All Updates

All Updates

icon
Filter
Partnerships
Stability AI introduces Stable Cascade, a text-to-image model based on three-phase approach
Foundation Models
Feb 12, 2024
This week:
M&A
N-able acquires Adlumin for USD 266 million to strengthen cybersecurity offerings
Next-gen Cybersecurity
Today
M&A
Bitsight acquires Cybersixgill for USD 115 million to enhance threat intelligence capabilities
Cyber Insurance
Today
M&A
Snowflake acquires Datavolo to enhance data integration capabilities for undisclosed sum
Generative AI Infrastructure
Today
M&A
Snowflake acquires Datavolo to enhance data integration capabilities for undisclosed sum
Data Infrastructure & Analytics
Today
Product updates
Microsoft launches Copilot Actions for workplace automation
Foundation Models
Yesterday
M&A
Almanac acquires Gro Intelligence's IP assets for undisclosed sum
Smart Farming
Yesterday
Partnerships
Aduro Clean Technologies partners with Zeton to build hydrochemolytic pilot plant
Waste Recovery & Management Tech
Yesterday
Funding
Oishii raises USD 16 million in Series B funding from Resilience Reserve
Vertical Farming
Yesterday
Management news
GrowUp Farms appoints Mike Hedges as CEO
Vertical Farming
Yesterday
M&A
Rise Up acquires Yunoo and expands LMS monetization capabilities
EdTech: Corporate Learning
Yesterday
Foundation Models

Foundation Models

Feb 12, 2024

Stability AI introduces Stable Cascade, a text-to-image model based on three-phase approach

Partnerships

  • Stability AI, a developer of Stable Diffusion text-to-image AI, has introduced Stable Cascade, a text-to-image model developed with a three-phase approach for the use of non-commercial requirements.

  • The model includes features like image creation, modification of generated images, improving an existing picture's resolution, and inpainting and outpainting where editing is applied on specific parts of an image. It also offers canny edge functionality, enabling users to generate a new image just from the edges of an existing one.

  • Additionally, the company will release scripts for checkpoints and inference, fine tuning, ControlNet, and LoRA training to enable users to experiment with the new architecture (Würstchen) found on the Stability GitHub page.

  • The company claims that the model will offer compression ability higher than VAE in Stable Diffusion and is 16x less than a similar-sized Stable Diffusion model during additional tuning in Stage C. Moreover, the model is designed to require approximately 20GB VRAM for inference, which can be further reduced using smaller variants.

Contact us

Gain access to all industry hubs, market maps, research tools, and more
Get a demo
arrow
menuarrow

By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.