is a Multimodal Diffusion Transformer (MMDiT) text-to-image model with that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency, with a focus on fewer inference steps.

Please note: This model is released under the . Visit to learn or for commercial licensing details.

Model Description

• Developed by: Stability AI

• Model type: MMDiT text-to-image generative model

• Model Description: This model generates images based on text prompts. It is an ADD-distilled that use three fixed, pretrained text encoders, and with QK-normalization.

License

• Community License: Free for research, non-commercial, and commercial use for organizations or individuals with less than $1M in total annual revenue. More details can be found in the . Read more at .

• For individuals and organizations with annual revenue above $1M: Please to get an Enterprise License.

Model Sources

For local or self-hosted use, we recommend for node-based UI inference, or or for programmatic use.

• ComfyUI: ,

• Huggingface Space:

• Diffusers: .

• GitHub: .

• API Endpoints:

Implementation Details

• QK Normalization: Implements the QK normalization technique to improve training Stability.

• Adversarial Diffusion Distillation (ADD) (see the ), which allows sampling with 4 steps at high image quality.

• Text Encoders：

  • CLIPs: , , context length 77 tokens

  • T5: , context length 77/256 tokens at different stages of training

• Training Data and Strategy:

  This model was trained on a wide variety of data, including synthetic data and filtered publicly available data.

For more technical details of the original MMDiT architecture, please refer to the .