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 42,520
Sd15 Inpainting ControlNet Canny FP16
This repository hosts the Sona Forge Phase 8 conversion of the SD 1.5 inpainting UNet to ONNX FP16 with additional ControlNet residual inputs.
Mimi Onnx Streaming
Streaming ONNX models for Kyutai Mimi neural audio codec, exported with explicit convolutional state buffers and transformer KV cache for frame-by-frame processing.
Spee Project Fairhindiser Clues
This repository contains the checkpoints for FairHindiSER, a speech emotion recognition model trained on a 50/50 mix of Hindi (IITKGP) and English (IEMOCAP) emotional speech. The model predicts four emotions: angry,...
Sparsity Anima
Sparsity Anima is an experimental diffusion model based on the Cosmos Predict 2 2B architecture and further fine tuned from the original Anima base model. The model was trained entirely on a single consumer GPU (RTX...
ControlNet 32D 05B Tagged
These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning. You can find some example images below.
Convnext Base.dinov3 Lvd1689m
dinov3-license
Laionbox v0.6 Wip
LoRA fine-tune of the DramaBox audio-only DiT (LTX-2.3-22B-Dev, 3.3B, ResembleAI) for expressive voice-acting TTS. Pure LoRA (rank 256 / alpha 256, 5 epochs) — no AdaLN, no auxiliary losses, just flow matching....
Audiosronnx Callenhancer
Pure-ONNX weights for the callenhancer engine in audiosronnx — call-centre / telephony speech restoration, 16 kHz → 48 kHz.
SeedVR2
Official release of SeedVR2 for ComfyUI that enables high-quality video and image upscaling.
Pictory ControlNet Upsample Edge Lr5e 6 Ep30
This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
Bambi Occlusion Classifiers
Binary clear vs occluded classifiers in an embedding + head design: a raw DINOv3 ViT-H+ embedding goes in, a triplet-loss-trained projection reduces it to a 256-d discriminative embedding, and a logistic head reads...
Piper En US Mira
A free Piper voice (VITS, medium, 22.05 kHz, LJSpeech-derived timbre) with trained non-verbal expressions: real laughs, sighs, gasps, groans, and throat-clears — produced by the vocal model itself, not spliced-in...
LEGO
LEGO is a research detector for binary classification of real and synthetic images. It specializes multiple LoRA branches on different generator families and uses a shared router to compose their residual features.
Confident Splatting
This repository contains the trained models on different sample scenes from various datasets for the paper Confident Splatting: Confidence-Based Compression of 3D Gaussian Splatting via Learnable Beta Distributions.
ToriiGate 0.5 ComfyUI NVFP4
ComfyUI-native NVFP4 safetensors conversion of Minthy/ToriiGate-0.5.
2xParimgCompact
Name: 2xParimgCompact Author: Philip Hofmann Release Date: 05.05.2023 License: CC BY 4.0 Model Architecture: SRVGG Scale: 2 Purpose: 2x Upscale photos based on Microsoft's ImagePairs Iterations: 100'000 batchsize:...
Cephtrace v4
1.050 mm MRE across 25 landmarks on a 151-image held-out test set, using image-adaptive spatial priors generated by anatomical analysis of each radiograph.
Qwen2 VL 7B Instruct Vsft
Qwen2-VL-7B-Instruct model trained on llava-instruct-mix-vsft-mini dataset. It is intended for visual question answering.
Forza Ia
Forza-ia est un modèle d'Intelligence Artificielle unique, conçu pour générer des dessins qui ressemblent à de véritables esquisses d'enfants \! Notre modèle est entraîné à capturer la naïveté, la simplicité et le...
TMoon
3D positional embedding (as in the text encoder replacement, object detection and others) Supports multiple image aspect ratios Contrastive prediction model AIMv2 vision model T5Gemma text encoder Moondream2 dataset
