"log_vml_cpu" not implemented for 'Half'

[anonymous-person]

I updated today to commit: 2c1bb46, and now I get this mysterious error message when I try to run txt2img or img2img via the UI. Any ideas what it means? I have some custom Dream Booth models that use 'half' precision, but i get this error even for the original 1.4 SD model.

Logs:
File "/home/me/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 159, in __init__ self.model_wrap = denoiser(sd_model, quantize=shared.opts.enable_quantization) File "/home/me/stable-diffusion-webui/repositories/k-diffusion/k_diffusion/external.py", line 135, in __init__ super().__init__(model, model.alphas_cumprod, quantize=quantize) File "/home/me/stable-diffusion-webui/repositories/k-diffusion/k_diffusion/external.py", line 92, in __init__ super().__init__(((1 - alphas_cumprod) / alphas_cumprod) ** 0.5, quantize) File "/home/me/stable-diffusion-webui/repositories/k-diffusion/k_diffusion/external.py", line 48, in __init__ self.register_buffer('log_sigmas', sigmas.log()) RuntimeError: "log_vml_cpu" not implemented for 'Half'

[anonymous-person]

Hmm, adding "--precision full --no-half" to my command line options works around the issue, but now image generation takes 5x longer. :(

[anonymous-person]

Never mind. Rebooting solved the issue.

[oostack]

rebooting is not a resolution, even rebooting solved the issue.

[nathanisayas]

how do you reboot it as in what buttons to press