GitLab

The img2vid model is conditioned on clip vision output only which means
there's no CLIP model which is why I added a ImageOnlyCheckpointLoader to
load it. Note that the unClipCheckpointLoader can also load it because it
also has a CLIP_VISION output.

SDV_img2vid_Conditioning is the node used to pass the right conditioning
to the img2vid model.

VideoLinearCFGGuidance applies a linearly decreasing CFG scale to each
video frame from the cfg set in the sampler node to min_cfg.

SDV_img2vid_Conditioning can be found in conditioning->video_models
ImageOnlyCheckpointLoader can be found in loaders->video_models
VideoLinearCFGGuidance can be found in sampling->video_models

* Add control_filter_list to filter items after queue

* fix regex

* backwards compatibility

* formatting

* revert

* Add and fix test

They will show up if both the taesd_encoder and taesd_decoder or taesdxl
model files are present in the models/vae_approx directory.

* Refactor multiline widget into generic DOM widget

* wip webp preview

* webp support

* fix check

* fix sizing

* show image when zoomed out

* Swap webp checkto generic animated image flag

* remove duplicate

* Fix falsy check

Pytorch supports two variants of fp8:
--fp8_e4m3fn-text-enc (the one that seems to give better results)
--fp8_e5m2-text-enc

Improve diffusers model detection.

By adding a downscale to the unet in the first timesteps this node lets
you generate images at higher resolutions with less consistency issues.

This doesn't affect how percentages behave in the frontend but breaks
things if you relied on them in the backend.

percent_to_sigma goes from 0 to 1.0 instead of 1.0 to 0 for less confusion.

Make percent 0 return an extremely large sigma and percent 1.0 return a
zero one to fix imprecision.