AuraFlow
Open source stream based text to image generation model
- Generate high-resolution images based on text descriptions
- Supports running on specific hardware, such as CUDA
- Provide multiple parameter settings to adjust the details of the generated image
- Use Torch Generator for randomness control
- Support high fidelity and surreal image generation
- The model is still under development and will continue to integrate community feedback for optimization
Product Details
AuraFlow v0.1 is a fully open-source, stream based text to image generation model that achieves state-of-the-art results on GenEval. At present, the model is in the beta stage and is constantly being improved, and community feedback is crucial. Thank you to the two engineers @ cloneofsimo and @ isidentical for turning this project into reality, as well as the researchers who laid the foundation for it.
