Microsoft did it .... again! (404 for their Mage-Flow models on HF)
Summary
Microsoft's Mage-Flow models appear to have been removed from HuggingFace (404), though community quantized versions remain available elsewhere.
Similar Articles
microsoft/Mage-Flow
Microsoft releases Mage-Flow, a compact 4B-parameter foundation model for efficient native-resolution text-to-image generation and instruction-based image editing, achieving competitive quality against much larger models.
Microsoft has taken down fastcontext model from everywhere
Microsoft has removed its FastContext model from Hugging Face and GitHub, with no official explanation yet.
Comfy-Org/Mage-Flow
Repackaged model files for ComfyUI from the Microsoft Mage-Flow model, including diffusion models, text encoder, and VAE.
Mage (GitHub Repo)
Microsoft releases Mage, a family of lightweight 4B-parameter multimodal models for visual understanding and generation, including Mage-VL for image/video understanding and Mage-Flow for text-to-image generation and editing, designed for research and deployment on modest hardware.
microsoft/Mage-VL · Hugging Face - An Efficient Codec-Native Streaming Multimodal Foundation Model
Microsoft introduces Mage-VL, a codec-native streaming multimodal foundation model for image and video understanding that achieves up to 3.5x inference speedup by using a sparsity pattern inspired by video codecs, cutting visual tokens by over 75%.