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 41,797
ComfyUI batch img to txt file — Florence2 Batch ImgToTxt
Using Florence2 in ComfyUI to batch extract prompts from images and output them as a txt file
WAN-VACE (Dual Image Reference) — v1.0
Want to know what this workflow actually does and how to start fast? This video explains what the tool is, how to launch the workflow instantly, and shares my core design logic — no local setup, no complicated...
Sora2 Quality Restoration (Video image quality repair workflow) — v1.0
Powered By RTX 4090 Series
Sonie+Cosyvoice 2 Digital Human Singing Workflow — v1.0
The workflow is very simple to use, and I have uploaded a tutorial on how to use it on YouTube. You can try it out and follow the tutorial and Civitai's workflow to easily reproduce the results. Thank you. If you...
ComfyUI | A Simple general image generation workflow with upscale latend and SD upscale — v2.5
im posting this as v2.5 because its not the first version i used, this one is just the best one.
(Zhi Lao Open Source) Qwen+Edit Pixel Offset Issue Solution V1 — v1.0
You can click on the link below and try it out directly. If the effect is good, you can deploy it locally
🎵HeartMuLa🎵最新最强开源音乐生成11 — v1.0
If your local computer cannot run or you want to experience the effect before downloading, please use the link below to run it online for free.
Lucy+Edit Video Editing (Object Addition) — v1.0
You can click on the link below and try it out directly. If the effect is good, you can deploy it locally
Type-and-Run Generator for Anima — v1.0
Initial release of the workflow. Should run on any hardware no problem, given all required files are installed.
DaSiWa Wan2.1 I2V Workflows — FastFidelity C-AiO 2.0
🧩 Automatic aspect‐ratio calculation and fitting
Qwen+Edit+2511 Mask+Image Editing V1 (No Offset) — v1.0
You can click on the link below and try it out directly. If the effect is good, you can deploy it locally
Flux2_Klein_Image Editing & Text Removal (6G VRAM can run it!) — v1.5
Flux2KleinImage Editing & Text Removal (6G VRAM can run it!)
SDTune - Tuned IP Adapter Workflow for ComfyUI — v2.2
Updated Derfuu Text Boxes
EchoShot – Cross-Shot Consistency — v1.0
Want to know what this workflow actually does and how to start fast? This video explains what the tool is, how to launch the workflow instantly, and shares my core design logic — no local setup, no complicated...
Magic-Wan-V2 accelerated tiled ultra-resolution upscaling — v1.0
This workflow is built to combine the speed of the accelerated Wan 2.2 four-step model with the precision of multi-tile ultra-resolution reconstruction. The image is first processed through Magic Wan 2.0’s...
KJ version of the new Hybrid Tousen Video Character Consistency Workflow — v1.0
The workflow is very simple to use, and I have uploaded a tutorial on how to use it on YouTube. You can try it out and follow the tutorial and Civitai's workflow to easily reproduce the results. Thank you. If you...
HuMo+InfiniteTalk Single-Person Reference Digital Population Model Stable Revised Version — v1.0
You can click on the link below and try it out directly. If the effect is good, you can deploy it locally
Precise image control (control composition/color matching/face/Checkpoints fusion/LoRA fusion) — v1.0
Workflows that allow you to precisely control the position of a person in the frame, their proportion, the tone of the picture, and the facial features of the person.
Wan_2.2_FMLF Multi-frame First and Last Frames — v1.0
you can click on the link below and try it out directly. If the effect is good, you can deploy it locally
Artifact Combo! HunYuanCombo Accelerated Dolora HD Repair Workflow V3 — v1.0
The workflow is very simple to use, and I have uploaded a tutorial on how to use it on YouTube. You can try it out and follow the tutorial and Civitai's workflow to easily reproduce the results. Thank you. If you...
