Error : Could not deserialize engine. See log for details.

[volksamt]

The tox was working just fine on my previous machine, I tried a fresh install on my current machine first with a manual install. Got a number of errors. Migrated to the portable build. Webui builds engines without errors but when I go to .tox to load them I get this error.
Could not deserialize engine. See log for details.

Python version 3.11 (embeded)
Cuda Version 11.8

[adityapadma]

Same for me I am trying to get Touch diffusion working for the first time. I am new to using AI in Touch Designer (very little ML, GEN AI Knowledge) Can someone help me understand what is happening and What I can do to get this working?

Loading TensorRT engine: C:\Users\CI_Lab\Downloads\TouchDiffusion-main\engines\sd-turbo--sd_1.5_turbo--512--512--None--2--2--img2img--None--None\unet.engine
[I] Loading bytes from C:\Users\CI_Lab\Downloads\TouchDiffusion-main\engines\sd-turbo--sd_1.5_turbo--512--512--None--2--2--img2img--None--None\unet.engine
[E] IRuntime::deserializeCudaEngine: Error Code 1: Internal Error (Failed due to an old deserialization call on a newer plan file. This might happen when the plan file was built from an older TensorRT version. You can use trtexec --getPlanVersionOnly to check the version of TensorRT that was used to create the plan file.)
Keyword arguments {'add_watermarker': False} are not expected by StableDiffusionPipeline and will be ignored.
Loading pipeline components...: 0%| | 0/5 [00:00<?, ?it/s]
Loading pipeline components...: 40%|#### | 2/5 [00:00<00:00, 14.12it/s]
Loading pipeline components...: 80%|######## | 4/5 [00:00<00:00, 13.30it/s]
Loading pipeline components...: 100%|##########| 5/5 [00:00<00:00, 14.75it/s]
You have disabled the safety checker for <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> by passing safety_checker=None. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at huggingface/diffusers#254 .
The config attributes {'skip_prk_steps': True} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.
[!] Could not deserialize engine. See log for details.
512 512