GitLab

It is based on: https://arxiv.org/abs/2407.12173

Add "beta" to the list of schedulers and the BetaSamplingScheduler node.

* Update samplers.py

* Update model_patcher.py

The old _pp ones will be updated automatically to the regular ones with 2x
the cfg.

My fault for not checking what the "_pp" samplers actually did.

Order 4 seems to give bad results.

Add euler_ancestral_pp which is the ancestral version of euler with the
same modification.

calc_cond_batch can take an arbitrary amount of cond inputs.

Added a calc_cond_uncond_batch wrapper with a warning so custom nodes
won't break.

* Implement Differential Diffusion

* Cleanup.

* Fix.

* Masks should be applied at full strength.

* Fix colors.

* Register the node.

* Cleaner code.

* Fix issue with getting unipc sampler.

* Adjust thresholds.

* Switch to linear thresholds.

* Only calculate nearest_idx on valid thresholds.

Use ModelSamplingContinuousEDM with edm_playground_v2.5 selected.

This causes some small changes to the uni pc inpainting behavior but it
seems to improve results slightly.

self.scheduler -> scheduler_name
Co-authored-by: Lt.Dr.Data <lt.dr.data@gmail.com>

Moved all the sag related code to comfy_extras/nodes_sag.py

* First SAG test

* need to put extra options on the model instead of patcher

* no errors and results seem not-broken

* Use @ashen-uncensored formula, which works better!!!

* Fix a crash when using weird resolutions. Remove an unnecessary UNet call

* Improve comments, optimize memory in blur routine

* SAG works with sampler_cfg_function