Generative AI Research Intern - Image-to-Video Diffusion
Core
Building next-generation generative systems that transform still images into high-quality, temporally consistent videos using diffusion and transformer-based architectures.
Role type
Research intern (image-to-video diffusion)
Builds
Experimental pipelines, model variants for motion modeling and temporal consistency, research reports
Domain
Computer Vision / Generative AI / Video Generation
Deliverable
research
Required skills
diffusion models, transformer-based architectures, motion modeling, temporal representation learning, Python, PyTorch, ablation studies, generative video evaluation metrics (LPIPS, FVD)
Preferred skills
optical flow, temporal consistency, large-scale training, multimodal models, video datasets, top-tier conference publications
