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 41,727
Picth Vision Checkpoint 6
This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.2964 Accuracy: 0.9664
Siglip2 Giant Opt Patch16 384 Spa 32768
This model is a 13.74% smaller version of google/siglip2-giant-opt-patch16-384 optimized for Spanish language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to...
Heart Sound Classifier Astbase04
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
OSP Next
Efficient High-Quality Video Generation with Sparse Sequence Parallelism, HiF8 Quantization, and Reinforcement Learning
Siglip2 Base Patch16 224 Vision
> Note: This is a stripped-down copy of google/siglip2-base-patch16-224 containing only the vision tower. It encodes images / video frames into the shared embedding space and is meant to be loaded on its own at...
LightOn Rerank LW 0.8B
Unified Text + Visual Document Reranker by LightOn
Comfy Org Wan 2 1 ComfyUI Repackaged
Wan 2.1 repackaged for ComfyUI use. For examples see:
Vilt B32 Mlm Finetuned Vqa 800
This model was trained from scratch on the vqa dataset. It achieves the following results on the evaluation set: Loss: 6.9132
Medsiglip 448 Ft Crc100k
This model is a fine-tuned version of google/medsiglip-448 on the imagefolder dataset. It achieves the following results on the evaluation set: Loss: 1.3559
Dermai Vit Base Patch16 224
Fine-tuned google/vit-base-patch16-224 for 7-class skin lesion classification on HAM10000. Part of the DermAI explainability project comparing CNN and Vision Transformer explanations.
Siglip2 Giant Opt Patch16 384 Swh 32768
This model is a 13.74% smaller version of google/siglip2-giant-opt-patch16-384 optimized for Swahili language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to...
Oxford 17 Flowers Resnet18
Backbone: resnet18 pretrained on ImageNet during training Input size: 224x224 Classes: 17 Weights: flowerresnet18.pth
ControlNet Model2
These are controlnet weights trained on stabilityai/stable-diffusion-2-1-base with new type of conditioning. You can find some example images below. prompt: High-quality close-up dslr photo of man wearing a hat with...
Ddpm Celebahq Finetuned Butterflies
pipeline = DDPMPipeline.frompretrained('lipinp/ddpm-celebahq-finetuned-butterflies') image = pipeline().images[0] image
Siglip2 Giant Opt Patch16 384 Rus 32768
This model is a 13.74% smaller version of google/siglip2-giant-opt-patch16-384 optimized for Russian language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to...
F5 TTS OpenBible Hausa
A zero-shot text-to-speech model for Hausa, trained from scratch on the Open Bible corpus using the F5-TTS architecture (diffusion transformer with vocos vocoder, 24 kHz output).
Siglip2 Giant Opt Patch16 384 Mon 32768
This model is a 13.74% smaller version of google/siglip2-giant-opt-patch16-384 optimized for Mongolian language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to...
DeepSeek OCR 2 CROHME LoRA
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...
Ddpm Celebahq Finetuned Butterflies 2epochs
pipeline = DDPMPipeline.frompretrained('tumorai/ddpm-celebahq-finetuned-butterflies-2epochs') image = pipeline().images[0] image
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...
