[Bug]: Depth Warping ON it gives me an error

[Bogodui]

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 I'm trying to run generation in 3D mode with Depth Warping ON it gives me an error.

Steps to reproduce the problem

1. Start AUTOMATIC1111 (I use portable version by serpotapov)
2. Go to Deforum tab and turn on the 3d mode, all other settings are the same as default (Depth Warp is automatically ON in 3d mode as I understand)
3. Press 'Generate' once and get: Error: 'argument of type 'NoneType' is not iterable'. Check your schedules/ init values please. Also make sure you don't have a backwards slash in any of your PATHs - use / instead of . Full error message is in your terminal/ cli.
4. Press generate the second time and get: Error: ''DepthModel' object has no attribute 'should_delete''. Check your schedules/ init values please. Also make sure you don't have a backwards slash in any of your PATHs - use / instead of . Full error message is in your terminal/ cli.

What should have happened/how would you fix it?

I fix it by turning off the Depth Warping but it's definitely not the best way to do it.

Torch version

torch: 2.0.1+cu118

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

Local PC setup (Windows)

Deforum settings

https://gist.github.com/Bogodui/20a501fa1c9857bbb6172853062cdb37

Webui core settings

https://gist.github.com/Bogodui/0daa2fe5b5718df37d55ee3079613b8a

Console logs

From https://github.com/AUTOMATIC1111/stable-diffusion-webui
 * branch              master     -> FETCH_HEAD
Already up to date.
venv "venv\Scripts\Python.exe"
fatal: No names found, cannot describe anything.
Python 3.10.9 (tags/v3.10.9:1dd9be6, Dec  6 2022, 20:01:21) [MSC v.1934 64 bit (AMD64)]
Version: ## 1.4.1
Commit hash: f865d3e11647dfd6c7b2cdf90dde24680e58acd8
Installing requirements

current transparent-background 1.2.3


Launching Web UI with arguments: --xformers --autolaunch --theme dark
=================================================================================
You are running xformers 0.0.17.
The program is tested to work with xformers 0.0.20.
To reinstall the desired version, run with commandline flag --reinstall-xformers.

Use --skip-version-check commandline argument to disable this check.
=================================================================================
2023-07-19 18:15:16,952 - ControlNet - INFO - ControlNet v1.1.233
ControlNet preprocessor location: X:\Stable-Diffusion\extensions\sd-webui-controlnet\annotator\downloads
2023-07-19 18:15:17,085 - ControlNet - INFO - ControlNet v1.1.233
Loading weights [9aba26abdf] from X:\Stable-Diffusion\models\Stable-diffusion\deliberate_v2.safetensors
Creating model from config: X:\Stable-Diffusion\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
*Deforum ControlNet support: enabled*
DiffusionWrapper has 859.52 M params.
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 16.1s (import torch: 4.8s, import gradio: 3.4s, import ldm: 1.0s, other imports: 2.8s, setup codeformer: 0.3s, list SD models: 0.2s, load scripts: 2.3s, create ui: 0.9s, gradio launch: 0.4s).
preload_extensions_git_metadata for 11 extensions took 1.45s
Applying attention optimization: xformers... done.
Textual inversion embeddings loaded(0):
Model loaded in 7.1s (load weights from disk: 0.5s, create model: 1.6s, apply weights to model: 2.4s, apply half(): 1.0s, move model to device: 1.3s, calculate empty prompt: 0.2s).
Deforum extension for auto1111 webui, v2.4b
Git commit: 858c4dd6
Saving animation frames to:
X:\Stable-Diffusion\outputs/img2img-images\Deforum_20230719181719
Loading MiDaS model from dpt_large-midas-2f21e586.pt...
*** Error verifying pickled file from X:\Stable-Diffusion\models/Deforum\dpt_large-midas-2f21e586.pt
*** -----> !!!! The file is most likely corrupted !!!! <-----
*** You can skip this check with --disable-safe-unpickle commandline argument, but that is not going to help you.
***
    Traceback (most recent call last):
      File "X:\Stable-Diffusion\modules\safe.py", line 83, in check_pt
        with zipfile.ZipFile(filename) as z:
      File "X:\Stable-Diffusion\python\lib\zipfile.py", line 1267, in __init__
        self._RealGetContents()
      File "X:\Stable-Diffusion\python\lib\zipfile.py", line 1334, in _RealGetContents
        raise BadZipFile("File is not a zip file")
    zipfile.BadZipFile: File is not a zip file

    During handling of the above exception, another exception occurred:

    Traceback (most recent call last):
      File "X:\Stable-Diffusion\modules\safe.py", line 137, in load_with_extra
        check_pt(filename, extra_handler)
      File "X:\Stable-Diffusion\modules\safe.py", line 104, in check_pt
        unpickler.load()
    _pickle.UnpicklingError: persistent IDs in protocol 0 must be ASCII strings

---

*START OF TRACEBACK*
Traceback (most recent call last):
  File "X:\Stable-Diffusion\extensions\deforum-for-automatic1111-webui\scripts\deforum_helpers\run_deforum.py", line 78, in run_deforum
    render_animation(args, anim_args, video_args, parseq_args, loop_args, controlnet_args, root)
  File "X:\Stable-Diffusion\extensions\deforum-for-automatic1111-webui\scripts\deforum_helpers\render.py", line 110, in render_animation
    depth_model = DepthModel(root.models_path, device, root.half_precision, keep_in_vram=keep_in_vram, depth_algorithm=anim_args.depth_algorithm, Width=args.W, Height=args.H,
  File "X:\Stable-Diffusion\extensions\deforum-for-automatic1111-webui\scripts\deforum_helpers\depth.py", line 32, in __new__
    cls._instance._initialize(models_path=args[0], device=args[1], half_precision=not cmd_opts.no_half, keep_in_vram=keep_in_vram, depth_algorithm=depth_algorithm, Width=Width, Height=Height, midas_weight=midas_weight)
  File "X:\Stable-Diffusion\extensions\deforum-for-automatic1111-webui\scripts\deforum_helpers\depth.py", line 48, in _initialize
    self._initialize_model()
  File "X:\Stable-Diffusion\extensions\deforum-for-automatic1111-webui\scripts\deforum_helpers\depth.py", line 63, in _initialize_model
    self.midas_depth = MidasDepth(self.models_path, self.device, half_precision=self.half_precision, midas_model_type=self.depth_algorithm)
  File "X:\Stable-Diffusion\extensions\deforum-for-automatic1111-webui\scripts\deforum_helpers\depth_midas.py", line 35, in __init__
    self.load_midas_model(models_path, self.midas_model_filename)
  File "X:\Stable-Diffusion\extensions\deforum-for-automatic1111-webui\scripts\deforum_helpers\depth_midas.py", line 42, in load_midas_model
    self.midas_model = DPTDepthModel(
  File "X:\Stable-Diffusion\extensions\deforum-for-automatic1111-webui\scripts\deforum_helpers\src\midas\dpt_depth.py", line 163, in __init__
    self.load(path)
  File "X:\Stable-Diffusion\extensions\deforum-for-automatic1111-webui\scripts\deforum_helpers\src\midas\base_model.py", line 13, in load
    if "optimizer" in parameters:
TypeError: argument of type 'NoneType' is not iterable
*END OF TRACEBACK*

User friendly error message:
Error: argument of type 'NoneType' is not iterable. Check your schedules/ init values please. Also make sure you don't have a backwards slash in any of your PATHs - use / instead of \.
2023-07-19 18:17:23,179 - httpx - INFO - HTTP Request: POST http://127.0.0.1:7860/api/predict "HTTP/1.1 200 OK"
2023-07-19 18:17:23,181 - httpx - INFO - HTTP Request: POST http://127.0.0.1:7860/reset "HTTP/1.1 200 OK"
Deforum extension for auto1111 webui, v2.4b
Git commit: 858c4dd6
Saving animation frames to:
X:\Stable-Diffusion\outputs/img2img-images\Deforum_20230719181812

*START OF TRACEBACK*
Traceback (most recent call last):
  File "X:\Stable-Diffusion\extensions\deforum-for-automatic1111-webui\scripts\deforum_helpers\run_deforum.py", line 78, in run_deforum
    render_animation(args, anim_args, video_args, parseq_args, loop_args, controlnet_args, root)
  File "X:\Stable-Diffusion\extensions\deforum-for-automatic1111-webui\scripts\deforum_helpers\render.py", line 110, in render_animation
    depth_model = DepthModel(root.models_path, device, root.half_precision, keep_in_vram=keep_in_vram, depth_algorithm=anim_args.depth_algorithm, Width=args.W, Height=args.H,
  File "X:\Stable-Diffusion\extensions\deforum-for-automatic1111-webui\scripts\deforum_helpers\depth.py", line 26, in __new__
    model_deleted = cls._instance and cls._instance.should_delete
AttributeError: 'DepthModel' object has no attribute 'should_delete'
*END OF TRACEBACK*

User friendly error message:
Error: 'DepthModel' object has no attribute 'should_delete'. Check your schedules/ init values please. Also make sure you don't have a backwards slash in any of your PATHs - use / instead of \.
2023-07-19 18:18:12,869 - httpx - INFO - HTTP Request: POST http://127.0.0.1:7860/api/predict "HTTP/1.1 200 OK"
2023-07-19 18:18:12,871 - httpx - INFO - HTTP Request: POST http://127.0.0.1:7860/reset "HTTP/1.1 200 OK"
reading custom settings from deforum_settings.txt
The custom settings file does not exist. The values will be unchanged.
2023-07-19 18:33:42,794 - httpx - INFO - HTTP Request: POST http://127.0.0.1:7860/api/predict "HTTP/1.1 200 OK"
2023-07-19 18:33:42,796 - httpx - INFO - HTTP Request: POST http://127.0.0.1:7860/reset "HTTP/1.1 200 OK"

Additional information

No response

[sal562]

same but on mac
Error: 'Init image path or mask image path is not valid'. Check your schedules/ init values please. Also make sure you don't have a backwards slash in any of your PATHs - use / instead of \. Full error message is in your terminal/ cli.

if i uncheck "use depth warping" it works. But i would assume depth warping would be a cool effect so i would like to enable this if possible

[jinnaluo0]

find this file then open: sd-webui\extensions\deforum-for-automatic1111-webui\scripts\deforum_helpers\depth.py
find this code line:model_deleted = cls._instance and cls._instance.should_delete
changed it to: model_deleted = cls._instance and True
save this file

restart the webui server,try it again.