runtime error

ative_v1.3.pt File successfully downloaded and saved: models/embeddings/JuggernautNegative-neg.pt File successfully downloaded and saved: models/Lora/SDXLrender_v2.0.safetensors File successfully downloaded and saved: models/Lora/more_details.safetensors File successfully downloaded and saved: models/ControlNet/control_v11f1e_sd15_tile.pth File successfully downloaded and saved: models/VAE/vae-ft-mse-840000-ema-pruned.safetensors Starting to load the pipeline... Setting up the pipeline... Loading pipeline components...: 0%| | 0/6 [00:00<?, ?it/s]Some weights of the model checkpoint were not used when initializing CLIPTextModel: ['text_model.embeddings.position_ids'] Loading pipeline components...: 83%|████████▎ | 5/6 [00:01<00:00, 3.21it/s] Loading pipeline components...: 100%|██████████| 6/6 [00:01<00:00, 3.42it/s] /usr/local/lib/python3.10/site-packages/peft/tuners/lora/model.py:388: UserWarning: Adapter cannot be set when the model is merged. Unmerging the model first. warnings.warn("Adapter cannot be set when the model is merged. Unmerging the model first.") The current API is supported for operating with a single LoRA file. You are trying to load and fuse more than one LoRA which is not well-supported. setup_pipeline took 309.57 seconds Moving pipeline to device: cuda load took 309.66 seconds Traceback (most recent call last): File "/home/user/app/app.py", line 176, in <module> def gradio_process_image(input_image, resolution, num_inference_steps, strength, hdr, guidance_scale): File "/usr/local/lib/python3.10/site-packages/spaces/zero/decorator.py", line 79, in GPU return _GPU(task, duration) File "/usr/local/lib/python3.10/site-packages/spaces/zero/decorator.py", line 113, in _GPU client.startup_report() File "/usr/local/lib/python3.10/site-packages/spaces/zero/client.py", line 45, in startup_report raise RuntimeError("Error while initializing ZeroGPU: Unknown") RuntimeError: Error while initializing ZeroGPU: Unknown

Container logs: