MMDiT (Multimodal Diffusion Transformer)
MMDiT (Multimodal Diffusion Transformer, sometimes written MM-DiT) is a transformer architecture for text-conditioned image generation that gives image tokens and text tokens their own separate weights but…
Image Generation
Explore Image Generation through related topics and the articles other pages reference most.
Explore articles
Browse subtopics: Model Architecture
Articles that also belong to these categories. Counts cover all of Image Generation.
All articles (84)Generative AI (51)AI Models (25)Diffusion Models (18)AI Companies (13)Computer Vision (13)Open Source AI (12)AI Tools & Products (11)OpenAI (9)Chinese AI (8)Multimodal AI (6)Video Generation (6)Google (5)Google DeepMind (5)Meta AI (5)AI Benchmarks (3)AI Incidents & Controversies (2)AI Research (2)Artificial Intelligence (2)ChatGPT (2)Developer Tools (2)AI Hardware (1)AI History (1)AI Inference (1)AI Infrastructure (1)AI Policy & Regulation (1)Deep Learning (1)MLOps (1)Machine Learning (1)Microsoft (1)Model Architecture (1)NVIDIA (1)People (1)Prompt Engineering (1)Reinforcement Learning (1)Transformer Models (1)
Showing 1-1 of 1 article