전체 검색

AI 모델 84999

• LFM2.5-230M-tools↗

  iromu

• Hy-MT2-1.8B-1.25Bit-GGUF↗

  kaptionai

• deformable-detr↗

  kernels-community

• Qwen3.6-14B-A3B-FableVibes-mlx-q6↗

  khanh2023

• Mi:dm K 2.5 Pro↗

  Korea Telecom

• ms-eff-gcvit-deepfake-b0-ff-plus-plus↗

  KoreaPeter

  Multi-Scale Efficient Global Context Vision Transformer (MS-EffGCViT) is a hybrid CNN-ViT architecture for **deepfake detection**. It fuses CNN-driven spatial inductive bias with hierarchical global-context attention to catch both *local* artifacts (textures, blending seams) and *global* artifacts (lighting, structural inconsistency). A single architecture ships in two sizes and three domain-tuned checkpoints, working on both **static images** and **video** at the **frame level**. Learning to detect manipulated facial images [[Paper]](https://arxiv.org/abs/1901.08971) [[Download]](https://github.com/ondyari/FaceForensics), featuring **1,000 original YouTube videos** manipulated by 5 face forgery methods.

• Mistral-7B-Instruct-v0.2-Neural-Story-GGUF↗

  Kquant03

• timee↗

  liamsbhoo

• LFM2.5-230M-MLX-bf16↗

  LiquidAI

• Qwen3.5-9B-abliterated-MLX-8bit↗

  lukey03