Introducing SegMoE: Segmind Mixture of Diffusion Experts Today, we're excited to announce the world's first open source Mixture of Experts (MoEs) framework for Stable Diffusion. Mixture of Experts (MoEs) are a class of Sparse Deep learning models which contain Sparse Linear Layers made up of the Linear Layers and Gate Layers. These gate layers route the input
Announcements Featured Introducing Segmind Vega: Compact model for Real-time Text-To-Image Segmind has introduced two new open-source text-to-image models, Segmind-VegaRT (Real Time) and Segmind-Vega, the fastest and smallest, open source models for image generation at the highest resolution.
Announcements Featured Announcing SSD-1B: A Leap in Efficient T2I Generation Segmind has introduced the revolutionary SSD-1B, an open-source text-to-image model, outperforming previous versions by being 50% smaller and 60% faster than SDXL.
Stable Diffusion Featured Segmind Shatters Existing SDXL Benchmarks: Unveiling Ultra-Fast Image Generation with Optimized SDXL 1.0 Segmind unveils its groundbreaking optimization of the Stable Diffusion XL (SDXL 1.0) model, setting new standards in rapid image generation. Achieving astonishing speeds, our model generates images in just 2.3 seconds on an NVIDIA A100.
Announcements Featured Scaling Down for Speed: Introducing SD-Small and SD-Tiny Stable Diffusion Models In the Segmind Distilled Stable Diffusion series, we're excited to open-source the Knowledge Distillation Code and Weights of our new compact models: SD-Small and SD-Tiny.
Generative AI Featured The ML developers guide to Schedulers in Stable Diffusion If you have used stable diffusion to create or edit images, you would have come across a parameter called a scheduler or sampler. A few popular schedulers used are DDIM, Euler, and UniPC. Learn more about how each of them works and when to use them.
