exceptions must derive from BaseException

[Amazon90]

ComfyUI Error Report

Error Details

• Node Type: InstantIR_Loader
• Exception Type: TypeError

• Exception Message: exceptions must derive from BaseException

  Stack Trace

  
  File "D:\ComfyUI\execution.py", line 323, in execute
  output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
  
  File "D:\ComfyUI\execution.py", line 198, in get_output_data
  return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
  
  File "D:\ComfyUI\execution.py", line 169, in _map_node_over_list
  process_inputs(input_dict, i)
  
  File "D:\ComfyUI\execution.py", line 158, in process_inputs
  results.append(getattr(obj, func)(**inputs))
  
  File "D:\ComfyUI\custom_nodes\ComfyUI_InstantIR_Wrapper\InstantIR_node.py", line 91, in main_
  raise "need chocie a lora checkpoint"

## System Information
- **ComfyUI Version:** v0.2.7-13-g8a52810
- **Arguments:** D:\ComfyUI\main.py --auto-launch --preview-method auto --disable-cuda-malloc --fast
- **OS:** nt
- **Python Version:** 3.10.11 (tags/v3.10.11:7d4cc5a, Apr  5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]
- **Embedded Python:** false
- **PyTorch Version:** 2.5.1+cu124
## Devices

- **Name:** cuda:0 NVIDIA GeForce RTX 4070 Ti : cudaMallocAsync
  - **Type:** cuda
  - **VRAM Total:** 12878086144
  - **VRAM Free:** 6538381024
  - **Torch VRAM Total:** 5033164800
  - **Torch VRAM Free:** 60278496

[smthemex]

[Amazon90]

Why are the results of image generation so blurry?

[smthemex]

more step and turn off use_clip_encoder

[Amazon90]

more step and turn off use_clip_encoder

The result based on your suggestion is still blurry.

[Amazon90]

any SDXL checkpoint ── sdxl_lightning_8step.safetensors

├── ComfyUI/models/InstantIR/models | ├── adapter.pt | ├── aggregator.pt | ├── previewer_lora_weights.bin ├── ComfyUI\models\InstantIR\dino | ├── config.json | ├── model.safetensors | ├── preprocessor_config.json ├── ComfyUI\models\loras | ├── lcm-lora-sdxl.safetensors

Are these models being used incorrectly?

[smthemex]

yeah, it's correct. you can try add ' a man image' in prompt

[Amazon90]

yeah, it's correct. you can try add ' a man image' in prompt

Following your suggestion, but the result is still blurry. I‘m downloading SDXL base 1.0, it might be an issue with the lightning model.

[Amazon90]

I doubt whether it is really effective. If that's the case, it can't compare to the Flux ControlNet upscaler at all.

[smthemex]

Yes, this image restoration method does have a problem of sometimes good and sometimes bad

[Amazon90]

Yes, this image restoration method does have a problem of sometimes good and sometimes bad

Thank you. Thank you for your efforts.