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 38,708
Videomamba Small Driver 4class
VideoMamba-Small trained from random init (no pretrain) on the mango driver-behavior dataset (4 classes), for comparison against Video Swin-T / SiftFormer on the same task.
LibreEfficientNetV2b0 Cls
EfficientNetV2-base-b0 image classifier (1000-class ImageNet-1k), repackaged for LibreYOLO. Eval resolution 224px; timm-reported top-1 accuracy 78.7%.
IllustraToon
Anima This is the Anima Base Version of my Model
Stable Lime v1.0
Stable-Lime-v1.0 is an unconditional diffusion model based on the Denoising Diffusion Probabilistic Models (DDPM) architecture. It has been trained specifically to generate images representing the "essence of Lime."
Prompt Depth Anything Vits
Prompt Depth Anything is a high-resolution and accurate metric depth estimation method, with the following highlights: using prompting to unleash the power of depth foundation models, inspired by success of prompting...
Qwen Image Edit
Qwen-Image-Edit-2509-Light-Migration.safetensors from dx8152/Qwen-Edit-2509-Light-Migration Qwen-Edit-2509-Multiple-angles.safetensors from dx8152/Qwen-Edit-2509-Multiple-angles...
Deepfake Detection Models
A 5-model soft-vote ensemble for binary deepfake detection, trained on FaceForensics++ C23 and zero-shot evaluated on Celeb-DF v2. Published as the production weights for the live demo at deepfakedetection.xyz.
ComfyUI Extracted LoRA
This repository contains personal LoRA extractions of the differences between models such as Wan2.x, Flux, and Chroma.
CPUBone
ImageNet-1k classification weights for the CPUBone model family (CVPR 2025), converted to the timm implementation of the architecture.
BERTc 315M CSC
| 指标 | 值 | | 句级 F1 | 0.8388 | | 准确率 | 0.8472 | | 精确率 | 0.9461 | | 召回率 | 0.7534 |
Lgd Cards Gen2
The second generation of the Live Game Defender (LGD) playing-card detector: gen 1 fine-tuned on the first day of real casino-table video from our proof-of-concept rig. This closed most of the synthetic→real gap that...
Ccip Anime Character Id
CCIP enables determining whether two images depict the same character, calculating visual similarity between characters.
ControlNet Landsat Scheduler
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: A satellite image of the earth. The weather is clear...
Escarda VE
Vision encoder for the Escarda family (39.6M, 448px / patch16 / 784 tokens). Byrne-VE plus a JEPA head next to the HRM refine block - that's the Escarda trait.
Rtmw L 384x288
This is a Hugging Face-compatible port of rtmw-l-384x288 from OpenMMLab MMPose.
Rqsa Mil v1
RQSA-MIL (Region-Quality Supervised Attention for Multiple Instance Learning) is a nudity detection model: a MobileNetV2 backbone with a spatial attention gate conditioned on region quality. During training the gate...
SeeGroup
we propose SeeGroup, a multi-layer depth estimation method that allows the model itself to adaptively assign surfaces to depth maps. We formulate per-pixel multi-layer depth as a point process, treating depth layers...
LightningDiT Diffusers
Diffusers-ready checkpoints for LightningDiT (VA-VAE–aligned latent diffusion with flow matching), converted from hustvl/lightningdit-xl-imagenet256-800ep for local/offline use.
Depth LoRA Checkpoints Hypersim Depth Light Hypersim Near High Light
> Base model: metric3dvitgiant2 > loaded via torch.hub.load("yvanyin/metric3d", "metric3dvitgiant2")
Sf3d
stabilityai-ai-community
