ValueError: unet/hotshot_xl.py does not exist in hotshotco/Hotshot-XL

Question

I am thinking of creating an AI video generation app that incorporates Hotshot. However, the inference.py cloned directly from github works, but when I import the modified inference.py in the app I am building, I get the following error. ValueError: unet/hotshot_xl.py as defined in model_index.json does not exist in hotshotco/Hotshot-XL and is not a module in 'diffusers/pipelines'.

Modified inference.py

def main(pretrained_path='hotshotco/Hotshot-XL',
         xformers=False,
         spatial_unet_base=None,
         lora=None,
         output='output_scuba.gif',
         steps=30,
         prompt='Sasquatch scuba diving, anime style',
         negative_prompt='blurry',
         seed=455,
         width=672,
         height=384,
         target_width=512,
         target_height=512,
         og_width=1920,
         og_height=1080,
         video_length=8,
         video_duration=1000,
         low_vram_mode=False,
         scheduler='EulerAncestralDiscreteScheduler',
         control_type=None, 
         controlnet_conditioning_scale=0.7,
         control_guidance_start=0.0,
         control_guidance_end=1.0,
         gif=None,
         precision='f16',
         autocast=None):
    
    args = argparse.Namespace(
        pretrained_path=pretrained_path,
        xformers=xformers,
        spatial_unet_base=spatial_unet_base,
        lora=lora,
        output=output,
        steps=steps,
        prompt=prompt,
        negative_prompt=negative_prompt,
        seed=seed,
        width=width,
        height=height,
        target_width=target_width,
        target_height=target_height,
        og_width=og_width,
        og_height=og_height,
        video_length=video_length,
        video_duration=video_duration,
        low_vram_mode=low_vram_mode,
        scheduler=scheduler,
        control_type=control_type,
        controlnet_conditioning_scale=controlnet_conditioning_scale,
        control_guidance_start=control_guidance_start,
        control_guidance_end=control_guidance_end,
        gif=gif,
        precision=precision,
        autocast=autocast
    )
# The following is the same as inference.py

Some of the Python code for my app

if generate_value == 4:
            main(pretrained_path='hotshotco/Hotshot-XL',
                 xformers=False,
                 spatial_unet_base=None,
                 lora=None,
                 output=filename_vid,
                 steps=steps,
                 prompt=prompt,
                 negative_prompt=negative_prompt,
                 seed=455,
                 width=width,
                 height=height,
                 target_width=width,
                 target_height=height,
                 og_width=width,
                 og_height=height,
                 video_length=video_length,
                 video_duration=1000,
                 low_vram_mode=False,
                 scheduler='EulerAncestralDiscreteScheduler',
                 control_type=None,
                 controlnet_conditioning_scale=0.7,
                 control_guidance_start=0.0,
                 control_guidance_end=1.0,
                 gif=None,
                 precision=precision,
                 autocast=None
                )

(These were all translated from Japanese by DeepL)

I was hoping to incorporate the main function with prompt, negative prompt, length of video to generate, precision, width and height as arguments in my app and then create a gif based on it, but I got an error.

Answer 1

I found the cause of this problem. It is the difference between running in py or python.

# Success example:
python main.py

# Failure example:
py main.py.
```