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
19 shown of 42,234
Face Emotion Detection
This model is a fine-tuned version of google/vit-base-patch16-224 for facial expression recognition on the FER2013 dataset.
HiDream O1 Image Dev 2604 FP8
This is the FP8 mixed-precision quantization of HiDream-ai/HiDream-O1-Image-Dev-2604 — the updated distilled Dev variant of HiDream-O1-Image released May 13, 2026 — for use with ComfyUI. At only 10 GB VRAM and 28...
Randy StarFru1T artist
Training on Randy StarFru1T art maker.
Mel Roformer Kim Vocal 2 Mlx
This model was converted to MLX format from KimberleyJSN/melbandroformer using a custom Mel-Band-RoFormer MLX port (the Blaizzy/mlx-audio PR + the xocialize/mel-roformer-mlx-swift Swift consumer). Refer to the...
I can't believe is not Kegant
I can't believe is not Kegant
MiniCPM O 4 5 GPTQ
> This repository hosts the GPTQ (W4A16, GPTQModel) quantized version of MiniCPM-o 4.5. For the original BF16 weights and the full model card, please refer to openbmb/MiniCPM-o-45.
Tokenizer Titok L32 Imagenet
This model has been pushed to the Hub using the PytorchModelHubMixin integration: Library: [More Information Needed] Docs: [More Information Needed]
Kaguya Houraisan (Touhou Project) - 蓬莱山輝夜 (東方)
Kaguya Houraisan from Touhou Project
Mediapipe Selfie Segmentation
If you haven't already, you can install the Transformers.js JavaScript library from NPM using: npm i @huggingface/transformers
Dee Vicious
Dee Vicious V3 added June 26th 2024
Qwen3.6 35B A3B Uncensored HauhauCS Aggressive Ollama
Note from braydenh563: Q4KM is still Q4KP but just renamed so that I can pull it directly into ollama. Same for the others.
Minimalist T2I Workflow for WAN Video 2.2
✅ this one → Minimalist T2I Workflow for WAN Video 2.2 (Hugging Face)
Gemma 4 12B It Uncensored Ara Refusals2 GGUF
| Parameter | Value | | startlayerindex | 23 | | endlayerindex | 43 | | preservegoodbehaviorweight | 0.2271 | | steerbadbehaviorweight | 0.0001 | | overcorrectrelativeweight | 0.1443 | | neighborcount | 13 |
Text Super Resolution GGUF
Lightweight super-resolution and image restoration models converted to GGUF for CrispEmbed OCR preprocessing.
Text Line Combine
Text line combine is both, a new node, and a workflow that combines text together, line by line.
ControlNet Seg Room
Big thanks to Google for lending us TPUv4s to train this model on. Big thanks to the Huggingface and Diffusers team for organising the JAX Diffusers sprint, giving support and making the JAX training scripts. Big...
FREE AI Hug Video Generator! How to Make Two People from Different Photos Hug with ComfyUI — v1.0
Check the video for how to use the workflow
女児服
ロラの強度は0.4~0.6が推奨 鞄も生成されますが、安定しないです。
Depth Anything Vitl14
The model card for our paper Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data.
