Microsoft releases 4B Mage-Flow for text-to-image and image editing
multimodalart · x · 2026-07-22
Microsoft releases Mage-Flow on Hugging Face
Microsoft has released Mage-Flow, a compact 4B-parameter text-to-image and image-editing model on Hugging Face.
- It is described as matching much larger open systems.
- The model supports image generation and editing.
- Reported inference speed is 0.59s per image at 1024².
- The attached architecture diagram shows a native-resolution MMDiT-style design and a Mage-VAE encoder/decoder stack.
Related event: Microsoft Asia Open-Sources 4B Image Model Mage-Flow(12 posts)→
More from Multimodal
- AI filmmaker PJaccetturo discusses building his NEXUS universe with Dreamina — DavidmComfort · 2026-10-27
- Runway launches App Studio: build no-code creative apps that generate image, video and audio — runwayml · 2026-10-27
- MiniMax H3 runs Maestro locally for free; Kling 4.0 vs Seedance 2.5 video editing compared — cocktailpeanut · 2026-10-27
- AI-generated movie-grade clip goes viral, blurring the line with real cinema — cneuralnetwork · 2026-10-27
- 10 practical ways to run Astra computer use on Premiere Pro for video editing — beechinour · 2026-10-27
- MiniMax H3 runs fully on a Galaxy S26: 5-second video with audio in ~7 minutes — BidFunny4862 · 2026-10-27