Search FoxAI

AI Models 84759

• Ternary-Bonsai-1.7B-mlx-2bit↗

  prism-ml

• nassila-sanad-9b↗

  QinEmPeRoR93

• Wan2.2-Fun-5B-Control-GGUF↗

  QuantStack

  Type | Name | Location | Download | ------------ | -------------------------------------------------- | --------------------------------- | ------------------------- | Main Model | Wan2.2-Fun-5B-Control | `ComfyUI/models/unet` | GGUF (this repo) | Text Encoder | Umt5-xxl | `ComfyUI/models/text_encoders` | Safetensors / GGUF | | VAE | Wan2.2_VAE.safetensors | `ComfyUI/models/vae` | Safetensors (this repo) | Since this is a quantized model, all original licensing terms and usage restrictions remain in effect.

• Qwen3.8-Flash-Next-Uncensored-NVFP4-2xGB10↗

  quocbao747

• gpt2-medium-amharic-28k-512↗

  rasyosef

• boredabdel_-_gemma-2b-sql-openassistant-gguf↗

  RichardErkhov

• distilbert-base-multilingual-cased-Actitud_de_tener_la_razon_Esp↗

  rogelioplatt

• Qwen3-ASR-0.6B-GGUF↗

  sakasegawa

• Solar-JEV-27B-R32↗

  SargeDev

• oneformer_ade20k_swin_large↗

  shi-labs

  OneFormer model trained on the ADE20k dataset (large-sized version, Swin backbone). It was introduced in the paper OneFormer: One Transformer to Rule Universal Image Segmentation by Jain et al. and first released in this repository. OneFormer is the first multi-task universal image segmentation framework. It needs to be trained only once with a single universal architecture, a single model, and on a single dataset, to outperform existing specialized models across semantic, instance, and panoptic segmentation tasks. OneFormer uses a task token to condition the model on the task in focus, making the architecture task-guided for training, and task-dynamic for inference, all with a single model. You can use this particular checkpoint for semantic, instance and panoptic segmentation. See the model hub to look for other fine-tuned versions on a different dataset.