Got total noise image when running stable diffusion script for QNN #7550
Description
🐛 Describe the bug
Follow up guide here: https://github.com/pytorch/executorch/blob/main/examples/qualcomm/qaihub_scripts/stable_diffusion/README.md
to download bin files and vocab json file
and then run (device is SM8650):
python examples/qualcomm/qaihub_scripts/stable_diffusion/qaihub_stable_diffusion.py -b build-android -m ${SOC_MODEL} -s ${SERIAL_NUM} --text_encoder_bin ${PATH_TO_TEXT_ENCODER_CONTEXT_BINARY} --unet_bin ${PATH_TO_UNET_CONTEXT_BINARY} --vae_bin ${PATH_TO_VAE_CONTEXT_BINARY} --vocab_json ${PATH_TO_VOCAB_JSON_FILE} --num_time_steps 20 --prompt "a photo of an astronaut riding a horse on mars"
No error, but the generated image is total noise.
Log on device:
[INFO] [Qnn ExecuTorch]: create QNN Logger with log_level 2
[WARNING] [Qnn ExecuTorch]: Initializing HtpProvider
[WARNING] [Qnn ExecuTorch]: Function not called, PrepareLib isn't loaded!
[INFO] [Qnn ExecuTorch]: Initialize Qnn backend parameters for Qnn executorch backend type 2
[INFO] [Qnn ExecuTorch]: Caching: Caching is in RESTORE MODE.
[WARNING] [Qnn ExecuTorch]: Function not called, PrepareLib isn't loaded!
[WARNING] [Qnn ExecuTorch]: Function not called, PrepareLib isn't loaded!
[INFO] [Qnn ExecuTorch]: Running level=1 optimization.
[INFO] [Qnn ExecuTorch]: create QNN Logger with log_level 2
[INFO] [Qnn ExecuTorch]: Initialize Qnn backend parameters for Qnn executorch backend type 2
[INFO] [Qnn ExecuTorch]: Caching: Caching is in RESTORE MODE.
[WARNING] [Qnn ExecuTorch]: Function not called, PrepareLib isn't loaded!
[INFO] [Qnn ExecuTorch]: Running level=1 optimization.
[INFO] [Qnn ExecuTorch]: create QNN Logger with log_level 2
[INFO] [Qnn ExecuTorch]: Initialize Qnn backend parameters for Qnn executorch backend type 2
[INFO] [Qnn ExecuTorch]: Caching: Caching is in RESTORE MODE.
[WARNING] [Qnn ExecuTorch]: Function not called, PrepareLib isn't loaded!
[INFO] [Qnn ExecuTorch]: Running level=1 optimization.
I 00:00:04.621670 executorch:runner.cpp:350] Start generating
I 00:00:08.161772 executorch:runner.cpp:555] Total Number of steps: 20
I 00:00:08.161985 executorch:runner.cpp:561] Tokenizer Load Time: 2.961000 (seconds)
I 00:00:08.162066 executorch:runner.cpp:567] Model Load Time: 1.658000 (seconds)
I 00:00:08.162130 executorch:runner.cpp:573] Generate Time(Tokenize + Encoder + UNet + VAE): 3.505000 (seconds)
I 00:00:08.162192 executorch:runner.cpp:580] Tokenize Time: 0.000000 (seconds)
I 00:00:08.162254 executorch:runner.cpp:586] Text Encoder Execution Time: 0.016000 (seconds)
I 00:00:08.162315 executorch:runner.cpp:592] Unet Aggregate (Cond + Uncond) Execution Time: 3.099000 (seconds)
I 00:00:08.162374 executorch:runner.cpp:598] Unet Average Execution Time: 0.077000 (seconds)
I 00:00:08.162434 executorch:runner.cpp:604] Unet Aggregate Post-Processing Time: 0.154000 (seconds)
I 00:00:08.162492 executorch:runner.cpp:611] Unet Average Post-Processing Time: 0.003000 (seconds)
I 00:00:08.162551 executorch:runner.cpp:617] VAE Execution Time: 0.180000 (seconds)
[INFO] [Qnn ExecuTorch]: Destroy Qnn backend parameters
[INFO] [Qnn ExecuTorch]: Destroy Qnn context
[INFO] [Qnn ExecuTorch]: Destroy Qnn device
[INFO] [Qnn ExecuTorch]: Destroy Qnn backend
[INFO] [Qnn ExecuTorch]: Destroy Qnn backend parameters
[INFO] [Qnn ExecuTorch]: Destroy Qnn context
[INFO] [Qnn ExecuTorch]: Destroy Qnn device
[INFO] [Qnn ExecuTorch]: Destroy Qnn backend
[INFO] [Qnn ExecuTorch]: Destroy Qnn backend parameters
[INFO] [Qnn ExecuTorch]: Destroy Qnn context
[INFO] [Qnn ExecuTorch]: Destroy Qnn device
[INFO] [Qnn ExecuTorch]: Destroy Qnn backend
Versions
Collecting environment information...
PyTorch version: 2.6.0.dev20241112+cpu
Is debug build: False
CUDA used to build PyTorch: Could not collect
ROCM used to build PyTorch: N/A
OS: Ubuntu 20.04.6 LTS (x86_64)
GCC version: (Ubuntu 9.4.0-1ubuntu1~20.04.3) 9.4.0
Clang version: Could not collect
CMake version: version 3.31.2
Libc version: glibc-2.31
Python version: 3.10.15 (main, Sep 7 2024, 18:35:33) [GCC 9.4.0] (64-bit runtime)
Python platform: Linux-5.4.0-195-generic-x86_64-with-glibc2.31
Is CUDA available: False
CUDA runtime version: 12.6.77
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: GPU 0: NVIDIA GeForce RTX 3090
Nvidia driver version: 560.35.03
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
Address sizes: 39 bits physical, 48 bits virtual
CPU(s): 32
On-line CPU(s) list: 0-31
Thread(s) per core: 1
Core(s) per socket: 24
Socket(s): 1
NUMA node(s): 1
Vendor ID: GenuineIntel
CPU family: 6
Model: 183
Model name: Intel(R) Core(TM) i9-14900HX
Stepping: 1
CPU MHz: 2478.337
CPU max MHz: 7400.0000
CPU min MHz: 800.0000
BogoMIPS: 4838.40
Virtualization: VT-x
L1d cache: 576 KiB
L1i cache: 384 KiB
L2 cache: 24 MiB
NUMA node0 CPU(s): 0-31
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 sdbg fma cx16 xtpr pdcm sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb intel_pt sha_ni xsaveopt xsavec xgetbv1 xsaves dtherm ida arat pln pts hwp hwp_notify hwp_act_window hwp_epp hwp_pkg_req umip pku ospke waitpkg gfni vaes vpclmulqdq rdpid movdiri movdir64b md_clear flush_l1d arch_capabilities
Versions of relevant libraries:
[pip3] executorch==0.5.0a0+d2b7b2f
[pip3] numpy==1.21.3
[pip3] nvidia-cublas-cu12==12.1.3.1
[pip3] nvidia-cuda-cupti-cu12==12.1.105
[pip3] nvidia-cuda-nvrtc-cu12==12.1.105
[pip3] nvidia-cuda-runtime-cu12==12.1.105
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.0.2.54
[pip3] nvidia-curand-cu12==10.3.2.106
[pip3] nvidia-cusolver-cu12==11.4.5.107
[pip3] nvidia-cusparse-cu12==12.1.0.106
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] nvidia-nvjitlink-cu12==12.6.85
[pip3] nvidia-nvtx-cu12==12.1.105
[pip3] onnx==1.16.2
[pip3] torch==2.6.0.dev20241112+cpu
[pip3] torchao==0.8.0+gitebc43034
[pip3] torchaudio==2.5.0.dev20241112+cpu
[pip3] torchsr==1.0.4
[pip3] torchvision==0.20.0.dev20241112+cpu
[pip3] triton==3.0.0