Resource directory
Find what you need for your workflow.
Guides: techniques, setup, and troubleshootingSearch Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.
Start with a workflow instead ↗Search results
All resources
14 shown of 35,315
ComfyUI-QuickWatermark
A simple ComfyUI node for adding a watermark to a video
Comfyui-AudioSegment
Custom node suite for ComfyUI designed for advanced audio processing
Sasha Nobody
Follow me to make sure you see new poses and Nobodys when I post them. Things move fast on this site, it's easy to miss.
IP Adapter XY Plot — NOOB_IPA
XY Plot of IP Adapter parameters
Colorful Burst
Colorful Burst is a style-focused LoRA designed to transform images into emotionally charged, high-contrast compositions where motion, emotion, and color collide . It excels at turning moment, quiet or explosive ,...
comfyui-reference-image-comparer
ComfyUI node: compare workflow output against a fixed reference image with a swipe slider
Airbag Deploy
Combines both datasets though I kept them prompted for LTX/Wan. Will redo at some point. But it works as is, fairly straight forward to use. AirbagDeploy is the trigger but you don't really need it. H3 has a good...
Endless_Up_SDXL_Neg
Improve the plastic feel of SDXL image quality, adjust the intensity from 0.1 to 2, and adjust the CFG value. (Strength 0.9, CFG34)
comfyui-yolo-pose
Generic YOLO-Pose keypoint detector node for ComfyUI: image -> keypoints JSON (to /history).
comfy_nanobanana
For calling gemini api directly with your api key
Ligne Claire (Mœbius-Jean Giraud) - [STYLE] [LORA] [FLUX]
Latest page update: Updated recommended workflow again to a version 2, which is slightly even better.
ComfyUI_SelectiveMetadata
Allows for Selective Saving of Metadata to Images Generated in ComfyUI
Yu-jin Nobody
Follow me to make sure you see new poses and Nobodys when I post them. Things move fast on this site, it's easy to miss.
Danganronpa Anime Style Mix
Short gist: Lora trained on the various Danganronpa anime. Version 1 of the lora is more averaged out between entries. Version 2's training data has Danganronpa 2.5: Nagito Komaeda and the World Vanquisher as the...
