Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
j1p3o23mp
Results Ready
Name
stable_diffusion_v1_5_quantized_UNet_Quantized
Target Device
  • Samsung Galaxy S24
  • Android 14
  • Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
latent: uint16[1, 64, 64, 4]
time_emb: uint16[1, 1280]
text_emb: uint16[1, 77, 768]
Completion Time
8/16/2024, 8:13:46 PM
Versions
  • QNN: v2.24.0.240626131148_96320
  • QNN Backend API: 5.24.0
  • QNN Core API: 2.17.0
  • Android: 14 (UP1A.231005.007)
  • AI Hub: aihub-2024.08.12.0
Estimated Inference Time
81.7 ms
Estimated Peak Memory Usage
0 ‑ 8 MB
Compute Units
NPU
4421
StageTimeMemory
First App Load
437 ms2‑9 MB
Subsequent App Load
390 ms1‑9 MB
Inference
81.7 ms0‑8 MB
QNNValue
context_options.htp_options.performance_modeBURST
default_graph_options.htp_options.precisionFLOAT16

Sign up to run this model on a hosted Qualcomm® device!

Run on device