* Update installation documentation.

* Add portable to description.

* Move cli further down.

Changes release schedule from weekly to fortnightly.

* Normalize extra_model_config.yaml paths before adding.

* Fix tests.

* Fix tests.

* Fix link pointing to non-exisiting docs

The current link is pointing to a path that does not exist any longer.
I changed it to point to the currect correct path for custom nodes datatypes.

* Update node_typing.py

https://github.com/comfyanonymous/ComfyUI/issues/6038#issuecomment-2661776795
https://github.com/comfyanonymous/ComfyUI/issues/5814#issue-2700816845

The change to support 32 channel hunyuan models is missing the `key_prefix` on the key.

This addresses a complain in the comments of acc152b6.

The frontend part isn't done yet so there is no video preview on the node
or dragging the webm on the interface to load the workflow yet.

This uses a new dependency: PyAV.

* add LoadImageOutput node

* add route for input/output/temp files

* update node_typing.py

* use literal type for image_folder field

* mark node as beta

* Support SkyReels-V1-Hunyuan-I2V

* VAE scaling

* Fix T2V

oops

* Proper latent scaling

Let me know if this slows things down on 2000 series and below.

* support system prompt and cfg renorm in Lumina2

* fix issues with the ruff style check

Co-authored-by: huchenlei <20929282+huchenlei@users.noreply.github.com>

Co-authored-by: huchenlei <20929282+huchenlei@users.noreply.github.com>

I'm not not sure which arches are supported yet. If you see improvements in
memory usage while using --use-pytorch-cross-attention on your AMD GPU let
me know and I will add it to the list.

* Using utf-8 encoding for yaml files.

* Fix test assertion.

Currently only works for diffusion models.

There is no way to check if the card actually supports it so it assumes
that it does if you use --use-pytorch-cross-attention with yours.

Functions can now easily be added to wrap/modify model weights.

* Fix for running via DirectML

Fix DirectML empty image generation issue with Flux1. add CPU fallback for unsupported path. Verified the model works on AMD GPUs

* fix formating

* update casual mask calculation