mage-flow-base / README.md
multimodalart's picture
multimodalart HF Staff
Upload folder using huggingface_hub
d58fd10 verified
|
Raw
History Blame Contribute Delete
620 Bytes

A newer version of the Gradio SDK is available: 6.20.0

Upgrade
metadata
title: Mage-Flow-Base
emoji: 🎨
colorFrom: yellow
colorTo: pink
sdk: gradio
sdk_version: 6.15.1
app_file: app.py
short_description: Text-to-image with Microsoft Mage-Flow-Base (4.1B MMDiT)
python_version: '3.12'
startup_duration_timeout: 1h

Mage-Flow-Base

Text-to-image generation with microsoft/Mage-Flow-Base, a 4.1B parameter native-resolution MMDiT model.

Enter a text prompt and generate images at resolutions from 512 to 2048 on any aspect ratio. The model uses a Qwen3-VL text encoder and a custom MageVAE for 128-channel, 16x downsampled latents.