Stability AI

On the 14th of September, Stability AI has officially released the Enterprise Audio Generation Model Stable Audio 2.5, which, relative to the previous generation, has been upgraded to focus on audio detail and production speed, stating that “it takes only two seconds to create three minutes of audio. It was described that the core improvements of Stable Audio 2.5 focused on the ability to produce music, which was described as producing results that were more accompanied by the actual chorus logic and presented a full multi-part structure of foreplay, development and end. And the new model is more accurate in its understanding of the hints..

In a blog post yesterday (October 22), Stability AI announced the release of Stable Diffusion 3.5, which marks a significant advancement in open source AI graphical models. Stable Diffusion 3.5 is available in Medium (released on October 29), Large and Large Turbo sizes, designed to meet the different needs of scientific researchers, enthusiasts, startups and enterprises, with the following introduction: Stable Dif...

Generating 3D images used to be an extremely difficult task involving complex wireframes, software, and hardware. But now, things have changed dramatically. Stability AI has announced a new generative AI technology called Stable Fast3D that can quickly generate 3D images from a single image. The best part is that according to Stability AI, the new model can generate 3D images in half a second. This processing speed is a qualitative leap compared to previous models that might take several minutes to generate similar effects, and Stability AI can generate 3D images from a single image in just half a second.

Recently, Stability AI announced the launch of a revolutionary video processing technology - Stable Video4D. This technology can convert a single-view video into 8 new perspectives, providing creators with unprecedented flexibility and creativity. Stable Video4D is built on the company's previously launched Stable Video Diffusion model. Unlike converting images to videos, the new model can receive video input and generate multiple new perspective video outputs, realizing the transition from image-based...

Recently, the Stability AI team launched a new open source audio generation model called Stable Audio Open. What is special about this model is that it can generate up to 47 seconds of stereo audio from text prompts with a sampling rate of up to 44.1kHz. Unlike many currently popular audio generation models, the weights of Stable Audio Open are open, which means that anyone can view, modify, and extend this model. This design concept not only promotes the progress of scientific research, but also provides developers with…

In the latest news, the famous open source big model platform Stability AI has modified the community license agreement to allow the latest released text graph model Stable Diffusion3Medium (SD3-M) to be used commercially. This change means that individual developers and start-ups can use this powerful big model for free, bringing positive development opportunities to the industry. According to the new agreement, as long as the annual income of enterprises or individual developers is less than 1 million US dollars, they can apply to Stability AI for free commercial use of SD3-M...

British artificial intelligence company Stability AI has attracted much attention for its image generator Stable Diffusion, but has repeatedly encountered twists and turns in business issues. Source note: Image generated by AI, image licensing service provider Midjourney Now, the company has announced a major financing, including a group of new investors including former Facebook president and Napster co-founder Sean Parker, and former Google CEO Eric Schmidt is also one of them. At the same time, film production and visual effects companies…

Co-CEO of Stability AI officially announced the open release date of Stable Diffusion 3 Medium as June 12th. This news delighted many people who were looking forward to using this model. Users can download it on Hugging Face from June 12th. SD3 Medium is a 2 billion parameter SD3 model. Here are some of its outstanding features: Photorealism: Overcomes common artifacts on hands and faces, providing high-quality images without complex workflows…

Stability AI has launched a friendly chatbot called Stable Assistant, which is equipped with Stability AI's latest text and image generation technology, including Stable Diffusion3 and Stable LM212B. This chatbot is currently in beta. Stable Assistant has excellent multi-topic prompts, image quality and spelling ability. It excels in generating images based on conversational prompts, providing knowledgeable answers, helping with writing projects, and matching...

According to Reuters and The Information, a spokesperson for Stability AI, a British artificial intelligence startup regarded as one of the "giants" in the field of artificial intelligence, said that the company is negotiating with a group of investors for a large equity financing to inject new funds into the current cash-strapped Stability AI. The spokesperson said that Stability AI is working exclusively with a "world-renowned" technology investment group. According to reports, Stability AI's revenue in the first quarter was less than...

Stability AI is a highly anticipated AI company. However, the news of CEO Emad Mostaque's resignation recently triggered a huge change within the company. After Mostaque's resignation, the company's COO Shan Shan Wong and CTO Christian Laforte temporarily served as co-CEOs. Mostaque announced on the social media platform X that after his resignation, he would focus on decentralized artificial intelligence (Decentrali…

On March 23, Stability AI, a leading AI image generation company based in London, UK, suddenly announced the resignation of its CEO Emad Mostaque. Subsequently, Emad Mostaque announced on the social media platform X that he would devote himself to decentralized artificial intelligence (Decentralized AI) after his resignation. Stability AI wrote in a blog post on its official website: Earlier today, Emad Mostaque resigned from his position as CEO and resigned from the company’s board of directors…

Recently, the core research team of Stable Diffusion announced their collective resignation, which has attracted widespread attention in the technology community. The team leader Robin Rombach, co-first author Andreas Blattmann and another author Dominik Lorenz are all on the resignation list. Although the specific reasons for the resignation have not been made public, according to Forbes, Stable AI may be facing challenges due to financial difficulties. Source Note: The picture is generated by AI, and the picture authorization service provider Midjourney S…

Stability AI recently released the Stable Video 3D model, which can create multi-view 3D videos from a single image. ▲ Image source Stability AI Stable Video 3D includes two variants, SV3D_u can generate track videos based on a single image input without camera adjustment; and SV3D_p extends the functionality of SVD3_u, which can accommodate track views, allowing 3D videos to be created along a specified camera path. Compared with the previous Stable…

According to the official press release of Stability AI, Stability AI recently launched a new generation of text graph model called "Stable Cascade". The model is built on the Würstchen architecture and is said to be able to be easily trained and fine-tuned on consumer-grade hardware. ▲ Image source: Stability AI official press release (the same below) The official claims that compared with the industry's familiar SDXL, the new Stable Cascade model has improved performance and claimed content quality. Currently…

Stability AI, the company behind Stable Diffusion, has now launched a subscription service to standardize and transform how its models are used for commercial purposes by customers. The company says the membership program "redefines" the way it grants commercial use rights to users, aiming to strike a balance between profitability and openness. Stability AI's membership program offers three tiers: a free version for personal and research use; a $20 per month subscription version for "creators, developers, and individuals with less than $1 million in annual revenue who have received 10...