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 38,631
CheX Phi35V
CheX-Phi3.5V is a vision–language model (VLM) that answers clinical questions about chest radiographs and generates structured findings reports. Built on Phi-3.5 Vision-Instruct (7 B), it introduces Direct Preference...
VideoMAE Base Wlasl 100 50ep CoR P10
This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set: Loss: 2.5394 Accuracy: 0.4911
ControlNet Train
These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning. You can find some example images below. prompt: red circle with blue background prompt: cyan circle with brown...
Uni Sign
Here, we provide the model weights for Uni-Sign and the pre-extracted pose files for the CSL-Daily dataset.
Pix2tex Mfr GGUF
GGUF-format models for on-device math OCR, converted from breezedeus/pix2text-mfr (MIT license).
Vit Beans Boosted
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.0531 Accuracy: 0.9850
Korean Sign Word Classifier Mediapipe
This repository contains an end-to-end inference wrapper for isolated Korean sign-language word clips:
Rfdetr Large 2026 Mlx Fp32
MLX-format conversion of Roboflow's RF-DETR Large (2026) object-detection model, for use with mlx-swift-rf-detr on Apple Silicon.
Whisper Dioula
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
LLaMA Mesh Q3 Mlx
The Model alexgusevski/LLaMA-Mesh-q3-mlx was converted to MLX format from Zhengyi/LLaMA-Mesh using mlx-lm version 0.21.4.
Siglip2 Base Patch16 512 Som 32768
This model is a 45.62% smaller version of google/siglip2-base-patch16-512 optimized for Somali language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to the...
Qwen Image Blockwise ControlNet Canny
This model is a structure control model for images, trained based on Qwen-Image. The model architecture is ControlNet, capable of controlling the generated image structure according to edge detection (Canny) maps....
Wav2vec2 Msp Dim Emotion Coreml
A Core ML (.mlpackage) conversion of audeering/wav2vec2-large-robust-12-ft-emotion-msp-dim for on-device dimensional speech emotion recognition (arousal / dominance / valence) on Apple Silicon (Neural Engine / GPU /...
ViViT Wlasl 100 Signer 20ep CoR
This model is a fine-tuned version of google/vivit-b-16x2-kinetics400 on an unknown dataset. It achieves the following results on the evaluation set: Loss: 1.2104 Accuracy: 0.6864
Nut Grounding Dino Tiny
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Qwen Audio AHA
This repository contains the official LoRA adapter for Qwen2.5-Omni-7B (Thinker), fine-tuned using the AHA (Audio Hallucination Alignment) framework.
MiniCPM O 2 6 GPTQ
A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone
Granite Vision Crispembed GGUF
GGUF conversion of ibm-granite/granite-vision-3.3-2b for CrispEmbed.
Ddpm Celebahq Finetuned Butterflies 2epochs
pipeline = DDPMPipeline.frompretrained('camlinke/ddpm-celebahq-finetuned-butterflies-2epochs') image = pipeline().images[0] image
Ddpm Celebahq Finetuned Butterflies 2epochs
pipeline = DDPMPipeline.frompretrained('smoothich/ddpm-celebahq-finetuned-butterflies-2epochs') image = pipeline().images[0] image
