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 41,899
ControlNet Inpainting Shuffle Processedprompt
These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning. You can find some example images below.
AnchorSplat 1x
Pretrained 1x checkpoint for AnchorSplat: Fast and Structure Consistent Detail Synthesis for Gaussian Splatting (ECCV 2026).
Koelectra Balanced B
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Naturalist Bioclip v1
On-device model package for the Sylva naturalist app (fungi & plants identification). This repo hosts a swappable model package consumed via a manifest; the app downloads only what the manifest lists.
Text To Image University Model
Developed by: [More Information Needed] Funded by [optional]: [More Information Needed] Shared by [optional]: [More Information Needed] Model type: [More Information Needed] Language(s) (NLP): [More Information...
Dinov3 Vitb16 Pretrain Lvd1689m ONNX
dinov3-license
Kanainet
KAN-AINet is a polyp segmentation architecture that leverages Kolmogorov–Arnold Networks (KAN) for adaptive illumination modulation and boundary-aware attention (MICCAI 2026). Unlike standard neural networks that use...
Murya Piper Hausa Tts
Multi-speaker Hausa text-to-speech, fine-tuned on Google's WAXAL corpus. To our knowledge this is the first TTS model trained on WAXAL-Hausa, the first open multi-speaker Hausa voice model, and the first built by a...
Sd21 ControlNet Circlefill T 50K Epoch 1 Lr 1e 5 Checkpoints 2000
These are controlnet weights trained on Manojb/stable-diffusion-2-1-base with new type of conditioning. You can find some example images below.
Yolo26s Ottoman Printed Line
Model Type: Line Detection Architecture: YOLO26s-seg (Ultralytics) Language: Ottoman Turkish Font/Style: Printed Naskh Task: Segmenting and detecting individual text lines within predefined text regions.
My Finetuned Whisper Model
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
CRC ESD
This repository provides the five patient-level cross-validation checkpoints for research on metastasis-risk prediction after endoscopic submucosal dissection (ESD) in colorectal cancer.
Text To Imagesss
This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
ComfyUI Setup
The repository contains: Z-Image-Turbo models, text encoder, vae Qwen-Image-Edit AIO (by Phr00t) Qwen-Image text encoder, vae Wan2.2 Image to Video models, text encoders, vae Wan2.1 Image to Video 720p distilled...
Cardcaptor v3
Architecture: YOLOv11m with oriented bounding box (OBB) head (7-value outputs: cx, cy, w, h, conf, class, angle) Input resolution: 1088 × 1088 Targets: Single class (tradingcard) with arbitrary rotations Exports:...
Food Depth Senet154
Trained 8 epochs on every 3. frame, batch 8, AMP. Encoder: timm legacysenet154 (stem pool0 included in Esenet). modelsenet.pth — final clean statedict (no module. prefix) checkpointlast.pth — resume checkpoint (model...
FDSpeech VoxCPM2
FDSpeech-VoxCPM2 is the selected compact three-target LoRA adapter from the paper [Fréchet Distance Loss on Speech Representations for Text-to-Speech Synthesis]( It is trained with a Fréchet-distance loss on speech...
ControlNet Bylllyasviel Onnx
Used for Dolls AI human image & video generator Create unlimited, AI generated images and videos — all for free, locally, right on your PC.
ComfyUI Zimage Sulphur NVFP4
An NVFP4-quantized build of Z-Image Turbo plus everything ComfyUI needs to run it, packaged for Blackwell GPUs (RTX 5090, DGX Spark / GB10) where NVFP4 runs natively.
ESPERNet
ESPERNet is a set of AI models for audio-to-audio speech processing. The versions available here have been trained on the Mozilla CommonVoice dataset.
