keras-sd/text-encoder-tflite

This repository hosts the TFLite version of text encoder part of KerasCV Stable Diffusion.

Stable Diffusion consists of text encoder, diffusion model, decoder, and some glue codes to handl inputs and outputs of each part. The TFLite version of text encoder in this repository is built not only with the text encoder itself but also TensorFlow operations that generates context and unconditional context. These output should be passed down to the diffusion model which is hosted in this repository.

TFLite conversion was based on the SavedModel from this repository, and TensorFlow version >= 2.12-nightly was used.

• —NOTE: Dynamic range quantization was used.
• —NOTE: TensorFlow version < 2.12-nightly will fail for the conversion process.
• —NOTE: For those who wonder how SavedModel is constructed, find it in keras-sd-serving repository.