Option:
 n_threads: 8
 mode: txt2img
 model_path: ../models/sd-v1-4-ggml-model-f16.bin
 output_path: output.png
 init_img:
 prompt: a lovely cat
 negative_prompt:
 cfg_scale: 7.00
 width: 512
 height: 512
 sample_method: eular a
 sample_steps: 20
 strength: 0.75
 seed: 42
System Info:
 BLAS = 1
 SSE3 = 0
 AVX = 0
 AVX2 = 0
 AVX512 = 0
 AVX512_VBMI = 0
 AVX512_VNNI = 0
 FMA = 0
 NEON = 1
 ARM_FMA = 1
 F16C = 0
 FP16_VA = 1
 WASM_SIMD = 0
 VSX = 0
[INFO] stable-diffusion.cpp:2687 - loading model from '../models/sd-v1-4-ggml-model-f16.bin'
[DEBUG] stable-diffusion.cpp:2695 - verifying magic
[DEBUG] stable-diffusion.cpp:2706 - loading hparams
[INFO] stable-diffusion.cpp:2712 - ftype: f16
[DEBUG] stable-diffusion.cpp:2718 - loading vocab
[DEBUG] stable-diffusion.cpp:2746 - ggml tensor size = 272 bytes
[DEBUG] stable-diffusion.cpp:2751 - clip params ctx size = 236.23 MB
[DEBUG] stable-diffusion.cpp:2770 - unet params ctx size = 1641.36 MB
[DEBUG] stable-diffusion.cpp:2791 - vae params ctx size = 95.51 MB
[DEBUG] stable-diffusion.cpp:2812 - preparing memory for the weights
[DEBUG] stable-diffusion.cpp:2828 - loading weights
[DEBUG] stable-diffusion.cpp:2932 - model size = 1969.67MB
[INFO] stable-diffusion.cpp:2941 - total params size = 1969.97MB (clip 235.01MB, unet 1640.45MB, vae 94.51MB)
[INFO] stable-diffusion.cpp:2943 - loading model from '../models/sd-v1-4-ggml-model-f16.bin' completed, taking 0.77s
[DEBUG] stable-diffusion.cpp:766 - parse 'a lovely cat' to [['a lovely cat', 1], ]
[DEBUG] stable-diffusion.cpp:353 - split prompt "a lovely cat" to tokens ["a</w>", "lovely</w>", "cat</w>", ]
[DEBUG] stable-diffusion.cpp:2982 - condition context need 10.19MB static memory, with work_size needing 9.00MB
[DEBUG] stable-diffusion.cpp:3006 - building condition graph completed: 633 nodes, 210 leafs
[DEBUG] stable-diffusion.cpp:3013 - computing condition graph completed, taking 0.16s
[INFO] stable-diffusion.cpp:3066 - condition graph use 248.13MB of memory: params 235.01MB, runtime 13.12MB (static 10.19MB, dynamic 2.93MB)
[DEBUG] stable-diffusion.cpp:3068 - 236544 bytes of dynamic memory has not been released yet
[DEBUG] stable-diffusion.cpp:766 - parse '' to [['', 1], ]
[DEBUG] stable-diffusion.cpp:353 - split prompt "" to tokens []
[DEBUG] stable-diffusion.cpp:2982 - condition context need 10.19MB static memory, with work_size needing 9.00MB
[DEBUG] stable-diffusion.cpp:3006 - building condition graph completed: 633 nodes, 210 leafs
[DEBUG] stable-diffusion.cpp:3013 - computing condition graph completed, taking 0.14s
[INFO] stable-diffusion.cpp:3066 - condition graph use 248.13MB of memory: params 235.01MB, runtime 13.12MB (static 10.19MB, dynamic 2.93MB)
[DEBUG] stable-diffusion.cpp:3068 - 236544 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3552 - get_learned_condition completed, taking 0.31s
[INFO] stable-diffusion.cpp:3568 - start sampling
[DEBUG] stable-diffusion.cpp:3119 - diffusion context need 69.56MB static memory, with work_size needing 67.50MB
[INFO] stable-diffusion.cpp:3260 - step 1 sampling completed, taking 13.14s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 2 sampling completed, taking 12.97s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 3 sampling completed, taking 13.04s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 4 sampling completed, taking 13.36s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 5 sampling completed, taking 13.30s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 6 sampling completed, taking 13.52s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 7 sampling completed, taking 13.80s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 8 sampling completed, taking 13.86s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 9 sampling completed, taking 13.90s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 10 sampling completed, taking 14.10s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 11 sampling completed, taking 14.13s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 12 sampling completed, taking 14.10s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 13 sampling completed, taking 14.27s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 14 sampling completed, taking 14.35s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 15 sampling completed, taking 14.28s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 16 sampling completed, taking 14.37s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 17 sampling completed, taking 14.38s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 18 sampling completed, taking 14.58s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 19 sampling completed, taking 14.49s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 20 sampling completed, taking 14.42s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3287 - diffusion graph use 2264.22MB of memory: params 1640.45MB, runtime 623.77MB (static 69.56MB, dynamic 554.21MB)
[DEBUG] stable-diffusion.cpp:3288 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3573 - sampling completed, taking 278.37s
[DEBUG] stable-diffusion.cpp:3449 - vae context need 1153.12MB static memory, with work_size needing 1152.00MB
[DEBUG] stable-diffusion.cpp:3473 - computing vae graph completed, taking 54.55s
[INFO] stable-diffusion.cpp:3496 - vae graph use 2271.63MB of memory: params 94.51MB, runtime 2177.12MB (static 1153.12MB, dynamic 1024.00MB)
[DEBUG] stable-diffusion.cpp:3497 - 3145728 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3586 - decode_first_stage completed, taking 54.58s
[INFO] stable-diffusion.cpp:3600 - txt2img completed in 333.25s, use 2358.73MB of memory: peak params memory 1969.97MB, peak runtime memory 2177.12MB
save result image to 'output.png'

bin -p "a lovely cat" -v
Option:
 n_threads: 8
 mode: txt2img
 model_path: ../models/sd-v1-4-ggml-model-f16.bin
 output_path: output.png
 init_img:
 prompt: a lovely cat
 negative_prompt:
 cfg_scale: 7.00
 width: 512
 height: 512
 sample_method: eular a
 sample_steps: 20
 strength: 0.75
 seed: 42
System Info:
 BLAS = 1
 SSE3 = 0
 AVX = 0
 AVX2 = 0
 AVX512 = 0
 AVX512_VBMI = 0
 AVX512_VNNI = 0
 FMA = 0
 NEON = 1
 ARM_FMA = 1
 F16C = 0
 FP16_VA = 1
 WASM_SIMD = 0
 VSX = 0
[INFO] stable-diffusion.cpp:2687 - loading model from '../models/sd-v1-4-ggml-model-f16.bin'
[DEBUG] stable-diffusion.cpp:2695 - verifying magic
[DEBUG] stable-diffusion.cpp:2706 - loading hparams
[INFO] stable-diffusion.cpp:2712 - ftype: f16
[DEBUG] stable-diffusion.cpp:2718 - loading vocab
[DEBUG] stable-diffusion.cpp:2746 - ggml tensor size = 272 bytes
[DEBUG] stable-diffusion.cpp:2751 - clip params ctx size = 236.23 MB
[DEBUG] stable-diffusion.cpp:2770 - unet params ctx size = 1641.36 MB
[DEBUG] stable-diffusion.cpp:2791 - vae params ctx size = 95.51 MB
[DEBUG] stable-diffusion.cpp:2812 - preparing memory for the weights
[DEBUG] stable-diffusion.cpp:2828 - loading weights
[DEBUG] stable-diffusion.cpp:2932 - model size = 1969.67MB
[INFO] stable-diffusion.cpp:2941 - total params size = 1969.97MB (clip 235.01MB, unet 1640.45MB, vae 94.51MB)
[INFO] stable-diffusion.cpp:2943 - loading model from '../models/sd-v1-4-ggml-model-f16.bin' completed, taking 0.65s
[DEBUG] stable-diffusion.cpp:766 - parse 'a lovely cat' to [['a lovely cat', 1], ]
[DEBUG] stable-diffusion.cpp:353 - split prompt "a lovely cat" to tokens ["a</w>", "lovely</w>", "cat</w>", ]
[DEBUG] stable-diffusion.cpp:2982 - condition context need 10.19MB static memory, with work_size needing 9.00MB
[DEBUG] stable-diffusion.cpp:3006 - building condition graph completed: 633 nodes, 210 leafs
[DEBUG] stable-diffusion.cpp:3013 - computing condition graph completed, taking 0.16s
[INFO] stable-diffusion.cpp:3066 - condition graph use 248.13MB of memory: params 235.01MB, runtime 13.12MB (static 10.19MB, dynamic 2.93MB)
[DEBUG] stable-diffusion.cpp:3068 - 236544 bytes of dynamic memory has not been released yet
[DEBUG] stable-diffusion.cpp:766 - parse '' to [['', 1], ]
[DEBUG] stable-diffusion.cpp:353 - split prompt "" to tokens []
[DEBUG] stable-diffusion.cpp:2982 - condition context need 10.19MB static memory, with work_size needing 9.00MB
[DEBUG] stable-diffusion.cpp:3006 - building condition graph completed: 633 nodes, 210 leafs
[DEBUG] stable-diffusion.cpp:3013 - computing condition graph completed, taking 0.15s
[INFO] stable-diffusion.cpp:3066 - condition graph use 248.13MB of memory: params 235.01MB, runtime 13.12MB (static 10.19MB, dynamic 2.93MB)
[DEBUG] stable-diffusion.cpp:3068 - 236544 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3552 - get_learned_condition completed, taking 0.31s
[INFO] stable-diffusion.cpp:3568 - start sampling
[DEBUG] stable-diffusion.cpp:3119 - diffusion context need 69.56MB static memory, with work_size needing 67.50MB
[INFO] stable-diffusion.cpp:3260 - step 1 sampling completed, taking 11.67s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 2 sampling completed, taking 11.76s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 3 sampling completed, taking 11.72s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 4 sampling completed, taking 11.96s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 5 sampling completed, taking 12.19s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 6 sampling completed, taking 12.30s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 7 sampling completed, taking 12.40s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 8 sampling completed, taking 12.51s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 9 sampling completed, taking 12.71s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 10 sampling completed, taking 12.88s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 11 sampling completed, taking 12.77s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 12 sampling completed, taking 12.83s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 13 sampling completed, taking 12.83s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 14 sampling completed, taking 12.90s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 15 sampling completed, taking 12.96s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 16 sampling completed, taking 12.89s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 17 sampling completed, taking 13.05s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 18 sampling completed, taking 13.01s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 19 sampling completed, taking 12.98s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3260 - step 20 sampling completed, taking 13.09s
[DEBUG] stable-diffusion.cpp:3264 - diffusion graph use 623.77MB runtime memory: static 69.56MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3265 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3287 - diffusion graph use 2264.22MB of memory: params 1640.45MB, runtime 623.77MB (static 69.56MB, dynamic 554.21MB)
[DEBUG] stable-diffusion.cpp:3288 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3573 - sampling completed, taking 251.44s
[DEBUG] stable-diffusion.cpp:3449 - vae context need 1153.12MB static memory, with work_size needing 1152.00MB
[DEBUG] stable-diffusion.cpp:3473 - computing vae graph completed, taking 31.81s
[INFO] stable-diffusion.cpp:3496 - vae graph use 2271.63MB of memory: params 94.51MB, runtime 2177.12MB (static 1153.12MB, dynamic 1024.00MB)
[DEBUG] stable-diffusion.cpp:3497 - 3145728 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3586 - decode_first_stage completed, taking 31.84s
[INFO] stable-diffusion.cpp:3600 - txt2img completed in 283.59s, use 2358.73MB of memory: peak params memory 1969.97MB, peak runtime memory 2177.12MB
save result image to 'output.png'

Option:
 n_threads: 8
 mode: txt2img
 model_path: ../models/sd-v1-4-ggml-model-f16.bin
 output_path: output.png
 init_img:
 prompt: a lovely cat
 negative_prompt:
 cfg_scale: 7.00
 width: 512
 height: 512
 sample_method: eular a
 sample_steps: 20
 strength: 0.75
 seed: 42
System Info:
 BLAS = 1
 SSE3 = 0
 AVX = 0
 AVX2 = 0
 AVX512 = 0
 AVX512_VBMI = 0
 AVX512_VNNI = 0
 FMA = 0
 NEON = 1
 ARM_FMA = 1
 F16C = 0
 FP16_VA = 1
 WASM_SIMD = 0
 VSX = 0
[INFO] stable-diffusion.cpp:2687 - loading model from '../models/sd-v1-4-ggml-model-f16.bin'
[DEBUG] stable-diffusion.cpp:2695 - verifying magic
[DEBUG] stable-diffusion.cpp:2706 - loading hparams
[INFO] stable-diffusion.cpp:2712 - ftype: f16
[DEBUG] stable-diffusion.cpp:2718 - loading vocab
[DEBUG] stable-diffusion.cpp:2746 - ggml tensor size = 272 bytes
[DEBUG] stable-diffusion.cpp:2751 - clip params ctx size = 236.23 MB
[DEBUG] stable-diffusion.cpp:2770 - unet params ctx size = 1641.36 MB
[DEBUG] stable-diffusion.cpp:2791 - vae params ctx size = 95.51 MB
[DEBUG] stable-diffusion.cpp:2812 - preparing memory for the weights
[DEBUG] stable-diffusion.cpp:2828 - loading weights
[DEBUG] stable-diffusion.cpp:2932 - model size = 1969.67MB
[INFO] stable-diffusion.cpp:2941 - total params size = 1969.97MB (clip 235.01MB, unet 1640.45MB, vae 94.51MB)
[INFO] stable-diffusion.cpp:2943 - loading model from '../models/sd-v1-4-ggml-model-f16.bin' completed, taking 0.64s
[DEBUG] stable-diffusion.cpp:766 - parse 'a lovely cat' to [['a lovely cat', 1], ]
[DEBUG] stable-diffusion.cpp:353 - split prompt "a lovely cat" to tokens ["a</w>", "lovely</w>", "cat</w>", ]
[DEBUG] stable-diffusion.cpp:2982 - condition context need 10.19MB static memory, with work_size needing 9.00MB
[DEBUG] stable-diffusion.cpp:3006 - building condition graph completed: 633 nodes, 210 leafs
[DEBUG] stable-diffusion.cpp:3013 - computing condition graph completed, taking 0.14s
[INFO] stable-diffusion.cpp:3066 - condition graph use 248.13MB of memory: params 235.01MB, runtime 13.12MB (static 10.19MB, dynamic 2.93MB)
[DEBUG] stable-diffusion.cpp:3068 - 236544 bytes of dynamic memory has not been released yet
[DEBUG] stable-diffusion.cpp:766 - parse '' to [['', 1], ]
[DEBUG] stable-diffusion.cpp:353 - split prompt "" to tokens []
[DEBUG] stable-diffusion.cpp:2982 - condition context need 10.19MB static memory, with work_size needing 9.00MB
[DEBUG] stable-diffusion.cpp:3006 - building condition graph completed: 633 nodes, 210 leafs
[DEBUG] stable-diffusion.cpp:3013 - computing condition graph completed, taking 0.13s
[INFO] stable-diffusion.cpp:3066 - condition graph use 248.13MB of memory: params 235.01MB, runtime 13.12MB (static 10.19MB, dynamic 2.93MB)
[DEBUG] stable-diffusion.cpp:3068 - 236544 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3564 - get_learned_condition completed, taking 0.26s
[INFO] stable-diffusion.cpp:3580 - start sampling
[DEBUG] stable-diffusion.cpp:3119 - diffusion context need 27.09MB static memory, with work_size needing 25.00MB
[INFO] stable-diffusion.cpp:3264 - step 1 sampling completed, taking 10.71s
[DEBUG] stable-diffusion.cpp:3268 - diffusion graph use 581.30MB runtime memory: static 27.09MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3269 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3264 - step 2 sampling completed, taking 10.78s
[DEBUG] stable-diffusion.cpp:3268 - diffusion graph use 581.30MB runtime memory: static 27.09MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3269 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3264 - step 3 sampling completed, taking 11.06s
[DEBUG] stable-diffusion.cpp:3268 - diffusion graph use 581.30MB runtime memory: static 27.09MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3269 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3264 - step 4 sampling completed, taking 11.17s
[DEBUG] stable-diffusion.cpp:3268 - diffusion graph use 581.30MB runtime memory: static 27.09MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3269 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3264 - step 5 sampling completed, taking 11.33s
[DEBUG] stable-diffusion.cpp:3268 - diffusion graph use 581.30MB runtime memory: static 27.09MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3269 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3264 - step 6 sampling completed, taking 11.45s
[DEBUG] stable-diffusion.cpp:3268 - diffusion graph use 581.30MB runtime memory: static 27.09MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3269 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3264 - step 7 sampling completed, taking 11.51s
[DEBUG] stable-diffusion.cpp:3268 - diffusion graph use 581.30MB runtime memory: static 27.09MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3269 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3264 - step 8 sampling completed, taking 11.61s
[DEBUG] stable-diffusion.cpp:3268 - diffusion graph use 581.30MB runtime memory: static 27.09MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3269 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3264 - step 9 sampling completed, taking 11.70s
[DEBUG] stable-diffusion.cpp:3268 - diffusion graph use 581.30MB runtime memory: static 27.09MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3269 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3264 - step 10 sampling completed, taking 11.68s
[DEBUG] stable-diffusion.cpp:3268 - diffusion graph use 581.30MB runtime memory: static 27.09MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3269 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3264 - step 11 sampling completed, taking 11.84s
[DEBUG] stable-diffusion.cpp:3268 - diffusion graph use 581.30MB runtime memory: static 27.09MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3269 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3264 - step 12 sampling completed, taking 11.87s
[DEBUG] stable-diffusion.cpp:3268 - diffusion graph use 581.30MB runtime memory: static 27.09MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3269 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3264 - step 13 sampling completed, taking 11.78s
[DEBUG] stable-diffusion.cpp:3268 - diffusion graph use 581.30MB runtime memory: static 27.09MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3269 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3264 - step 14 sampling completed, taking 11.85s
[DEBUG] stable-diffusion.cpp:3268 - diffusion graph use 581.30MB runtime memory: static 27.09MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3269 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3264 - step 15 sampling completed, taking 11.77s
[DEBUG] stable-diffusion.cpp:3268 - diffusion graph use 581.30MB runtime memory: static 27.09MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3269 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3264 - step 16 sampling completed, taking 11.85s
[DEBUG] stable-diffusion.cpp:3268 - diffusion graph use 581.30MB runtime memory: static 27.09MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3269 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3264 - step 17 sampling completed, taking 11.82s
[DEBUG] stable-diffusion.cpp:3268 - diffusion graph use 581.30MB runtime memory: static 27.09MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3269 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3264 - step 18 sampling completed, taking 11.95s
[DEBUG] stable-diffusion.cpp:3268 - diffusion graph use 581.30MB runtime memory: static 27.09MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3269 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3264 - step 19 sampling completed, taking 11.91s
[DEBUG] stable-diffusion.cpp:3268 - diffusion graph use 581.30MB runtime memory: static 27.09MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3269 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3264 - step 20 sampling completed, taking 11.94s
[DEBUG] stable-diffusion.cpp:3268 - diffusion graph use 581.30MB runtime memory: static 27.09MB, dynamic 554.21MB
[DEBUG] stable-diffusion.cpp:3269 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3291 - diffusion graph use 2221.75MB of memory: params 1640.45MB, runtime 581.30MB (static 27.09MB, dynamic 554.21MB)
[DEBUG] stable-diffusion.cpp:3292 - 65536 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3585 - sampling completed, taking 231.60s
[DEBUG] stable-diffusion.cpp:3457 - vae context need 1.14MB static memory, with work_size needing 0.00MB
[DEBUG] stable-diffusion.cpp:3485 - computing vae graph completed, taking 20.08s
[INFO] stable-diffusion.cpp:3508 - vae graph use 1759.64MB of memory: params 94.51MB, runtime 1665.14MB (static 1.14MB, dynamic 1664.00MB)
[DEBUG] stable-diffusion.cpp:3509 - 3145728 bytes of dynamic memory has not been released yet
[INFO] stable-diffusion.cpp:3598 - decode_first_stage completed, taking 20.09s
[INFO] stable-diffusion.cpp:3612 - txt2img completed in 251.95s, use 2316.26MB of memory: peak params memory 1969.97MB, peak runtime memory 1665.14MB
save result image to 'output.png'