>sd.exe -m sd_xl_turbo_1.0.q8_0.gguf --taesd taesdxl.q8_0.gguf -o output.png -p "A lovely cat" --cfg-scale 1 --steps 1 --verbose
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = NVIDIA GeForce GTX 1660 SUPER (NVIDIA) | uma: 0 | fp16: 1 | warp size: 32 | shared memory: 49152 | int dot: 0 | matrix cores: none
[INFO ] stable-diffusion.cpp:191  - loading model from 'sd_xl_turbo_1.0.q8_0.gguf'
[INFO ] model.cpp:995  - load sd_xl_turbo_1.0.q8_0.gguf using gguf format
[INFO ] stable-diffusion.cpp:242  - Version: SDXL
[INFO ] stable-diffusion.cpp:276  - Weight type:                 q8_0
[INFO ] stable-diffusion.cpp:277  - Conditioner weight type:     q8_0
[INFO ] stable-diffusion.cpp:278  - Diffusion model weight type: q8_0
[INFO ] stable-diffusion.cpp:279  - VAE weight type:             f32
  |==================================================| 2641/2641 - 38.46it/s�[K[K
[INFO ] stable-diffusion.cpp:557  - total params memory size = 4138.55MB (VRAM 4138.55MB, RAM 0.00MB): clip 1118.92MB(VRAM), unet 2925.17MB(VRAM), vae 94.47MB(VRAM), controlnet 0.00MB(VRAM), pmid 0.00MB(VRAM)
[INFO ] stable-diffusion.cpp:561  - loading model from 'sd_xl_turbo_1.0.q8_0.gguf' completed, taking 30.62s
[INFO ] stable-diffusion.cpp:603  - running in eps-prediction mode
[INFO ] stable-diffusion.cpp:2007 - TXT2IMG
[INFO ] stable-diffusion.cpp:737  - Attempting to apply 0 LoRAs
[INFO ] stable-diffusion.cpp:1561 - apply_loras completed, taking 0.00s
[INFO ] stable-diffusion.cpp:1695 - get_learned_condition completed, taking 1688 ms
[INFO ] stable-diffusion.cpp:1718 - sampling using Euler A method
[INFO ] stable-diffusion.cpp:1767 - generating image: 1/1 - seed 42
  |==================================================| 1/1 - 1.55s/it
[INFO ] stable-diffusion.cpp:1805 - sampling completed, taking 1.56s
[INFO ] stable-diffusion.cpp:1813 - generating 1 latent images completed, taking 1.60s
[INFO ] stable-diffusion.cpp:1816 - decoding 1 latents
[INFO ] stable-diffusion.cpp:1826 - latent 1 decoded, taking 2.99s
[INFO ] stable-diffusion.cpp:1830 - decode_first_stage completed, taking 2.99s
[INFO ] stable-diffusion.cpp:2078 - generate_image completed in 6.29s
save result PNG image to 'output.png'