You have disabled the safety checker for <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'>

[motoyagugu]

got prompt
Loading pipeline components...: 100%|█████████████████████████████████████████████████████████████| 5/5 [00:04<00:00, 1.10it/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 .
You have disabled the safety checker for <class 'K:\AI\Comfy_nunchaku\custom_nodes\ComfyUI_InvSR.comfyui_invsr_trimmed.pipeline_stable_diffusion_inversion_sr.StableDiffusionInvEnhancePipeline'> 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 .
Activating gradient checkpoing for vae...
!!! Exception during processing !!! maximum recursion depth exceeded while getting the repr of an object
Traceback (most recent call last):

[motoyagugu]

LoadInvSRModels
maximum recursion depth exceeded while getting the repr of an object

[yuvraj108c]

Downgrade diffusers
it only works with diffusers>=0.30.0,<=0.32.2

[ALT7580]

For the "maximum recursion depth" issue, I kept diffusers 0.33.1 and commented these lines in sampler_invsr.py instead, the node works now.
if self.configs.gradient_checkpointing_vae:
self.write_log(f"Activating gradient checkpoing for vae...")
# sd_pipe.vae._set_gradient_checkpointing(sd_pipe.vae.encoder, True)
# sd_pipe.vae._set_gradient_checkpointing(sd_pipe.vae.decoder, True)

[yuvraj108c]

@ALT7580 does it affect performance?

[ALT7580]

@yuvraj108c not sure as I did a fresh install and I don't have a baseline to match. I am also using 8 GB VRAM, and I'm getting a lot of OOM errors. I was able to process a 320x480 image in about 80 seconds. I used these settings.