Various ways of serving Stable Diffusion

This repository shows a various ways to deploy Stable Diffusion. Currently, we are interested in the Stable Diffusion implementation from keras-cv, and the target platforms/frameworks that we aim includes TF Serving, Hugging Face Endpoint, and FastAPI.

From the version 0.4.0 release of keras-cv, StableDiffusionV2 is included, and this repository support both version 1 and 2 of the Stable Diffusion.

1. All in One Endpoint

This method shows how to deploy Stable Diffusion as a whole in a single endpoint. Stable Diffusion consists of three models(encoder, diffusion model, decoder) and some glue codes to handle the inputs and outputs of each models. In this scenario, everything is packaged into a single Endpoint.

• Hugging Face 🤗 Endpoint: In order to deploy something in Hugging Face Endpoint, we need to create a custom handler. Hugging Face Endpoint let us easily deploy any machine learning models with pre/post processing logics in a custom handler [Colab | Standalone Codebase]

• FastAPI Endpoint: [Colab | Standalone]

  • Docker Image: gcr.io/gcp-ml-172005/sd-fastapi-allinone:latest

2. Three Endpoints

This method shows how to deploy Stable Diffusion in three separate Endpoints. As a preliminary work, this notebook was written to demonstrate how to split three parts of Stable Diffusion into three separate modules. In this example, you will see how to interact with three different endpoints to generate images with a given text prompt.

• Hugging Face Endpoint: [Colab | Text Encoder | Diffusion Model | Decoder]

• FastAPI Endpoint: [Central | Text Encoder | Diffusion Model | Decoder]

  • Docker Image(text-encoder): gcr.io/gcp-ml-172005/sd-fastapi-text-encoder:latest
  • Docker Image(diffusion-model): gcr.io/gcp-ml-172005/sd-fastapi-diffusion-model:latest
  • Docker Image(decoder): gcr.io/gcp-ml-172005/sd-fastapi-decoder:latest

• TF Serving Endpoint: [Colab | Dockerfiles + k8s Resources]

  • SavedModel: [Colab | Text Encoder | Diffusion Model | Decoder]
    • wrapping encoder, diffusion model, and decoder and some glue codes in separate SavedModels. With them, we can not only deploy each models on cloud with TF Serving but also embed in web and mobild applications with TFJS and TFLite. We will explore the embedded use cases later phase of this project.
  • Docker Images
    • text-encoder: gcr.io/gcp-ml-172005/tfs-sd-text-encoder:latest
    • text-encoder w/ base64: gcr.io/gcp-ml-172005/tfs-sd-text-encoder-base64:latest
    • text-encoder-v2: gcr.io/gcp-ml-172005/tfs-sd-text-encoder-v2:latest
    • text-encoder-v2 w/ base64: gcr.io/gcp-ml-172005/tfs-sd-text-encoder-v2-base64:latest
    • diffusion-model: gcr.io/gcp-ml-172005/tfs-sd-diffusion-model:latest
    • diffusion-model w/ base64: gcr.io/gcp-ml-172005/tfs-sd-diffusion-model-base64:latest
    • diffusion-model-v2: gcr.io/gcp-ml-172005/tfs-sd-diffusion-model-v2:latest
    • diffusion-model-v2 w/ base64: gcr.io/gcp-ml-172005/tfs-sd-diffusion-model-v2-base64:latest
    • decoder: gcr.io/gcp-ml-172005/tfs-sd-decoder:latest
    • decoder w/ base64: gcr.io/gcp-ml-172005/tfs-sd-decoder-base64:latest

NOTE: Passing intermediate values between models through network could be costly, and some platform limits certain payload size. For instance, Vertex AI limits the request size to 1.5MB. To this end, we provide different TF Serving Docker images which handles inputs and produces outputs in base64 format.

3. One Endpoint with Two local APIs (w/ 🤗 Endpoint)

With the separation of Stable Diffusion, we could organize each parts in any environments. This is powerful especially if we want to deploy specialized diffusion models such as inpainting and finetuned diffusion model. In this case, we only need to replace the currently deployed diffusion model or just deploy a new diffusion model besides while keeping the other two(text encoder and decoder) as is.

Also, it is worth noting that we could run text encoder and decoder parts in local(Python clients or web/mobile with TF Serving) while having diffusion model on cloud. In this repository, we currently show an example using Hugging Face 🤗 Endpoint. However, you could easily expand the posibilities.

NOTE: along with this project, we have developed one more project to fine-tune Keras based Stable Diffusion at Fine-tuning Stable Diffusion using Keras. We currently provide a fine-tuned model to Pokemon dataset.

• Original txt2img generation: [Colab]

• Original inpainting: [Colab]

4. On-Device Deployment (w/ TFLite) - WIP

We have managed to convert SavedModels into TFLite models, and we are hosting them as below (thanks to @farmaker47):

• Text Encoder TFLite Model - 127MB
• Diffusion Model TFLite Model - 864MB
• Decoder TFLite Model - 99MB

These TFLite models have the same signature as the SavedModels, and all the pre/post operations are included inside. All of them are converted with float16 quantization optimize process. You can find more about how to convert SavedModels to TFLite models in this repository.

TODO

• Implement SimpleTokenizer in JAVA and JavaScript
• Run TFLite models on Android and Web browser

Timing Tests

🚨 XLA support

In this notebook, we show how we can XLA-compile the SavedModels to achieve a speed-up of about 52% over the non-XLA variant.

Acknowledgements

Thanks to the ML Developer Programs' team at Google for providing GCP credits.