Skip to content

Resource directory

Find what you need for your workflow.

Guides: techniques, setup, and troubleshooting

Search 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 41,869

Node packGitHub

minimax_h3_novel_pipeline

Provide concise instructions for AI coding agents to implement a ComfyUI plugin that reproduces the behavior of the three-step novel reference pipeline in this repository as ComfyUI nodes

Status
ListedC
ModelCivitai

Hair Style Fixers - FemShortHair

WARNING: I can't guarantee how well these work, it largely DEPENDS on the model. Because they are EMBED/prompts rather than loras or trained TI's - it depends on the model's feelings and mood.

TextualInversionSD 1.5
Status
ListedB
ModelCivitai

SD 1.5: Fixer Ti Set (Negative Embeddings) - DrafterNeg

These are Fixer TI's like AntiChild, DrafterNeg etc - now including a BARELY working Bad hands negative version.

TextualInversionSD 1.5
Status
ListedB
ModelCivitai

Oksana Ivanova MXAI

Oksana is a lovely figment of the AI's imagination, trained on 140 prompted images.

TextualInversionSD 1.5
Status
ListedB
WorkflowExternal source

Foton's Workflow with ControlNet upscale — v1.2

Added CFG Skimming and better metadata collection for Civitai uploads.

UpscalingIllustrious
Status
ListedB
ModelCivitai

[noob] Artist Style: Pottsness

trained on artwork by illustrator:Pottsness

LoConNoobAI
Status
ListedB
ModelCivitai

Tyrannosaurus Rex Fun

A fun little model for creating T-Rexes.

LORAIllustrious
Status
ListedB
ModelCivitai

Susana (Wii Sports Resort)

Susana is the CPU Mii from the Wii generation. (Wii Sports Resort and Wii Party).

LORAIllustrious
Status
ListedB
ModelHugging Face

Git Base Vqav2

GIT (short for GenerativeImage2Text) model, base-sized version, fine-tuned on VQAv2. It was introduced in the paper GIT: A Generative Image-to-text Transformer for Vision and Language by Wang et al. and first...

Text model
Status
ListedB
WorkflowCivitai

WAN-Animate Character Animation Tutorial | 5 Easy Steps in ComfyUI #wananimate #comfyui — v1.0

WAN-Animate Character Animation Tutorial | 5 Easy Steps in ComfyUI #wananimate #comfyui #wananimate

Image to imageWan 2.1
Status
ListedB
Node packGitHub

ComfyUI-kokoro

Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With...

Status
ListedC
ModelCivitai

Ahoge Hornball Face

Drooling, blush, crazed but not entirely horny - i mean you could be in the throws of the Flu WE DONT KNOW - MAYBE you've lost the plot - WE DONT KNOW.

TextualInversionSD 1.5
Status
ListedB
ModelCivitai

Hiro from Camp Buddy [IllustriousXL]

Reviews, Hearts, Likes etc. are very appreciated!

LORAAnima
Status
ListedB
Node packGitHub

ComfyUI-ContextAnchoredTileRefine

Seamless tiled refinement and upscaling for ComfyUI. The VL nodes step all tiles on one shared latent, conditioned by vision tokens and per-tile captions instead of a prompt, so objects never repeat across tiles....

Status
ListedB
WorkflowCivitai

ComfyUI - Sd1.5 & SDXL Upscale workflow (Simple ,Basic)

This workflow is designed to be directly applied in ComfyUI and serves as an upscale workflow.

MultiSDXL 1.0
Status
ListedB
Node packGitHub

ComfyUI-MechaBaby-WorkflowTracer

Efficient Path Tracing & Workflow Optimizer for ComfyUI. Visualize node execution sequences and timing instantly. Convert active execution paths into simplified workflows to eliminate clutter and unorganized...

Status
ListedC
ModelCivitai

Mexican Mix (Experimental)

This embedding was trained on one image each of 55 beautiful Mexican women.

TextualInversionSD 1.5
Status
ListedB
WorkflowCivitai

MPI Random Prompt Gen — v3.1

Check earlier versions for more examples!

MultiSDXL 1.0
Status
ListedB
WorkflowExternal source

FireRed Image Edit 1.1 and Qwen Image Edit 2511 ComfyUI Workflow by Smittie — v1

initial release

Image editQwen
Status
ListedB
ModelCivitai

Wuyang - Overwatch [NoobAI-XL]

Wuyang Ye character DoRA trained on NoobAI-XL (NAI-XL) EPS 1.1 Version .

DoRANoobAI
Status
ListedB