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
20 shown of 35,133
comfyui-ppwc
This extension offers wildcard prompting works solely in workflow.
Milani Vicious
MILANI VICIOUS Step aside, culinary legends, because 19-year-old Milani Vicious from Italy is redefining the art of pasta-making with a level of innovation that will leave you questioning your taste buds. When not...
ComfyUI-RDNA35-Attention
RDNA 3.5 optimized attention backends for ComfyUI, including fixed-block and PISA paths.
ComfyUI-AudioTools
A set of nodes to enhance and normalize audio
comfyui-save-with-exif
ComfyUI node to save images while copying EXIF metadata from a source image
comfyui-BatchNameLoop
iterates over a folder of images and passes the name to the batch save node.
ForgeAI-HeartMuLa
All-in-one ComfyUI Node for HeartMuLa Quantized 4bit or 8bit
negative_prompt
Place in negative prompt field. DO use negativeprompt with a VERY strong negative TEXT prompt- DO NOT use on its own. DOES NOT combine well with other bad image negative embeddings. DOES work with bad hands v5 on...
WAS_Extras
Experimental nodes, or other random extra helper nodes.
liquid oil emulsion
This Motion LoRA ist trained on the movement of a Oil water emulsion. Works best with Photonv1 and epicrealism model (SD1.5) - Use eulerA and simpel scheduler. For base aspect ratio I would recommend 576x320 to get...
ComfyUI-WanMoeKSampler
Modification of the KSampler for running models like Wan2.2 a14B
ComfyUI-StrokeReveal
A ComfyUI custom node that creates an animated stroke reveal effect
ComfyUI-Keyframe
ComfyUI Nodes,set denoise strength for keyframe
ComfyUI-Chaser-nodes
Chaser's personal ComfyUI custom node repo
tropical-island
This Textual Inversion has trained publicly available images of Tropical Island with a Stable Diffusion 1.5 with 12 images at a scale of 512x512.
[SDXL] Artist Style: kanzarin
SDXL LoRA/LyCORIS works best on the model that it was trained on. I will release multiple versions for a few popular models. Feel free to request for artist or model.
Desolation
A hypernetwork I trained on anime/painterly style post-apocalypse and cyberpunk images. I was going for a Lain/Dorohedoro/Texhnolyze kind of feel. This works great on semi-realistic models and anime models.
Semi-Realistic Digital Concept Art - [STYLE] [LORA] [FLUX]
Latest page update: Updated recommended workflow again to a version 2, which is slightly even better.
ancient-ruin
This Textual Inversion has trained publicly available images of Ancient Ruins with a Stable Diffusion 1.5 with 12 images at a scale of 512x512.
Rina's Robo Faces v2
Updated with v2! The first version had some shortcomings, namely the strong asian predilection of facial features, and being tricky to trigger. The new embedding works better, and also produces crisper lines in many...
