Derp Learning

For people having ImportError: cannot import name 'packaging' from 'pkg_resources' error:
run this in a new line:
!pip install  setuptools==69.5.1
and restart the notebook

For people having jax error on colab in animatediff mode, run this once, in a new line:

!pip uninstall jax -y

Google Colab has updated its env, so we need to fix a few things for it to work.
For people having pytorch\xformers error (xFormers can't load C++/CUDA extensions) and all sorts of import errors like ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor':
1) run Prepare folders & Install cell
2) check "skip install" after running it
3) add a new code cell below it with this code:

!pip uninstall torch xformers -y
!python -m pip install torch==2.0.1 torchvision==0.15.2 --extra-index-url https://download.pytorch.org/whl/cu118 xformers==0.0.21

and run it.
4) delete or comment that newly added cell to make sure you don't run it every time you restart the env.
5) restart your env and run all as usual

  For people having Softedge controlnet annotator error,download it manually here - https://github.com/Sxela/ControlNet-v1-1-nightly/releases/download/v0.1.0/table5_pidinet.pth and put into  ControlNet\annotator\ckpts\ folder inside you warp folder  

If you're having DWPose error like

Access denied with the following error:

Cannot retrieve the public link of the file. You may need to change

the permission to 'Anyone with the link', or have had many accesses.

Which means that the DWPose author's google drive \ python gdown package user has hit the rate limit.

To fix this you need to manually download the models from  these links: https://drive.google.com/uc?id=12L8E2oAgZy4VACGSK9RaZBZrfgx7VTA2
https://drive.google.com/uc?id=1w9pXC8tT0p9ndMN-CArp1__b2GbzewWI
(the files you download are yolox_l.onnx and dw-ll_ucoco_384.onnx)
or from
https://huggingface.co/yzd-v/DWPose/resolve/main/dw-ll_ucoco_384.onnx
https://huggingface.co/yzd-v/DWPose/resolve/main/yolox_l.onnx

and put them into

ControlNet\annotator\ckpts\

inside your warp folder

If you're getting xformers error on colab about cuda version mismatch:
Google colab env has been updated (their cuda version was bumped from 11.8 to 12.1), so we need to update our dependencies.

I'm rolling a hotfix soon, but for now you can:
add a new code cell after the install cell and before the import dependencies cell, with
!pip install https://download.pytorch.org/whl/cu121/xformers-0.0.22.post4-cp310-cp310-manylinux2014_x86_64.whl#sha256=7075114dbf698b609b599f0d35032c0b2f9a389751e8bbf4dd3c628376b0dd9c
and run once. You may or may not need to restart the session (NOT reset) after that.

Local install guide: https://github.com/Sxela/WarpFusion#local-installation-guide-for-windows-venv.
If something's not working, make a new env and grab a fresh install.bat from that repo first, ask questions later :D

Changelog:

- add FreeU Hack from https://huggingface.co/papers/2309.11497

- add option to apply FreeU before or after controlnet outputs

- add inpaint-softedge and temporal-depth controlnet models

- auto-download inpaint-softedge and temporal-depth checkpoints

- fix sd21 lineart model not working

- refactor get_controlnet_annotations a bit

- add inpaint-softedge and temporal-depth controlnet preprocessors

- fix controlnet preview (next_frame error)

- fix dwpose 'final_boxes' error for frames with no people

- move width_height to video init cell to avoid people forgetting to run it to - update width_height

- fix xformers version

- fix flow preview error for fewer than 10 frames

- fix pillow errors (UnidentifiedImageError: cannot identify image file)

- fix timm import error (isDirectory error)

- deprecate v2_depth model (use depth controlnet instead)

Local install guide: https://github.com/Sxela/WarpFusion#local-installation-guide-for-windows-venv.
A100 or 24 GB card is highly recommended for sdxl.
Make a new env and grab a fresh install.bat from that repo.  

- add dw pose estimator from https://github.com/IDEA-Research/DWPose

- add onnxruntime-gpu install, (update env for dw_pose)

- add dw_pose model downloader

- add controlnet preview, kudos to #kytr.ai

- add temporalnet sdxl - v1 (3-channel)

- add prores thanks to #sozeditit

- make width_height accept 1 number to resize the frame to that size keeping the - aspect ratio

- add cc masked template for content-aware scheduling

- add reverse frames extraction

- move looped image to video init cell as video source mode

- fix settings not being loaded via the button

- fix bug when cc_masked_diffusion == 0

- add a message on missing audio during video export / mute exception

Colab updated its env again 😄

If you're having torch version errors on colab

replace:

!python -m pip -q install xformers==0.0.21

with

!python -m pip -q install https://download.pytorch.org/whl/cu118/xformers-0.0.22.post4%2Bcu118-cp310-cp310-manylinux2014_x86_64.whl

Hard-locking torch version (that will downgrade the existing torch) is a lot slower, but maybe that is still a better option.

thanks to @huemin.art