test-time-training/ttt-video-dit

fine-tuning diffusion transformers for long-range video style transfer and context

View on index · View in 3D Map

Related repos

• Controls video motion without training
• LTX-Video, open source code for a model that generates videos from prompts or images using diffusion transformers
• diffusion transformer models for video restoration
• open source cinematic video generation with diffusion models
• video diffusion model for text-to-video, image-to-video, extension, and transitions
• video virtual try-on framework using video diffusion transformer for swapping clothes in videos
• diffusion model for upscaling real-world videos with text prompts
• Trains agents to act from videos
• Upscale, denoise, and interpolate videos
• transforms text into images, videos, 3D objects, and audio using flow-based diffusion transformers