hijack
    return getattr(processing, '__controlnet_original_process_images_inner')(p, *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/sd/modules/processing.py", line 981, in process_images_inner
    samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/sd/modules/processing.py", line 1328, in sample
    samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/sd/modules/sd_samplers_kdiffusion.py", line 218, in sample
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_aenerate.py", line 78, in generate                                                              return generate_inner(args, keys, anim_args, loop_args, controlnet_args, root, parseq_adapter, frame, sampler_name, scheduler_name)                                                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/sd/extensions/deforum-for-automatic1111-webui/scripts/deforum_helpers/generate.py", line 249, in generate_inner
    processed = processing.process_images(p_txt)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/sd/modules/processing.py", line 845, in process_images                     res = process_images_inner(p)                                                                    ^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/sd/extensions/sd-webui-controlnet/scripts/batch_hijack.py", line 59, in processing_process_images_hijack                                                              return getattr(processing, '__controlnet_original_process_images_inner')(p, *args, **kwargs)                                                                                                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/sd/modules/processing.py", line 981, in process_images_inner
    samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/sd/modules/processing.py", line 1328, in sample                            samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^                                             File "/home/user/sd/modules/sd_samplers_kdiffusion.py", line 218, in sample
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^                                                                                       File "/home/user/sd/modules/sd_samplers_common.py", line 272, in launch_sampling
    return func()                                                                                     ^^^^^^
  File "/home/user/sd/modules/sd_samplers_kdiffusion.py", line 218, in <lambda>
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
                                                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^                                                                                        File "/home/user/sd/venv/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^                                                             File "/home/user/sd/repositories/k-diffusion/k_diffusion/sampling.py", line 668, in sample_dpmpp_3m_sde
    denoised = model(x, sigmas[i] * s_in, **extra_args)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/sd/venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)                                                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/sd/venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/sd/modules/sd_samplers_cfg_denoiser.py", line 237, in forward
    x_out = self.inner_model(x_in, sigma_in, cond=make_condition_dict(cond_in, image_cond_in))
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/sd/venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/sd/venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/sd/repositories/k-diffusion/k_diffusion/external.py", line 113, in forward
    return input + eps * c_out
                   ~~~~^~~~~~~
RuntimeError: The size of tensor a (2) must match the size of tensor b (3) at non-singleton dimension 0
*END OF TRACEBACK*

User friendly error message:
Error: The size of tensor a (2) must match the size of tensor b (3) at non-singleton dimension 0. Please, check your schedules/ init values.
Deforum progress:   4%|█▌                                | 50/1112 [00:09<03:20,  5.29it/s]

Additional information

No response