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 42,211
TTPLanet SDXL ControlNet Tile Realistic V1
This model is a copy of It is hosted here (with files renamed) for compatibility with InvokeAI.
Qwen3.5 4B Base ZitGen V1 GGUF
For a convenient overview and download list, visit our model page for this model.
Fasternet M Coco 256x192
A 2D human pose estimation model trained at DeKUT-DSAIL using the MMPose framework. Predicts 17 COCO keypoints from a single cropped person image.
KazEGA Hubert
Multi-task HuBERT model for Kazakh speech, jointly predicting emotion, gender, and age from raw audio. Trained on the KazEGA corpus.
Euroset Resnet50
ResNet50 fine-tuned via transfer learning to classify Sentinel-2 satellite image patches into 10 land cover categories, using the EuroSAT dataset.
KhanhTTS OmniVoice GGUF
Đây là phiên bản lượng hóa (quantized) định dạng GGUF của mô hình kjanh/KhanhTTS-OmniVoice.
Vits Piper Pt PT Dii High
This model is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0).
Sana 600M ControlNet HED Smashed
This model was created using the pruna library. Pruna is a model optimization framework built for developers, enabling you to deliver more efficient models with minimal implementation overhead.
Qwen3.5 0.8B Base Mmproj GGUF
This is an mmproj GGUF of Qwen/Qwen3.5-0.8B-Base created using llama.cpp.
Depth Head Kitti
Monocular depth estimation head trained on KITTI (RMSE: 2.79). Part of A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens (CVPR 2026 Highlight).
Ground3D LMM CAVQA 4B Joint
Fine-tuned Ground3D-LMM checkpoint for CA-VQA (paper Table 9 — generality beyond ScanNet), 3D+2D (point cloud + RGB views) setting. Reproduces the paper's Table-9 average (48).
2xHFA2k LUDVAE SPAN
Name: 2xHFA2kLUDVAESPAN Author: Philip Hofmann Release Date: 26.12.2023 License: CC BY 4.0 Network: SPAN Scale: 2 Purpose: A lightweight anime 2x upscaling model with realistic degradations, based on musl's...
LibreResNet50 Cls
ResNet-50 image classifier (224px, ImageNet-1k, 1000 classes), repackaged for LibreYOLO. 25.6M parameters.
RealESR Gx4 FP16
RealESRGx4fp16 is an ONNX export of a Real-ESRGAN-based super-resolution model designed for general-purpose 4× image upscaling.
SAGE
Official checkpoints for SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition.
Sam ControlNet
These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning. You can find some example images below. prompt: Horses graze in front of a large building amid snow. prompt: some...
Hijab Person Rfdetr
RF-DETR (DINOv2 backbone) person detector exported to ONNX, used by the people viscom in the vidiomatic CV platform. Private / internal (nextoar) — do not redistribute.
ArSL Models
Two PyTorch models for Arabic Sign Language (ArSL) recognition, used by the CSLR app (deployed as a Hugging Face Space):
Pedsense Yolo26m Pose Jaad 10e
A pedestrian keypoint detection model fine-tuned on the JAAD (Joint Attention in Autonomous Driving) dataset using the PedSense-AI framework. Detects pedestrians and predicts 17 COCO body keypoints per person.
ControlNet Inpainting Shuffle Processedpromp Changemask Condition Random Mask
These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning. You can find some example images below.
