Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jpyyn100p
Results Ready
Name
controlnet_canny_unet
Target Device
  • Arduino VENTUNO Q
  • Ubuntu 24.04
  • Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
latent: uint16[1, 64, 64, 4]
timestep: uint16[1, 1]
text_emb: uint16[1, 77, 768]
controlnet_downblock0: uint16[1, 64, 64, 320]
controlnet_downblock1: uint16[1, 64, 64, 320]
controlnet_downblock2: uint16[1, 64, 64, 320]
controlnet_downblock3: uint16[1, 32, 32, 320]
controlnet_downblock4: uint16[1, 32, 32, 640]
controlnet_downblock5: uint16[1, 32, 32, 640]
controlnet_downblock6: uint16[1, 16, 16, 640]
controlnet_downblock7: uint16[1, 16, 16, 1280]
controlnet_downblock8: uint16[1, 16, 16, 1280]
controlnet_downblock9: uint16[1, 8, 8, 1280]
controlnet_downblock10: uint16[1, 8, 8, 1280]
controlnet_downblock11: uint16[1, 8, 8, 1280]
controlnet_midblock: uint16[1, 8, 8, 1280]
Completion Time
11/14/2026, 8:37:17 AM
Options
--qairt_version latest
Versions
  • ONNX Runtime: 1.30.0
  • QNN Execution Provider: 2.5.0
  • QAIRT: v2.51.0.260929181845
  • Qualcomm Linux: 24.04
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
103 ms
Estimated Peak Memory Usage
10 ‑ 27 MB
Compute Units
NPU
3412
StageTimeMemory
First App Load
1.13 s851‑852 MB
Subsequent App Load
1.08 s851‑852 MB
Inference
103 ms10‑27 MB
ONNX RuntimeValue
execution_modeSEQUENTIAL
intra_op_num_threads0
inter_op_num_threads0
enable_memory_patternfalse
enable_cpu_memory_arenafalse
graph_optimization_levelENABLE_ALL
QNN Execution ProviderValue
htp_performance_mode"burst"
htp_graph_finalization_optimization_mode"3"
enable_htp_fp16_precision"1"
capture_network_visualizationsfalse
context_priority"normal"
offload_graph_io_quantization"1"
num_graph_prepare_threads"1"

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

Run on device