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
update Eclipse to 1.0.81
fixed the group: load image from folder, added my new node LoadImageFromFolder (it was already broken in the last version, i just didn't noticed)
replaced sdxl prompt styler with my new node Prompt Styler wich basicly does the same but allows to switch the style_mode from tags to natural language. it also allows you to create your own files, they are loaded at startup
location is comfyui\models\eclipse\styles
replaced all ReplaceString v2 nodes with the latest version ReplaceString v3
added a replacestringv3 to the detailer: tiles to remove the image description and shot style because they are not needed for the description of tiles imo but you can change that.
all Smart LML v2 nodes are set to huggingface, if a model doesn't exists the node will download it automaticly. for florence2 models it checks models\florence2 first. the standard template is updated after this with the local path.