Phenaki
Click to visit website
About
Phenaki is an advanced model designed for the synthesis of realistic videos based on a sequence of textual prompts. It can create videos that last for several minutes using an innovative encoder-decoder approach that processes input frames with contextual prompts. The model leverages causal attention in time and is capable of handling variable-length videos, enabling it to generate video tokens from text using a bidirectional masked transformer. With joint training on extensive image-text pairs along with selected video-text examples, Phenaki generalizes effectively to produce high-quality video content. This model marks a significant achievement in video generation technology by allowing users to create arbitrary-length videos based on narratives or time-variable prompts, surpassing traditional per-frame methods in spatio-temporal quality.
Platform
Task
Features
• generate realistic videos from text prompts
• outperforms per-frame baselines in quality
• handles dynamic prompts that can change over time
• uses a causal model for learning video representation
• supports variable-length video generation
Average Rating: 0.0
Average Rating: 0.0
5 Stars:
0 Ratings
4 Stars:
0 Ratings
3 Stars:
0 Ratings
2 Stars:
0 Ratings
1 Star:
0 Ratings
User Ratings
No ratings available.
Sign In to Rate this Tool
Alternatives
Minimax AI Video Generator
An AI tool that generates high-quality videos from text prompts.
View DetailsFeatured Tools
Dezyn
Interactive architectural diagram tool with AI-powered features for flowcharts and cloud architectures.
View DetailsChoice AI
Personalized OTT entertainment platform using AI for tailored viewing experiences.
View Details