multiple changes in preperation for 4.4 release

workflows/IMG2IMG/v4.4/changelog.md

@@ -1,6 +1,10 @@
 - implementation of new image loading node (by me) to be able to multi-select one or more images for a run
 - complete overhaul, removal of all group nodes & abstraction through subgraphs
+- replaced the single lora loaders and their 6 activation buttons with rgthree's lora stack loader to load as many as you want (same for detailer loras)
 - fixed v-pred model bug that didn't apply v-parameterization
 - fixed modelname not saving correctly for civitai
+- dynamic prompts/wildcards now supported through Impact-Pack, syntax [here](https://github.com/ltdrdata/ComfyUI-extension-tutorials/blob/Main/ComfyUI-Impact-Pack/tutorial/ImpactWildcard.md) - txt files have to be in folder BEFORE comfy starts to be recognized
+- switch for turning off seperate VAE to use baked-in VAE of checkpoint
 
-_low VRAM for transfer not put into a subggraph yet because of an output bug when bypassed in current comfy versions_
+_low VRAM for transfer not put into a subggraph yet because of an output bug when bypassed in current comfy versions_
+_wanted to add recommended detailer values you can just activate/deactivate (more vram but better results) but this will have to wait 1 version since multiple custom_nodes still have issues with subgraphs_

workflows/IMG2IMG/v4.4/todo.md

@@ -1,6 +1,2 @@
-TODO:
-- Add Area for Detailer settings more prominently
-(guide_size, max_size, feather, cfg, sampler/scheduler, bbox dilation)
-- check dynamic prompts compatibility, S&R {red|blue|green} etc.
-- extra boolean for baked in vae that inject vae from model loader instead
+- Add Area for Detailer settings more prominently (guide_size, max_size, feather, cfg, sampler/scheduler, bbox dilation)
 - check how easy it is to implement a refiner like [this](https://openart.ai/workflows/openart/basic-sdxl-refiner-workflow/Q6n55PcgIumjDRoPmPHX)

workflows/TXT2IMG/v4.4/todo.md

@@ -0,0 +1,10 @@
+TODO:
+- Add Area for Detailer settings more prominently
+(guide_size, max_size, feather, cfg, sampler/scheduler, bbox dilation)
+- check dynamic prompts compatibility, S&R {red|blue|green} etc.
+- extra boolean for baked in vae that inject vae from model loader instead
+- check how easy it is to implement a refiner like [this](https://openart.ai/workflows/openart/basic-sdxl-refiner-workflow/Q6n55PcgIumjDRoPmPHX)
+- check if v-pred model works correctly
+- swap group nodes for subgraphs, turn big major tasks into subgraphs
+- swap lora loader
+- check if modelname saves correctly