runtime error

Exit code: 1. Reason: rs: 0%| | 0.00/336M [00:00<?, ?B/s] vae/diffusion_pytorch_model.safetensors: 71%|███████ | 239M/336M [00:01<00:00, 239MB/s] vae/diffusion_pytorch_model.safetensors: 100%|██████████| 336M/336M [00:01<00:00, 296MB/s] Loading pipeline components...: 0%| | 0/4 [00:00<?, ?it/s]Using `use_fast=True` but `torchvision` is not available. Falling back to the slow image processor. Loading pipeline components...: 50%|█████ | 2/4 [00:01<00:01, 1.33it/s] Loading pipeline components...: 100%|██████████| 4/4 [00:01<00:00, 2.65it/s] 2026-03-02 11:20:04 - __main__ - INFO - Loading NSFW detector... preprocessor_config.json: 0%| | 0.00/325 [00:00<?, ?B/s] preprocessor_config.json: 100%|██████████| 325/325 [00:00<00:00, 1.73MB/s] config.json: 0%| | 0.00/724 [00:00<?, ?B/s] config.json: 100%|██████████| 724/724 [00:00<00:00, 4.28MB/s] Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`. model.safetensors: 0%| | 0.00/343M [00:00<?, ?B/s] model.safetensors: 22%|██▏ | 75.1M/343M [00:01<00:04, 59.3MB/s] model.safetensors: 100%|██████████| 343M/343M [00:01<00:00, 174MB/s] 2026-03-02 11:20:07 - __main__ - INFO - NSFW detector loaded successfully. Traceback (most recent call last): File "/home/user/app/app.py", line 210, in <module> def _generate_image(prompt_embeds, image_list, width, height, num_inference_steps, guidance_scale, seed, progress=gr.Progress()): File "/usr/local/lib/python3.10/site-packages/spaces/zero/decorator.py", line 115, in _GPU TypeError: regular_function_wrapper() takes 2 positional arguments but 3 were given

Container logs: