Upload README.md with huggingface_hub

README.md

@@ -144,9 +144,11 @@ This [export script](https://aihub.qualcomm.com/models/stable_diffusion_v2_1_qua
 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: **Upload compiled model**
+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.
 
-Upload compiled models from `qai_hub_models.models.stable_diffusion_v2_1_quantized` on hub.
 ```python
 import torch
 
@@ -154,11 +156,60 @@ import qai_hub as hub
 from qai_hub_models.models.stable_diffusion_v2_1_quantized import Model
 
 # Load the model
-model = Model.from_precompiled()
+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_textencoder_quantized = hub.upload_model(model.text_encoder.get_target_model_path())
-model_unet_quantized = hub.upload_model(model.unet.get_target_model_path())
-model_vaedecoder_quantized = hub.upload_model(model.vae_decoder.get_target_model_path())
 ```