Mage-Flow-4B: RL-Aligned Text-to-Image Generation

ComfyUI Wiki

Mage-Flow-4B is Microsoft Asia's RL-aligned 4B text-to-image model with native resolution up to 2048 and 20-step inference.

M

Mage-Flow-4B (RL-aligned)

Text-to-Image4B ParametersRL-Aligned20 Steps

The RL-aligned text-to-image variant of the Mage-Flow family. Uses rectified flow matching in the Mage-VAE latent space with Qwen3-VL as the text encoder. Achieves **GenEval 0.90** — the highest among all open-source models — surpassing FLUX.2 (0.87), Qwen-Image (0.87), and Z-Image (0.84). On DPG-Bench, scores 86.26, competitive with much larger models.

DeveloperMicrosoft Asia
Release Date2026-07-22
Architecture4B NR-MMDiT + Mage-VAE
Text EncoderQwen3-VL (4B)
LicenseMIT
Output Resolution512×512 to 2048×2048 (any aspect ratio)
Inference Steps20
VRAM~18-20 GB at 1024×1024
GenEval0.90

ComfyUI Support

Mage-Flow-4B has native ComfyUI support via the integration PR (#15026). Download the repackaged weights from Comfy-Org/Mage-Flow on Hugging Face, including int8 ConvRot quantized variants.

See the Mage-Flow news article for more details on the full model family.

Guides and workflows related to this model series.

No articles found.

Comments

Sign in with GitHub to join the discussion.

Loading comments…