Mage-Flow: Microsoft's 4B Native-Resolution Image Model Family

ComfyUI Wiki

Mage-Flow is a compact 4B generative stack from Microsoft Asia for text-to-image and image editing at native resolution up to 2048, with RL-aligned and Turbo variants.

M

Mage-Flow by Microsoft

Text-to-ImageImage Editing4B ParametersNative ResolutionMIT License

Mage-Flow is a compact **4B-parameter generative stack** from Microsoft Asia for efficient text-to-image generation and instruction-based image editing. Instead of scaling to tens of billions of parameters, it reaches state-of-the-art-competitive quality through careful tokenizer-backbone-system co-design, keeping it fast, memory-light, and easy to fine-tune under realistic compute budgets.

DeveloperMicrosoft Asia
Release Date2026-07-22
Architecture4B NR-MMDiT (Native-Resolution Multimodal Diffusion Transformer) + Mage-VAE
Text EncoderQwen3-VL (4B)
LicenseMIT
Output Resolution512×512 to 2048×2048 (any aspect ratio, up to 4:1)
Inference Steps4 to 30 (depends on variant)
VRAM~18-20 GB at 1024×1024
GenEval Score0.90 (highest among open-source models)

Variants

VariantTaskStepsDescription
Mage-Flow-4BText-to-Image20RL-aligned generation
Mage-Flow-4B-TurboText-to-Image4Few-step distilled generation
Mage-Flow-Edit-4BImage Editing30RL-aligned instruction-based editing
Mage-Flow-Edit-4B-TurboImage Editing4Few-step distilled editing

All weights are self-contained diffusers-style checkpoints on Hugging Face. Curated ComfyUI-ready downloads (including int8 ConvRot quantized variants) are available in the Model Hub catalog.

Comments

Sign in with GitHub to join the discussion.

Loading comments…