Search FoxAI

AI Models 84755

• 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

• X-Ray_Alpha-GGUF↗

  matrixportalx

• Hermes2-Gutenberg2-Mistral-7B-GGUF↗

  MaziyarPanahi

• Qwen3.8-cyber-RedTeam-Surgical-Abliterated↗

  medismera

• hotpot-v2-brier-7b-no-split↗

  mehuldamani