Error
root@orangepi5plus:/home/orangepi/sd_lcm# python ./run_rknn-lcm.py -i ./model -o ./images --num-inference-steps 4 -s 512x512 --prompt "Majestic mountain landscape with snow-capped peaks, autumn foliage in vibrant reds and oranges, a turquoise river winding through a valley, crisp and serene atmosphere, ultra-realistic style."
/usr/local/lib/python3.10/dist-packages/transformers/utils/generic.py:311: FutureWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
torch.utils._pytree._register_pytree_node(
/usr/local/lib/python3.10/dist-packages/diffusers/utils/outputs.py:63: FutureWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
torch.utils._pytree._register_pytree_node(
I:main:Setting random seed to 93
user_specified_scheduler LCMScheduler {
"_class_name": "LCMScheduler",
"_diffusers_version": "0.22.0",
"beta_end": 0.012,
"beta_schedule": "scaled_linear",
"beta_start": 0.00085,
"clip_sample": false,
"clip_sample_range": 1.0,
"dynamic_thresholding_ratio": 0.995,
"num_train_timesteps": 1000,
"original_inference_steps": 50,
"prediction_type": "epsilon",
"rescale_betas_zero_snr": false,
"sample_max_value": 1.0,
"set_alpha_to_one": true,
"steps_offset": 1,
"thresholding": false,
"timestep_spacing": "leading",
"trained_betas": null
}
I:main:Loading ./model/text_encoder
W rknn-toolkit-lite2 version: 2.3.0
I RKNN: [11:47:27.569] RKNN Runtime Information, librknnrt version: 2.3.2 (429f97ae6b@2025-04-09T09:09:27)
I RKNN: [11:47:27.569] RKNN Driver Information, version: 0.9.6
I RKNN: [11:47:27.569] RKNN Model Information, version: 6, toolkit version: 2.3.0(compiler version: 2.3.0 (c949ad889d@2024-11-07T11:39:30)), target: RKNPU v2, target platform: rk3588, framework name: ONNX, framework layout: NCHW, model inference type: static_shape
W RKNN: [11:47:27.873] query RKNN_QUERY_INPUT_DYNAMIC_RANGE error, rknn model is static shape type, please export rknn with dynamic_shapes
W Query dynamic range failed. Ret code: RKNN_ERR_MODEL_INVALID. (If it is a static shape RKNN model, please ignore the above warning message.)
I:main:Done. Took 0.6 seconds.
I:main:Loading ./model/unet
W rknn-toolkit-lite2 version: 2.3.0
I RKNN: [11:47:28.906] RKNN Runtime Information, librknnrt version: 2.3.2 (429f97ae6b@2025-04-09T09:09:27)
I RKNN: [11:47:28.906] RKNN Driver Information, version: 0.9.6
I RKNN: [11:47:28.907] RKNN Model Information, version: 6, toolkit version: 2.3.0(compiler version: 2.3.0 (c949ad889d@2024-11-07T11:39:30)), target: RKNPU v2, target platform: rk3588, framework name: ONNX, framework layout: NCHW, model inference type: static_shape
W RKNN: [11:47:31.005] query RKNN_QUERY_INPUT_DYNAMIC_RANGE error, rknn model is static shape type, please export rknn with dynamic_shapes
W Query dynamic range failed. Ret code: RKNN_ERR_MODEL_INVALID. (If it is a static shape RKNN model, please ignore the above warning message.)
I:main:Done. Took 3.1 seconds.
I:main:Loading ./model/vae_decoder
W rknn-toolkit-lite2 version: 2.3.0
I RKNN: [11:47:31.237] RKNN Runtime Information, librknnrt version: 2.3.2 (429f97ae6b@2025-04-09T09:09:27)
I RKNN: [11:47:31.237] RKNN Driver Information, version: 0.9.6
I RKNN: [11:47:31.237] RKNN Model Information, version: 6, toolkit version: 2.3.0(compiler version: 2.3.0 (c949ad889d@2024-11-07T11:39:30)), target: RKNPU v2, target platform: rk3588, framework name: ONNX, framework layout: NCHW, model inference type: static_shape
W RKNN: [11:47:32.550] query RKNN_QUERY_INPUT_DYNAMIC_RANGE error, rknn model is static shape type, please export rknn with dynamic_shapes
W Query dynamic range failed. Ret code: RKNN_ERR_MODEL_INVALID. (If it is a static shape RKNN model, please ignore the above warning message.)
I:main:Done. Took 1.5 seconds.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
I:main:Beginning image generation.
input 0 shape: (1, 77), dtype: int32
output shape: (1, 77, 768)
output shape: (1, 768)
Prompt encoding time: 0.09s
0%| | 0/4 [00:00<?, ?it/s]input 0 shape: (1, 4, 64, 64), dtype: float32
input 1 shape: (1,), dtype: int32
input 2 shape: (1, 77, 768), dtype: float32
input 3 shape: (1, 256), dtype: float32
段错误 (核心已转储)
I used rknn-toolkit-lite2==2.3.0 librknnrt.so ==2.3.0 NPU == 0.9.6 ,why the error happened?How can I solve it?