Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
Resource directory
Search Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.
Start with a workflow instead ↗Search results
16 shown of 34,597
Img2img+face detailer workflow(Flux/Illustrious),and you can compare the result before/after the face refine. I tested with several checkpoints,this workflow fits better with:
This a very short and simple workflow to upscale and enchance images. Barely a workflow, but for someone just starting out, it nice to have prepared.
Update for new embeddings placement
(This is not an exhaustive changelog)
Welcome to the official repository for Chenkin-UniControl-XL !
Update Jun 5, 2026: ☁️ Deploy Chronos-2 on AWS with AutoGluon-Cloud. Real-time, serverless, or batch inference in 3 lines of code — pandas DataFrames in, forecasts out. Check out the new deployment guide.
Join my Discord for everything related to anime models and AI art. If you’d like to support my work, you can do so on SubscribeStar Every bit helps me continue making AI models and even an AI VTuber, which is...
This workflow works fine with 8GB VRAM, if you have a better card, you might want to disable the Lightning LoRA, add more steps, and cfg to every KSampler. Maybe 20 steps and cfg 2.5? You should try. Unlike the...
As it says in the title, this is a simple workflow for changing the colors of the area covered by the mask. 7-10 different nodes used several times and connected together. Nothing special, but I think that this...
This is a 9 column prompt grid for SDXL/PonyXL with LoRA support. It generates 9 images based on 1 seed and the 9 prompts that you enter. It has an on/off toggle for each column in case you don't need to use all of...
Decided to make a cleaner and upgraded version of my workflow. Works with any model, but it may require tweaking for some models (I think)
fast yet good image. intended for wainsfw v13, may not work with other checkpoints
From my personal experience the quality difference with Comfy-Org FP8 isn't huge at first glance, but the subtle improvements in details grew on me over time, now I clearly notice them when using Kijai quantizations...
A lightweight ComfyUI custom node pack for Qwen3-ASR, providing simple speech‐to‐text workflows with local model caching and optional timestamp output. Supports Qwen/Qwen3‐ASR‐1.7B and 0.6B, with...
Taking advantage of a new node
