runtime error

Exit code: 1. Reason: fetensors: 6%|▌ | 269M/4.81G [00:07<01:31, 49.6MB/s] ltx-2-2.4b-pruned.safetensors: 8%|▊ | 372M/4.81G [00:09<01:27, 50.7MB/s] ltx-2-2.4b-pruned.safetensors: 30%|██▉ | 1.42G/4.81G [00:10<00:12, 273MB/s] ltx-2-2.4b-pruned.safetensors: 38%|███▊ | 1.82G/4.81G [00:11<00:10, 286MB/s] ltx-2-2.4b-pruned.safetensors: 45%|████▌ | 2.18G/4.81G [00:12<00:09, 278MB/s] ltx-2-2.4b-pruned.safetensors: 86%|████████▌ | 4.12G/4.81G [00:14<00:01, 632MB/s] ltx-2-2.4b-pruned.safetensors: 100%|██████████| 4.81G/4.81G [00:15<00:00, 320MB/s] Loading VAE configs from Hugging Face repo... video_vae_config.json: 0%| | 0.00/423 [00:00<?, ?B/s] video_vae_config.json: 100%|██████████| 423/423 [00:00<00:00, 1.82MB/s] audio_vae_config.json: 0%| | 0.00/530 [00:00<?, ?B/s] audio_vae_config.json: 100%|██████████| 530/530 [00:00<00:00, 3.48MB/s] Separated: 883 transformer, 187 vae, 102 audio_vae keys Loading 2.4B Transformer... Loading Video VAE with pruned config... The config attributes {'sample_size': 256} were passed to AutoencoderKLLTX2Video, but are not expected and will be ignored. Please verify your config.json configuration file. Traceback (most recent call last): File "/app/app.py", line 123, in <module> pipeline = load_lean_pipeline() File "/app/app.py", line 87, in load_lean_pipeline missing, unexpected = vae.load_state_dict(vae_state, strict=False) ~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/torch/nn/modules/module.py", line 2629, in load_state_dict raise RuntimeError( ...<3 lines>... ) RuntimeError: Error(s) in loading state_dict for AutoencoderKLLTX2Video: size mismatch for encoder.conv_out.conv.weight: copying a param with shape torch.Size([129, 2048, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([129, 512, 3, 3, 3]).

Container logs: