Find what you need for your workflow.

Dbnetpp Repvit Ch

Lightweight text detection model combining DBNet++ with RepViT backbone, optimized for efficient inference. Pretrained on Chinese text detection datasets.

Agrivision Blip2 Model

AgriVision BLIP2 is a fine-tuned multimodal Vision-Language Model developed for intelligent crop disease diagnosis from plant leaf images.

Masbro F5 Tts

This indonesian finetune of F5-TTS is made to introduce indonesian speech capabilities on the model. This version 2 finetune should be much better than version 1 in terms of speaker similarity, naturalism, and...

GUARD

Wqm Zzl Swin Tiny Tomato Disease

Fine-tuned Swin Tiny model for tomato disease classification based on the PlantVillage dataset.

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.