Stability AI has released its most powerful AI models, Stable Diffusion 3.5. The models come with three next-generation open-source text-to-image AI model variants. The models include Stable Diffusion 3.5 Large, 3.5 Large Turbo, and 3.5 Medium.
These AI models run on consumer hardware and are available for use under the permissive Stability AI Community License. With greater degrees of customization and accessibility for both local and cloud deployments, each variant has been created to meet the demands of scientific researchers, enthusiasts, and business clients.
“In June, we released Stable Diffusion 3 Medium, the first open release from the Stable Diffusion 3 series. This release didn’t fully meet our standards or our communities’ expectations. After listening to the valuable community feedback, instead of a quick fix, we took the time to further develop a version that advances our mission to transform visual media,” the company said.
The Stable Diffusion 3.5 version excels in customizability, efficient performance, diverse outputs, and versatile styles. This makes it one of the most customizable and accessible image models on the market.
According to the company’s analysis, Stable Diffusion 3.5 Large leads the market in prompt adherence and rivals much larger models in image quality.
Even when compared to non-distilled models of comparable size, Stable Diffusion 3.5 Large Turbo maintains a very competitive picture quality and timely adherence while providing among of the fastest inference speeds for its size.
Outperforming other medium-sized models, Stable Diffusion 3.5 Medium strikes a mix between image quality and rapid adherence, making it a great option for effective, high-quality performance.
“We are pleased to release this model under our permissive community license,” Stability AI said in an announcement. The key components of the license are Free for non-commercial use, Free for commercial use (up to $1M in annual revenue), and Ownership of outputs.
Availability of Stable Diffusion 3.5
Stable Diffusion 3.5 Large and Stable Diffusion 3.5 Large Turbo models are available to download on Hugging Face and and the inference code on GitHub. The models can also be accessed through Stability AI API, Replicate, ComfyUI, and DeepInfra.
According to Stability AI, Stable Diffusion 3.5 Medium will be publicly available on 29th October 2024.
Also Read:
- IBM Introduces High Performing AI Models ‘Granite 3.0’ for Businesses
- Canvas in ChatGPT: What is It?
Stay Tuned to The Future Talk for more AI news and insights!