At 2.5 billion parameters, with improved MMDiT-X architecture and training methods, this model is designed to run “out of the box” on consumer hardware, striking a balance between quality and ease of customization. It is capable of generating images ranging between 0.25 and 2 megapixel resolution.
At 2.5 billion parameters, with improved MMDiT-X architecture and training methods, this model is designed to run “out of the box” on consumer hardware, striking a balance between quality and ease of customization. It is capable of generating images ranging between 0.25 and 2 megapixel resolution.
text prompt
negative text prompt
Num Images
number of images to generate (Default: 1, 1 ≤ num_images ≤ 4)
Num Inference Steps
number of denoising steps (Default: 35, 1 ≤ num_inference_steps ≤ 50)
indirectly defines the width and height 9
Guidance Scale
classifier-free guidance, higher means follow prompt more closely (Default: 7, 0 ≤ guidance_scale ≤ 20)
random seed, empty means random (Default: empty, 0 ≤ seed < 18446744073709552000)
You need to login to use this model
Stable Diffusion 3.5 Medium is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.
Please note: This model is released under the Stability Community License. Visit Stability AI to learn or contact us for commercial licensing details.
QK Normalization: Implements the QK normalization technique to improve training Stability.
Text Encoders:
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 Research paper.
See blog for our study about comparative performance in prompt adherence and aesthetic quality.
Intended uses include the following:
All uses of the model must be in accordance with our Acceptable Use Policy.
The model was not trained to be factual or true representations of people or events. As such, using the model to generate such content is out-of-scope of the abilities of this model.
As part of our safety-by-design and responsible AI deployment approach, we take deliberate measures to ensure Integrity starts at the early stages of development. We implement safety measures throughout the development of our models. We have implemented safety mitigations that are intended to reduce the risk of certain harms, however we recommend that developers conduct their own testing and apply additional mitigations based on their specific use cases.
For more about our approach to Safety, please visit our Safety page.
Our integrity evaluation methods include structured evaluations and red-teaming testing for certain harms. Testing was conducted primarily in English and may not cover all possible harms.
Please report any issues with the model or contact us: