StablediffusionV2.1 on MI15 device

🚀 The feature, motivation and pitch

python examples/qualcomm/qaihub_scripts/stable_diffusion/qaihub_stable_diffusion.py -b build-android -m SM8750 -s c23ff2a7 --text_encoder_bin elitesd/text_encoder_serialized_bin_mq9wo4elm.bin --unet_bin elitesd/unet_serialized_bin_mqpd2w6vq.bin --vae_bin elitesd/vae_channel_last_serialized_bin_mq8zjwvzq.bin --vocab_json Stable-Diffusion-v2.1/vocab.json --num_time_steps 20 --prompt "a photo of cat wearing silver armour and ready for war "

Stable-Diffusion-v2.1/vocab.json: 1 file pushed. 29.8 MB/s (862328 bytes in 0.028s)
I 00:00:00.001124 executorch:qaihub_stable_diffusion_runner.cpp:100] Stable Diffusion runner started
I 00:00:00.001305 executorch:runner.cpp:72] creating module: model_path=/data/local/tmp/executorch/qaihub_stable_diffusion/qaihub_stable_diffusion_text_encoder.pte
I 00:00:00.001326 executorch:runner.cpp:72] creating module: model_path=/data/local/tmp/executorch/qaihub_stable_diffusion/qaihub_stable_diffusion_unet.pte
I 00:00:00.001348 executorch:runner.cpp:72] creating module: model_path=/data/local/tmp/executorch/qaihub_stable_diffusion/qaihub_stable_diffusion_vae.pte
I 00:00:00.001357 executorch:runner.cpp:127] Loading Tokenizer from json
[INFO] [Qnn ExecuTorch]: Deserializing processed data using QnnContextCustomProtocol
[INFO] [Qnn ExecuTorch]: create QNN Logger with log_level 2
[WARNING] [Qnn ExecuTorch]: QnnDsp Initializing HtpProvider

[WARNING] [Qnn ExecuTorch]: QnnDsp Function not called, PrepareLib isn't loaded!

[INFO] [Qnn ExecuTorch]: Initialize Qnn backend parameters for Qnn executorch backend type 2
[WARNING] [Qnn ExecuTorch]: Qnn API version 2.24.0 is used. The version is tested against 2.22.0.
[INFO] [Qnn ExecuTorch]: Caching: Caching is in RESTORE MODE.
[INFO] [Qnn ExecuTorch]: QnnContextCustomProtocol expected magic number: 0x5678abcd but get: 0x2000000
[ERROR] [Qnn ExecuTorch]: QnnDsp Skel lib id mismatch: expected (v2.31.0.250130151446_114721), detected (v2.24.15.241023110117_20363)

[ERROR] [Qnn ExecuTorch]: QnnDsp Failed to create transport for device, error: 1008

[ERROR] [Qnn ExecuTorch]: QnnDsp Failed to load skel, error: 1008

[ERROR] [Qnn ExecuTorch]: QnnDsp Transport layer setup failed: 1008

[ERROR] [Qnn ExecuTorch]: QnnDsp Failed to parse default platform info: 1008

[ERROR] [Qnn ExecuTorch]: QnnDsp Failed to load default platform info: 1008

[ERROR] [Qnn ExecuTorch]: QnnDsp Failed to parse platform config: 1008

[ERROR] [Qnn ExecuTorch]: Failed to create device_handle for Backend ID 6, error=1008
E 00:00:02.864099 executorch:QnnManager.cpp:305] Fail to configure Qnn device
E 00:00:02.864121 executorch:QnnExecuTorchBackend.cpp:93] Fail to initialize Qnn Manager
E 00:00:02.864140 executorch:method.cpp:113] Init failed for backend QnnBackend: 0x1
F 00:00:02.864185 executorch:qaihub_stable_diffusion_runner.cpp:128] In function main(), assert failed (runner.load() == Error::Ok): Runner failed to load method
Aborted
/data/local/tmp/executorch/qaihub_stable_diffusion/outputs/: 0 files pulled.

Alternatives

No response

Additional context

No response

RFC (Optional)

No response

cc @cccclai @cbilgin