Comfyui Workflow (Image Generation)
required Custom Nodes:
ComfyUI_Eclipse: Version 2.3.13, ComfyReg (Nodes 2.0 compat, V3 API)
ComfyUI_SmartLML: Version 2.3.14, ComfyReg (Nodes 2.0 compat, V3 API)
added fast bypasser etc. from rgthree to eclipse (v3, nodes 2.0 compat)
if you need help installing nunchaku or how to use the nodes check the readme files in the repo readme folder at github.
llama-cpp-python is needed for the loading_method: GGUF (llama-cpp-python) in the Smart LML Node
nunchaku wheels:
nunchaku model files:
Wildcards
Description
reuploaded: because there is a difference in the file size when exporting the workflow with the "new" menu and with the legacy layout. uploaded the legacy output.
i've also changed the save behavior of the initial render. the image is now saved when you continue instead of saving all images. (That was a backup for me because I sometimes forgot to fix the seed. But since both seeds are now in the initial render group, that's probably no longer necessary.)
this version requires RvTools version 1.0.25
i did a lot of changes to both smartloader, improved template handling and lora support (model only)
all groups are reworked and the workflow is basicly finished (final) but the controlnet groups is not finally finished.