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 38,710
Rqsa Mil v1
RQSA-MIL (Region-Quality Supervised Attention for Multiple Instance Learning) is a nudity detection model: a MobileNetV2 backbone with a spatial attention gate conditioned on region quality. During training the gate...
SeeGroup
we propose SeeGroup, a multi-layer depth estimation method that allows the model itself to adaptively assign surfaces to depth maps. We formulate per-pixel multi-layer depth as a point process, treating depth layers...
LightningDiT Diffusers
Diffusers-ready checkpoints for LightningDiT (VA-VAE–aligned latent diffusion with flow matching), converted from hustvl/lightningdit-xl-imagenet256-800ep for local/offline use.
Depth LoRA Checkpoints Hypersim Depth Light Hypersim Near High Light
> Base model: metric3dvitgiant2 > loaded via torch.hub.load("yvanyin/metric3d", "metric3dvitgiant2")
Sf3d
stabilityai-ai-community
Cloth ControlNet
These are ControlNet for stable-diffusion-v1-5/stable-diffusion-v1-5. You can find some example images in the following.
SiT Diffusers
Diffusers-ready checkpoints for Scalable Interpolant Transformers (SiT), converted for local/offline use.
LibreYOLO9m
YOLOv9-M weights converted from MultimediaTechLab/YOLO (release v1.0-alpha, file v9-m.pt) to the LibreYOLO format.
Meshanythingv2
This model has been pushed to the Hub using the PytorchModelHubMixin integration: Library: Docs: [More Information Needed]
Nethack Ppo Ablation No Hmm No Intrinsic
This repository contains a complete Sequential Skill RL model trained on NetHack/MiniHack environments.
Strikenet
StrikeNet is the 79k-parameter CNN that pdf-strikethrough-detect uses to resolve pixel-ambiguous strikethrough cases on scanned document pages. A thin strike over an ascender-less word is pixel-identical to an...
Microsam Vit T Lm Onnx
Promptable micro-sam vittlm (TinyViT encoder, via MobileSAM) exported to ONNX for client-side inference with onnxruntime-web + WebGPU, used by the JAX Image Tools viewer (jit-ui#90) SAM segment tool. This is the tiny...
Omar Rq Base Freesound Large
> [!WARNING] This model was trained on Freesound data and intended for research in general sound applications. > It was trained following the large (660M params) architecture from the paper using the multicodebook...
Sam Onnx
ONNX bundle pairing the MobileSAM ViT-T image encoder with Meta's original SAM mask decoder. Together they form a complete Segment Anything pipeline at 60 MB total — orders of magnitude smaller than the original SAM...
Brainscan Tfjs
This repository contains the weights and topology of the BrainScan classification model converted to TensorFlow.js layers format for in-browser client-side execution.
ControlNet Celeb v1 2 8TBlk
These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning.
VCLR
This repository contains the model presented in v-CLR: View-Consistent Learning for Open-World Instance Segmentation.
Asl Citizen Bigru Attention Encoder 200
This repository contains the trained isolated American Sign Language recognition model for the FYP project:
Audiosronnx Dpdfnet
ONNX weights for the dpdfnet denoise engine in audiosronnx — a mirror of Ceva-IP/DPDFNet (Apache-2.0), pinned so the library can resolve a fixed revision.
Htdemucs Ft Bass Onnx
Bass extraction specialist from HT-Demucs FT, packaged as ONNX. 1.31× faster than PyTorch CPU, no PyTorch required at inference.
