Tencent has released Hy Image 3.5 Preview, a unified model for image generation and editing. This model consolidates multiple workflows, including text-to-image, image-to-image transformations, and multi-turn editing, into a single endpoint. It supports up to 20 reference images for tasks like maintaining style and character consistency, and features a 100K context window. The preview version is currently available for free, though pricing and availability may change. AI
IMPACT Consolidates image generation and editing workflows into a single model, potentially simplifying development for AI-powered image applications.
RANK_REASON Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →