Pardon my image samples, I'm on a mac so diffuse'ing sd3 takes a while, so I didn't do much tweaking or many steps, but I'm gonna update them to be all the same seed/size and workflow to compare at least.

Thanks to city96 for all his hard work for the conversion utility work an getting things working with me on his github, all the thanks in the world to him for the incredible help.

Stable Diffusion 3.5 Large 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.

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 a Multimodal Diffusion Transformer that use three fixed, pretrained text encoders, and with QK-normalization to improve training stability.

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 Community License Agreement. Read more at https://stability.ai/license.
For individuals and organizations with annual revenue above $1M: please contact us to get an Enterprise License.

Implementation Details

QK Normalization: Implements the QK normalization technique to improve training Stability.
Text Encoders：
- CLIPs: OpenCLIP-ViT/G, CLIP-ViT/L, context length 77 tokens
- T5: T5-xxl, 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 Research paper.