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
updated the custom node v1.0.22
beta version, not every group may function properly
reuploaded:
with another small fix, if the negative prompt is disabled, the detailer tile is using a dummy "watermark" so no false negative prompt is saved to the image metadata anymore because it can be empty now.
updated the image load group to use the prompt (allows to bypass all nodes in the prompt group or advance the prompt loaded from the image) updated the note in this group
replaced patch torch settings with cfgzerostar in the detailers.
apart from the controlnet group all groups are checked/reworked and seem to work correctly now :P
leave a comment if you have issues somewhere