import gradio as gr from convert import run_conversion from hub_utils import push_to_hub, save_model_card PRETRAINED_CKPT = "CompVis/stable-diffusion-v1-4" DESCRIPTION = """ This Space lets you convert KerasCV Stable Diffusion weights to a format compatible with [Diffusers](https://github.com/huggingface/diffusers) 🧨. This allows users to fine-tune using KerasCV and use the fine-tuned weights in Diffusers taking advantage of its nifty features (like schedulers, fast attention, etc.). Specifically, the parameters are converted and then they are wrapped into a [`StableDiffusionPipeline`](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/overview). This pipeline is then pushed to the Hugging Face Hub given you have provided a `your_hf_token`. ## Notes (important) * Only Stable Diffusion (v1) is supported as of now. In particular this checkpoint: [`"CompVis/stable-diffusion-v1-4"`](https://huggingface.co/CompVis/stable-diffusion-v1-4). * Only the text encoder and the UNet parameters converted since only these two elements are generally fine-tuned. * [This Colab Notebook](https://colab.research.google.com/drive/1RYY077IQbAJldg8FkK8HSEpNILKHEwLb?usp=sharing) was used to develop the conversion utilities initially. * You can choose not to provide `text_encoder_weights` and `unet_weights` in case you don't have any fine-tuned weights. In that case, the original parameters of the respective models (text encoder and UNet) from KerasCV will be used. * You can provide only `text_encoder_weights` or `unet_weights` or both. * When providing the weights' links, ensure they're directly downloadable. Internally, the Space uses [`tf.keras.utils.get_file()`](https://www.tensorflow.org/api_docs/python/tf/keras/utils/get_file) to retrieve the weights locally. * If you don't provide `your_hf_token` the converted pipeline won't be pushed. Check [here](https://github.com/huggingface/diffusers/blob/31be42209ddfdb69d9640a777b32e9b5c6259bf0/examples/dreambooth/train_dreambooth_lora.py#L975) for an example on how you can change the scheduler of an already initialized pipeline. """ def run(hf_token, text_encoder_weights, unet_weights, repo_prefix): if text_encoder_weights == "": text_encoder_weights = None if unet_weights == "": unet_weights = None pipeline = run_conversion(text_encoder_weights, unet_weights) output_path = "kerascv_sd_diffusers_pipeline" pipeline.save_pretrained(output_path) save_model_card( base_model=PRETRAINED_CKPT, repo_folder=output_path, weight_paths=[text_encoder_weights, unet_weights], repo_prefix=repo_prefix, ) push_str = push_to_hub(hf_token, output_path, repo_prefix) return push_str demo = gr.Interface( title="KerasCV Stable Diffusion to Diffusers Stable Diffusion Pipelines 🧨🤗", description=DESCRIPTION, allow_flagging="never", inputs=[ gr.Text(max_lines=1, label="your_hf_token"), gr.Text(max_lines=1, label="text_encoder_weights"), gr.Text(max_lines=1, label="unet_weights"), gr.Text(max_lines=1, label="output_repo_prefix"), ], outputs=[gr.Markdown(label="output")], fn=run, ) demo.launch()