Optimizations that might break things/lower quality will be put behind
this flag first and might be enabled by default in the future.

Currently the only optimization is float8_e4m3fn matrix multiplication on
4000/ADA series Nvidia cards or later. If you have one of these cards you
will see a speed boost when using fp8_e4m3fn flux for example.

Now you can load text encoders straight from a list of state dicts.

--reserve-vram 1.0 for example will make ComfyUI try to keep 1GB vram free.

This can also be useful if workflows are failing because of OOM errors but
in that case please report it if --reserve-vram improves your situation.

* Update config.yml

* Typos

* Update README to include frontend section

* nit

It fixed some perf issues but caused other issues that need to be debugged.

* Add Flux model support for InstantX style controlnet residuals

* Refactor Flux controlnet residual step to a separate method

* Rollback minor change

* New format for applying controlnet residuals: input->double_blocks, output->single_blocks

* Adjust XLabs Flux controlnet to fit new syntax of applying Flux controlnet residuals

* Remove unnecessary import and minor style change

Some branches with VAELoader -> VAEDecode -> Preview were being executed
last. With this change they will be executed earlier.

* add taef1 handling to several places

* remove guess_latent_channels and add latent_channels info directly to flux model

* remove TODO

* fix numbers