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 38,615
Dental Panoramic Detector
YOLO11-N model trained to detect dental pathologies on panoramic radiographs.
Pictory ControlNet Upsample Edge Prompt Lr5e 6 Ep15
This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
Timesformer BDSLW60 U5 20 CoR WithoutAug
This model is a fine-tuned version of facebook/timesformer-base-finetuned-k400 on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.6824 Accuracy: 0.86
Semantic DACVAE Japanese
Semantic-DACVAE-Japanese is a fine-tuned version of facebook/dacvae-watermarked, specifically optimized for Japanese speech.
EBEN Reverse Rigid In Ear Microphone
Developed by: Cnam-LMSSC Model: EBEN(M=4,P=4,Q=4) (see publication in IEEE TASLP - arXiv link) Language: French License: MIT Training dataset: speechclean subset of Cnam-LMSSC/vibravox (see VibraVox paper on arXiV)...
Siglip2 Base Patch16 512 Text
> Note: This is a stripped-down copy of google/siglip2-base-patch16-512 containing only the text tower. It encodes text queries into the shared embedding space and is meant to be loaded on its own at retrieval time,...
KiwiWAI_IlluXL
This model is a merge based on KiwiMix , updated with WAI-illustrious .
Ddpm Celebahq Finetuned Butterflies 2epochs
pipeline = DDPMPipeline.frompretrained('Atomax00/ddpm-celebahq-finetuned-butterflies-2epochs') image = pipeline().images[0] image
Vit Base Patch16 Dinov3 Qkvb.lvd1689m
dinov3-license
Stable Diffusion 8bit Chain Of Zoom
High-quality diffusion model optimized with 8-bit quantization for Chain-of-Zoom super-resolution. Core component for generating detailed super-resolved images.
Huihui Gemma 4 12B It Abliterated
This is an uncensored version of google/gemma-4-12B-it created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from...
Dreamcar123
DreamCar can reconstruct a completed 3D car model in the moving-forward scene given a few images even a single image.
Kokoro 82M v1.0 ONNX
Kokoro is a frontier TTS model for its size of 82 million parameters (text in/audio out).
Emoji VAE Init
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Sakura Dreams
Positive Prompt: masterpiece, newest,absurdres,incredibly absurdres, best quality, amazing quality, very aesthetic
Lens DF11
For more information (including how to compress models yourself), check out and
Siglip2 So400m Patch14 384 Text
> Note: This is a stripped-down copy of google/siglip2-so400m-patch14-384 containing only the text tower. It encodes text queries into the shared embedding space and is meant to be loaded on its own at retrieval...
ControlNet
These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning. You can find some example images below.
Ddpm Celebahq Finetuned Butterflies 2epochs
pipeline = DDPMPipeline.frompretrained('Ron936/ddpm-celebahq-finetuned-butterflies-2epochs') image = pipeline().images[0] image
Convnext Tiny.dinov3 Lvd1689m
dinov3-license
