Segmentation fault

[Siddharth1India]

Error says:

$ ./bin/sd -m ../models/sd-v1-4-ggml-model-q4_0.bin -p "cat"
[INFO]  stable-diffusion.cpp:2830 - loading model from '../models/sd-v1-4-ggml-model-q4_0.bin'
[INFO]  stable-diffusion.cpp:2858 - model type: SD1.x
[INFO]  stable-diffusion.cpp:2866 - ftype: q4_0
[INFO]  stable-diffusion.cpp:3094 - total params size = 1431.17MB (clip 66.46MB, unet 1270.21MB, vae 94.50MB)
[INFO]  stable-diffusion.cpp:3096 - loading model from '../models/sd-v1-4-ggml-model-q4_0.bin' completed, taking 2.13s
[INFO]  stable-diffusion.cpp:3121 - running in eps-prediction mode
[INFO]  stable-diffusion.cpp:3372 - condition graph use 79.79MB of memory: params 66.46MB, runtime 13.33MB (static 10.40MB, dynamic 2.93MB)
[INFO]  stable-diffusion.cpp:3372 - condition graph use 79.79MB of memory: params 66.46MB, runtime 13.33MB (static 10.40MB, dynamic 2.93MB)
[INFO]  stable-diffusion.cpp:4228 - get_learned_condition completed, taking 0.89s
[INFO]  stable-diffusion.cpp:4244 - start sampling
[INFO]  stable-diffusion.cpp:3565 - sampling using Euler A method
Segmentation fault

Idk what is an issue because nothing is written here.

[leejet]

Could you please provide me with information about your environment? This should include your CPU architecture, operating system, and the compilation parameters for sd.cpp. Or you can use the '-v' flag when executing the command to get detailed output.

[tap222]

Also, I am getting the same error of segmentation fault.

./bin/sd -m "../models/v2-1_768-nonema-pruned.q4_0.gguf" -H 128 -W 128 -p 'a lovely cat holding a sign says "Stable diffusion 3"' --sampling-method euler -v --steps 30

[INFO ] stable-diffusion.cpp:195 - loading model from '../models/v2-1_768-nonema-pruned.q4_0.gguf' [INFO ] model.cpp:885 - load ../models/v2-1_768-nonema-pruned.q4_0.gguf using gguf format [DEBUG] model.cpp:902 - init from '../models/v2-1_768-nonema-pruned.q4_0.gguf' [INFO ] stable-diffusion.cpp:242 - Version: SD 2.x [INFO ] stable-diffusion.cpp:275 - Weight type: q4_0 [INFO ] stable-diffusion.cpp:276 - Conditioner weight type: q4_0 [INFO ] stable-diffusion.cpp:277 - Diffusion model weight type: q4_0 [INFO ] stable-diffusion.cpp:278 - VAE weight type: q4_0 [DEBUG] stable-diffusion.cpp:280 - ggml tensor size = 400 bytes [DEBUG] clip.hpp:171 - vocab size: 49408 [DEBUG] clip.hpp:182 - trigger word img already in vocab [DEBUG] ggml_extend.hpp:1111 - clip params backend buffer size = 190.67 MB(VRAM) (388 tensors) [DEBUG] ggml_extend.hpp:1111 - unet params backend buffer size = 1280.18 MB(VRAM) (686 tensors) [DEBUG] ggml_extend.hpp:1111 - vae params backend buffer size = 94.47 MB(VRAM) (140 tensors) [DEBUG] stable-diffusion.cpp:417 - loading weights [DEBUG] model.cpp:1698 - loading tensors from ../models/v2-1_768-nonema-pruned.q4_0.gguf |==================================================| 1323/1323 - 333.33it/s [INFO ] stable-diffusion.cpp:516 - total params memory size = 1565.32MB (VRAM 1565.32MB, RAM 0.00MB): clip 190.67MB(VRAM), unet 1280.18MB(VRAM), vae 94.47MB(VRAM), controlnet 0.00MB(VRAM), pmid 0.00MB(VRAM) [INFO ] stable-diffusion.cpp:520 - loading model from '../models/v2-1_768-nonema-pruned.q4_0.gguf' completed, taking 1.86s zsh: segmentation fault ./bin/sd -m "../models/v2-1_768-nonema-pruned.q4_0.gguf" -H 128 -W 128 -p