20261101@1910EST: 9.4.1 is released as a hotfix for 9.4 issue with muting Stage0.
Simpler version of my now retired "Combined Workflow" split into three workflows.
## "combined"
This is the primary image generator that has supports for multiple image models for sampling (with about 500 custom nodes)
The workflow include an optional model resampler, VOSR2 upscalers, and Face and Eyes detailers.
See the embedded READ ME FIRST for usage details.
## "ModelTools"
Designed to be used with the original generation model, this workflow provide acces to 2x Model resamplers, an Inpainting detailers, SAM detailers with small/large distinction and a final VOSR2 upscaler (about 250 custom nodes).
See the embedded READ ME FIRST for usage details.
## "AltModelResampler"
Designed to be used with any image, this workflow will allow resampling of the intput image usign Flux1.D or Krea2 with some LoRAs and can create very different results from the source image (about 200 custom nodes).
See the embedded READ ME FIRST for usage details.
Description
I am still working on it, and I want to update the side workflows for the final release, but it is working and I want to share for people to try it out. The final v9.4 will be out when I am ready with it.
Added Klein.3 and MOSS Image generations (need ComfyUI 0.41.3 at minimum)
Added a CLIP method (same one as is used for MOSS) for LLM generation
Making use of great nodes by @lonecatone23 (might have to install from git, check his account for details)
Replaced initial upscaler to use VOSR2 at 2x (ie 4x the MegaPixels)
Optional Face and Eyes Detailers (yes the same feature I add in the very large original combined workflow but without the small/regular size logic, this one is still present in the other workflow present in 9.3). Those are recommended for SDXL/Pony/Illustrious and in some case Anima, but I have not needed them for the other models supported.
Optional final upscale: also VOSR2 at 2x