Canva Debuts Craft Model Using Two-Stage Architectural Planning
Canva has launched Craft, an in-house image generation model that utilizes a planning stage to improve spatial precision and design composition.
AI & Culture Desk 2 min read
All stories tagged computer vision on The Silicon Valley News.
Canva has launched Craft, an in-house image generation model that utilizes a planning stage to improve spatial precision and design composition.
Elorian has released Glimpse, a multimodal model that attempts to solve the limitations of current vision AI by utilizing a "visual scratch space" to re-examine image data during the reasoning process rather than relying solely on initial text tokenization.
OpenAI's reported acquisition of smartphone camera maker Glass Imaging suggests a strategic expansion into advanced computational photography and multimodal AI capabilities, moving beyond its foundational large language models.