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 βSearch results
All resources
20 shown of 42,664
SD Class Butterflies 32
This model is a diffusion model for unconditional image generation of cute π¦.
MeshAnythingV2
Contents Installation Usage Important Notes Acknowledgement BibTeX
LFM2.5 350M T Wix Ru
lfm1.0
Gemma 4 12B
Hugging Face | GitHub | Launch Blog | Documentation
Imagenet Sae Top K 64 Patches Only Layer 7 Hook Resid Post 128 79
This model is a sparse autoencoder trained on CLIP's internal representations.
Gemma 4 E2B It
Hugging Face | GitHub | Launch Blog | Documentation
Imagenet Sae Top K 64 Patches Only Layer 6 Hook Resid Post 256 87
This model is a sparse autoencoder trained on CLIP's internal representations.
Deim Dfine X Int8 Ov
Model creator: GetiTM Original model: DEIM D-FINE-X
Tempo 6B Stage0
This repository contains the intermediate checkpoint (Stage 0) for Tempo-6B.
Medical Vqa Dpo
LoRA/adapter checkpoint for the DPO-tuned medical VQA model.
SD Class Butterflies 32
This model is a diffusion model for unconditional image generation of cute π¦.
Efficientnet B7 FP16 Ov
Model creator: torchvision Original model: efficientnetb7
SD Class Butterflies 32
This model is a diffusion model for unconditional image generation of cute π¦.
SD Class Butterflies 32
This model is a diffusion model for unconditional image generation of cute π¦.
Z Image FP8
Quantized fp8 Z-Image for ComfyUI.
SD Class Butterflies 32
This model is a diffusion model for unconditional image generation of cute π¦.
Dpt Dinov2 Base Nyu
with ONNX weights to be compatible with Transformers.js.
SD Class Butterflies 32
This model is a diffusion model for unconditional image generation of cute π¦.
BS RoFormer ONNX
Band-Split RoPE Transformer (BS-RoFormer) η ONNX ζ ΌεΌζ¨‘ε,η¨δΊι³δΉζΊε离(δΊΊε£°/δΌ΄ε₯ε离)γ
FACM
π₯ FACM outperforms 2Γ250-step Lightning-DiT on ImageNet 256 with only 2 steps
