Upload README.md with huggingface_hub

README.md

@@ -9,7 +9,7 @@ pipeline_tag: unconditional-image-generation
 
 ---
 
-![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/riffusion_quantized/web-assets/model_demo.png)
+![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/riffusion/web-assets/model_demo.png)
 
 # Riffusion: Optimized for Mobile Deployment
 ## State-of-the-art generative AI model used to generate spectrogram images given any text input. These spectrograms can be converted into audio clips
@@ -22,7 +22,7 @@ This model is an implementation of Riffusion found [here](https://github.com/Com
 
 This repository provides scripts to run Riffusion on Qualcomm® devices.
 More details on model performance across various devices, can be found
-[here](https://aihub.qualcomm.com/models/riffusion_quantized).
+[here](https://aihub.qualcomm.com/models/riffusion).
 
 
 ### Model Details
@@ -58,7 +58,7 @@ More details on model performance across various devices, can be found
 
 Install the package via pip:
 ```bash
-pip install "qai-hub-models[riffusion-quantized]"
+pip install "qai-hub-models[riffusion]"
 ```
 
 
@@ -82,7 +82,7 @@ The package contains a simple end-to-end demo that downloads pre-trained
 weights and runs this model on a sample input.
 
 ```bash
-python -m qai_hub_models.models.riffusion_quantized.demo
+python -m qai_hub_models.models.riffusion.demo
 ```
 
 The above demo runs a reference implementation of pre-processing, model
@@ -91,7 +91,7 @@ inference, and post processing.
 **NOTE**: If you want running in a Jupyter Notebook or Google Colab like
 environment, please add the following to your cell (instead of the above).
 ```
-%run -m qai_hub_models.models.riffusion_quantized.demo
+%run -m qai_hub_models.models.riffusion.demo
 ```
 
 
@@ -104,7 +104,7 @@ device. This script does the following:
 * Accuracy check between PyTorch and on-device outputs.
 
 ```bash
-python -m qai_hub_models.models.riffusion_quantized.export
+python -m qai_hub_models.models.riffusion.export
 ```
 ```
 Profiling Results
@@ -139,75 +139,21 @@ Compute Unit(s)                 : NPU (4933 ops)
 
 ## How does this work?
 
-This [export script](https://aihub.qualcomm.com/models/riffusion_quantized/qai_hub_models/models/Riffusion/export.py)
+This [export script](https://aihub.qualcomm.com/models/riffusion/qai_hub_models/models/Riffusion/export.py)
 leverages [Qualcomm® AI Hub](https://aihub.qualcomm.com/) to optimize, validate, and deploy this model
 on-device. Lets go through each step below in detail:
 
-Step 1: **Compile model for on-device deployment**
-
-To compile a PyTorch model for on-device deployment, we first trace the model
-in memory using the `jit.trace` and then call the `submit_compile_job` API.
+Step 1: **Upload compiled model**
 
+Upload compiled models from `qai_hub_models.models.riffusion` on hub.
 ```python
 import torch
 
 import qai_hub as hub
-from qai_hub_models.models.riffusion_quantized import Model
+from qai_hub_models.models.riffusion import Model
 
 # Load the model
-model = Model.from_pretrained()
-text_encoder_model = model.text_encoder
-unet_model = model.unet
-vae_decoder_model = model.vae_decoder
-
-# Device
-device = hub.Device("Samsung Galaxy S23")
-
-# Trace model
-text_encoder_input_shape = text_encoder_model.get_input_spec()
-text_encoder_sample_inputs = text_encoder_model.sample_inputs()
-
-traced_text_encoder_model = torch.jit.trace(text_encoder_model, [torch.tensor(data[0]) for _, data in text_encoder_sample_inputs.items()])
-
-# Compile model on a specific device
-text_encoder_compile_job = hub.submit_compile_job(
-    model=traced_text_encoder_model ,
-    device=device,
-    input_specs=text_encoder_model.get_input_spec(),
-)
-
-# Get target model to run on-device
-text_encoder_target_model = text_encoder_compile_job.get_target_model()
-# Trace model
-unet_input_shape = unet_model.get_input_spec()
-unet_sample_inputs = unet_model.sample_inputs()
-
-traced_unet_model = torch.jit.trace(unet_model, [torch.tensor(data[0]) for _, data in unet_sample_inputs.items()])
-
-# Compile model on a specific device
-unet_compile_job = hub.submit_compile_job(
-    model=traced_unet_model ,
-    device=device,
-    input_specs=unet_model.get_input_spec(),
-)
-
-# Get target model to run on-device
-unet_target_model = unet_compile_job.get_target_model()
-# Trace model
-vae_decoder_input_shape = vae_decoder_model.get_input_spec()
-vae_decoder_sample_inputs = vae_decoder_model.sample_inputs()
-
-traced_vae_decoder_model = torch.jit.trace(vae_decoder_model, [torch.tensor(data[0]) for _, data in vae_decoder_sample_inputs.items()])
-
-# Compile model on a specific device
-vae_decoder_compile_job = hub.submit_compile_job(
-    model=traced_vae_decoder_model ,
-    device=device,
-    input_specs=vae_decoder_model.get_input_spec(),
-)
-
-# Get target model to run on-device
-vae_decoder_target_model = vae_decoder_compile_job.get_target_model()
+model = Model.from_precompiled()
 
 ```
 
@@ -222,18 +168,6 @@ provided job URL to view a variety of on-device performance metrics.
 
 # Device
 device = hub.Device("Samsung Galaxy S23")
-profile_job_textencoder_quantized = hub.submit_profile_job(
-    model=model_textencoder_quantized,
-    device=device,
-)
-profile_job_unet_quantized = hub.submit_profile_job(
-    model=model_unet_quantized,
-    device=device,
-)
-profile_job_vaedecoder_quantized = hub.submit_profile_job(
-    model=model_vaedecoder_quantized,
-    device=device,
-)
 
 ```
 
@@ -243,30 +177,6 @@ To verify the accuracy of the model on-device, you can run on-device inference
 on sample input data on the same cloud hosted device.
 ```python
 
-input_data_textencoder_quantized = model.text_encoder.sample_inputs()
-inference_job_textencoder_quantized = hub.submit_inference_job(
-    model=model_textencoder_quantized,
-    device=device,
-    inputs=input_data_textencoder_quantized,
-)
-on_device_output_textencoder_quantized = inference_job_textencoder_quantized.download_output_data()
-
-input_data_unet_quantized = model.unet.sample_inputs()
-inference_job_unet_quantized = hub.submit_inference_job(
-    model=model_unet_quantized,
-    device=device,
-    inputs=input_data_unet_quantized,
-)
-on_device_output_unet_quantized = inference_job_unet_quantized.download_output_data()
-
-input_data_vaedecoder_quantized = model.vae_decoder.sample_inputs()
-inference_job_vaedecoder_quantized = hub.submit_inference_job(
-    model=model_vaedecoder_quantized,
-    device=device,
-    inputs=input_data_vaedecoder_quantized,
-)
-on_device_output_vaedecoder_quantized = inference_job_vaedecoder_quantized.download_output_data()
-
 ```
 With the output of the model, you can compute like PSNR, relative errors or
 spot check the output with expected output.
@@ -292,7 +202,7 @@ provides instructions on how to use the `.so` shared library or `.bin` context b
 
 
 ## View on Qualcomm® AI Hub
-Get more details on Riffusion's performance across various devices [here](https://aihub.qualcomm.com/models/riffusion_quantized).
+Get more details on Riffusion's performance across various devices [here](https://aihub.qualcomm.com/models/riffusion).
 Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)