zai-org/CogView2
Hierarchical transformer model for generating images from text descriptions, based on SwissArmyTransformer library.
Not currently ranked — collecting fresh signals.
star history
CogView2 is a large-scale generative model for text-to-image synthesis in both Chinese and English. The model uses a hierarchical transformer architecture with 6B-9B-9B parameters and includes LoPAR for accelerated generation and CogLM for bidirectional completion. This implementation provides pretrained models for text-to-image generation and text-guided completion, deployed via Huggingface Spaces and Replicate web demos.
Frequently asked
- What is zai-org/CogView2?
- Hierarchical transformer model for generating images from text descriptions, based on SwissArmyTransformer library.
- Is CogView2 open source?
- Yes — zai-org/CogView2 is open source, released under the Apache-2.0 license.
- What language is CogView2 written in?
- zai-org/CogView2 is primarily written in Python.
- How popular is CogView2?
- zai-org/CogView2 has 955 stars on GitHub.
- Where can I find CogView2?
- zai-org/CogView2 is on GitHub at https://github.com/zai-org/CogView2.