[INFO] setup plugin alembic.autogenerate.schemas
[INFO] setup plugin alembic.autogenerate.tables
[INFO] setup plugin alembic.autogenerate.types
[INFO] setup plugin alembic.autogenerate.constraints
[INFO] setup plugin alembic.autogenerate.defaults
[INFO] setup plugin alembic.autogenerate.comments
[WARNING] --disable-api-nodes is deprecated and will be removed in a future version. It currently behaves like --offline. Use --offline to keep the frontend offline, or --disable-partner-nodes to only disable partner nodes.
[INFO] Adding extra search path diffusion_models <home>/bild-raster-2910/models/diffusion_models
[INFO] Adding extra search path text_encoders <home>/bild-raster-2910/models/text_encoders
[INFO] Adding extra search path vae <home>/bild-raster-2910/models/vae
[INFO] Setting output directory to: <home>/bild-raster-2910/out/zimage_int8-d3
[INFO] Setting user directory to: <home>/bild-raster-2910/user
[INFO] Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope1_', 'apply_rope_', 'apply_rope_split_half', 'apply_rope_split_half1', 'apply_rope_split_half1_', 'apply_rope_split_half_', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_embedding', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'dequantize_w4a8_int8_weight', 'fp16_conv3d', 'fp16_conv3d_out', 'fp16_linear', 'gemv_awq_w4a16', 'group_norm_silu_pad3d', 'group_norm_silu_pad3d_out', 'group_norm_stats3d', 'int8_linear', 'int8_linear_modulated', 'int8_linear_rms_modulated', 'na3d', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'quantize_w4a8_int8_weight', 'rms_adaln', 'rms_gated_residual', 'rms_rope', 'rms_rope1', 'rms_rope1_', 'rms_rope_', 'rms_rope_split_half', 'rms_rope_split_half1', 'rms_rope_split_half1_', 'rms_rope_split_half_', 'rotate_int8_convrot_weight', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'sol_attn', 'stochastic_rounding_fp8', 'w4a8_int8_linear', 'w4a8_packed_linear']}
[INFO] Found comfy_kitchen backend ascend: {'available': False, 'disabled': False, 'unavailable_reason': "torch-npu is not installed: No module named 'torch_npu'", 'capabilities': []}
[INFO] Found comfy_kitchen backend cuda: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope1_', 'apply_rope_', 'apply_rope_split_half', 'apply_rope_split_half1', 'apply_rope_split_half1_', 'apply_rope_split_half_', 'closest_point_on_mesh', 'connected_components', 'convrot_w4a4_linear', 'delaunay3d', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'dequantize_w4a8_int8_weight', 'edge_collapse_checks', 'fp16_conv3d', 'fp16_conv3d_out', 'fp16_linear', 'gemv_awq_w4a16', 'group_norm_silu_pad3d', 'group_norm_silu_pad3d_out', 'group_norm_stats3d', 'int8_linear', 'mesh_bvh', 'min_cut', 'na3d', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'quantize_w4a8_int8_weight', 'rms_adaln', 'rms_rope', 'rms_rope1', 'rms_rope1_', 'rms_rope_', 'rms_rope_split_half', 'rms_rope_split_half1', 'rms_rope_split_half1_', 'rms_rope_split_half_', 'rotate_int8_convrot_weight', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'sol_attn', 'stochastic_rounding_fp8', 'w4a8_int8_linear', 'w4a8_packed_linear']}
[INFO] Found comfy_kitchen backend triton: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope1_', 'apply_rope_', 'apply_rope_split_half', 'apply_rope_split_half1', 'apply_rope_split_half1_', 'apply_rope_split_half_', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'int8_linear', 'na3d', 'quantize_and_rotate_rowwise', 'quantize_int8_rowwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'rms_adaln', 'rms_rope', 'rms_rope1', 'rms_rope1_', 'rms_rope_', 'rms_rope_split_half', 'rms_rope_split_half1', 'rms_rope_split_half1_', 'rms_rope_split_half_', 'w4a8_int8_linear']}
[INFO] Found comfy_kitchen backend hip: {'available': False, 'disabled': False, 'unavailable_reason': 'PyTorch ROCm/HIP runtime not available', 'capabilities': []}
[INFO] Checkpoint files will always be loaded safely.
[INFO] Total VRAM 32150 MB, total RAM 94192 MB
[INFO] pytorch version: 2.14.0.dev20260706+cu130
[INFO] Set vram state to: NORMAL_VRAM
[INFO] Device: cuda:0 NVIDIA GeForce RTX 5090 : cudaMallocAsync
[INFO] Using async weight offloading with 2 streams
[INFO] Enabled pinned memory 84772.0
[INFO] Using pytorch attention
[INFO] aimdo: /project/src/control.c:283:INFO:comfy-aimdo inited for GPU: NVIDIA GeForce RTX 5090 (VRAM: 32149 MB)
[INFO] DynamicVRAM support detected and enabled
[INFO] Python version: 3.13.5 (main, May  5 2026, 21:05:52) [GCC 14.2.0]
[INFO] ComfyUI version: 0.43.0
[INFO] comfy-aimdo version: 0.6.0
[INFO] comfy-kitchen version: 0.2.40
[INFO] Setting temp directory to: <home>/bild-raster-2910/temp/temp
[INFO] comfy-aimdo version: 0.6.0
[INFO] comfy-kitchen version: 0.2.40
[WARNING] ________________________________________________________________________
WARNING WARNING WARNING WARNING WARNING

Installed comfyui-frontend-package version 1.53.6 is lower than the recommended version 1.57.4.
Installed comfyui-workflow-templates version 0.11.66 is lower than the recommended version 0.11.97.
Installed comfyui-embedded-docs version 0.5.12 is lower than the recommended version 0.5.15.

Please install the updated requirements.txt file by running:
<home>/bild-raster-2910/venv/bin/python -m pip install -r <home>/bild-raster-2910/ComfyUI/requirements.txt
If you are on the portable package you can run: update\update_comfyui.bat to solve this problem.
________________________________________________________________________
[INFO] [Prompt Server] web root: <home>/ai/ComfyUI/venv/lib/python3.13/site-packages/comfyui_frontend_package/static
[INFO] Asset seeder disabled
[INFO] No OpenGL_accelerate module loaded: No module named 'OpenGL_accelerate'
[INFO] 
Import times for custom nodes:
[INFO]    0.0 seconds: <home>/bild-raster-2910/ComfyUI/custom_nodes/websocket_image_save.py
[INFO] 
[INFO] Using RAM pressure cache.
[INFO] ComfyUI is developed by Comfy Org. We also offer commercial products to deploy ComfyUI as scalable cloud endpoints. Visit platform.comfy.org/ascii for more information.
[WARNING] ________________________________________________________________________
WARNING WARNING WARNING WARNING WARNING

Installed comfyui-frontend-package version 1.53.6 is lower than the recommended version 1.57.4.
Installed comfyui-workflow-templates version 0.11.66 is lower than the recommended version 0.11.97.
Installed comfyui-embedded-docs version 0.5.12 is lower than the recommended version 0.5.15.

Please install the updated requirements.txt file by running:
<home>/bild-raster-2910/venv/bin/python -m pip install -r <home>/bild-raster-2910/ComfyUI/requirements.txt
If you are on the portable package you can run: update\update_comfyui.bat to solve this problem.
________________________________________________________________________
[INFO] Starting server

[INFO] To see the GUI go to: http://127.0.0.1:8201
[INFO] got prompt
[INFO] Model storage policy: fast_disk=True paths=['<home>/bild-raster-2910/models/vae/ae.safetensors']
[INFO] Using pytorch attention in VAE
[INFO] Using pytorch attention in VAE
[INFO] VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
[INFO] Found quantization metadata version 1
[INFO] Using MixedPrecisionOps for text encoder
[INFO] Model storage policy: fast_disk=True paths=['<home>/bild-raster-2910/models/text_encoders/qwen_3_4b_fp8_mixed.safetensors']
[INFO] CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
[INFO] Requested to load ZImageTEModel_
[INFO] Model ZImageTEModel_ prepared for dynamic VRAM loading. 5370MB Staged. 0 patches attached. Force pre-loaded 145 weights: 383 KB.
[INFO] Found quantization metadata version 1
[INFO] Detected mixed precision quantization
[INFO] Using mixed precision operations
[INFO] Native ops: mxfp8, float8_e4m3fn, int8_tensorwise, nvfp4, w6a8_int8, convrot_w4a4, asym_w4a8_int8, float8_e5m2 
[INFO] model weight dtype torch.bfloat16, manual cast: torch.bfloat16
[INFO] model_type FLOW
[INFO] Model storage policy: fast_disk=True paths=['<home>/bild-raster-2910/models/diffusion_models/z_image_turbo_int8_convrot.safetensors']
[INFO] Requested to load Lumina2
[INFO] Model Lumina2 prepared for dynamic VRAM loading. 5888MB Staged. 0 patches attached. Force pre-loaded 205 weights: 2087 KB.

  0%|          | 0/8 [00:00<?, ?it/s]
  0%|          | 0/8 [00:00<?, ?it/s,   Model Initializing ...  ]
  0%|          | 0/8 [00:00<?, ?it/s,  Model Initialization complete!  ]
 12%|█▎        | 1/8 [00:00<00:04,  1.60it/s,  Model Initialization complete!  ]
 12%|█▎        | 1/8 [00:00<00:04,  1.60it/s]                                   
 25%|██▌       | 2/8 [00:00<00:00,  6.99it/s]
 38%|███▊      | 3/8 [00:00<00:00,  6.94it/s]
 50%|█████     | 4/8 [00:00<00:00,  6.57it/s]
 62%|██████▎   | 5/8 [00:00<00:00,  6.54it/s]
 75%|███████▌  | 6/8 [00:00<00:00,  6.53it/s]
 88%|████████▊ | 7/8 [00:01<00:00,  6.52it/s]
100%|██████████| 8/8 [00:01<00:00,  6.53it/s]
100%|██████████| 8/8 [00:01<00:00,  6.69it/s]
[INFO] Requested to load AutoencodingEngine
[INFO] Model AutoencodingEngine prepared for dynamic VRAM loading. 159MB Staged. 0 patches attached. Force pre-loaded 108 weights: 182 KB.
[INFO] Prompt executed in 3.15 seconds
[INFO] got prompt
[INFO] Model ZImageTEModel_ prepared for dynamic VRAM loading. 5370MB Staged. 0 patches attached. Force pre-loaded 145 weights: 383 KB.
[INFO] Model Lumina2 prepared for dynamic VRAM loading. 5888MB Staged. 0 patches attached. Force pre-loaded 205 weights: 2087 KB.

  0%|          | 0/8 [00:00<?, ?it/s]
  0%|          | 0/8 [00:00<?, ?it/s,   Model Initializing ...  ]
  0%|          | 0/8 [00:00<?, ?it/s,  Model Initialization complete!  ]
 12%|█▎        | 1/8 [00:00<00:01,  6.75it/s,  Model Initialization complete!  ]
 12%|█▎        | 1/8 [00:00<00:01,  6.75it/s]                                   
 25%|██▌       | 2/8 [00:00<00:00,  6.64it/s]
 38%|███▊      | 3/8 [00:00<00:00,  6.43it/s]
 50%|█████     | 4/8 [00:00<00:00,  6.38it/s]
 62%|██████▎   | 5/8 [00:00<00:00,  6.34it/s]
 75%|███████▌  | 6/8 [00:00<00:00,  6.36it/s]
 88%|████████▊ | 7/8 [00:01<00:00,  6.36it/s]
100%|██████████| 8/8 [00:01<00:00,  6.37it/s]
100%|██████████| 8/8 [00:01<00:00,  6.44it/s]
[INFO] Model AutoencodingEngine prepared for dynamic VRAM loading. 159MB Staged. 0 patches attached. Force pre-loaded 108 weights: 182 KB.
[INFO] Prompt executed in 1.56 seconds
[INFO] got prompt
[INFO] Model ZImageTEModel_ prepared for dynamic VRAM loading. 5370MB Staged. 0 patches attached. Force pre-loaded 145 weights: 383 KB.
[INFO] Model Lumina2 prepared for dynamic VRAM loading. 5888MB Staged. 0 patches attached. Force pre-loaded 205 weights: 2087 KB.

  0%|          | 0/8 [00:00<?, ?it/s]
  0%|          | 0/8 [00:00<?, ?it/s,   Model Initializing ...  ]
  0%|          | 0/8 [00:00<?, ?it/s,  Model Initialization complete!  ]
 12%|█▎        | 1/8 [00:00<00:01,  6.99it/s,  Model Initialization complete!  ]
 12%|█▎        | 1/8 [00:00<00:01,  6.99it/s]                                   
 25%|██▌       | 2/8 [00:00<00:00,  6.63it/s]
 38%|███▊      | 3/8 [00:00<00:00,  6.40it/s]
 50%|█████     | 4/8 [00:00<00:00,  6.37it/s]
 62%|██████▎   | 5/8 [00:00<00:00,  6.36it/s]
 75%|███████▌  | 6/8 [00:00<00:00,  6.35it/s]
 88%|████████▊ | 7/8 [00:01<00:00,  6.36it/s]
100%|██████████| 8/8 [00:01<00:00,  6.36it/s]
100%|██████████| 8/8 [00:01<00:00,  6.43it/s]
[INFO] Model AutoencodingEngine prepared for dynamic VRAM loading. 159MB Staged. 0 patches attached. Force pre-loaded 108 weights: 182 KB.
[INFO] Prompt executed in 1.57 seconds
[INFO] got prompt
[INFO] Model ZImageTEModel_ prepared for dynamic VRAM loading. 5370MB Staged. 0 patches attached. Force pre-loaded 145 weights: 383 KB.
[INFO] Model Lumina2 prepared for dynamic VRAM loading. 5888MB Staged. 0 patches attached. Force pre-loaded 205 weights: 2087 KB.

  0%|          | 0/8 [00:00<?, ?it/s]
  0%|          | 0/8 [00:00<?, ?it/s,   Model Initializing ...  ]
  0%|          | 0/8 [00:00<?, ?it/s,  Model Initialization complete!  ]
 12%|█▎        | 1/8 [00:00<00:01,  6.97it/s,  Model Initialization complete!  ]
 12%|█▎        | 1/8 [00:00<00:01,  6.97it/s]                                   
 25%|██▌       | 2/8 [00:00<00:00,  6.61it/s]
 38%|███▊      | 3/8 [00:00<00:00,  6.36it/s]
 50%|█████     | 4/8 [00:00<00:00,  6.34it/s]
 62%|██████▎   | 5/8 [00:00<00:00,  6.33it/s]
 75%|███████▌  | 6/8 [00:00<00:00,  6.34it/s]
 88%|████████▊ | 7/8 [00:01<00:00,  6.33it/s]
100%|██████████| 8/8 [00:01<00:00,  6.33it/s]
100%|██████████| 8/8 [00:01<00:00,  6.40it/s]
[INFO] Model AutoencodingEngine prepared for dynamic VRAM loading. 159MB Staged. 0 patches attached. Force pre-loaded 108 weights: 182 KB.
[INFO] Prompt executed in 1.58 seconds
[INFO] got prompt
[INFO] Model ZImageTEModel_ prepared for dynamic VRAM loading. 5370MB Staged. 0 patches attached. Force pre-loaded 145 weights: 383 KB.
[INFO] Model Lumina2 prepared for dynamic VRAM loading. 5888MB Staged. 0 patches attached. Force pre-loaded 205 weights: 2087 KB.

  0%|          | 0/8 [00:00<?, ?it/s]
  0%|          | 0/8 [00:00<?, ?it/s,   Model Initializing ...  ]
  0%|          | 0/8 [00:00<?, ?it/s,  Model Initialization complete!  ]
 12%|█▎        | 1/8 [00:00<00:00,  7.04it/s,  Model Initialization complete!  ]
 12%|█▎        | 1/8 [00:00<00:00,  7.04it/s]                                   
 25%|██▌       | 2/8 [00:00<00:00,  6.71it/s]
 38%|███▊      | 3/8 [00:00<00:00,  6.45it/s]
 50%|█████     | 4/8 [00:00<00:00,  6.41it/s]
 62%|██████▎   | 5/8 [00:00<00:00,  6.40it/s]
 75%|███████▌  | 6/8 [00:00<00:00,  6.39it/s]
 88%|████████▊ | 7/8 [00:01<00:00,  6.39it/s]
100%|██████████| 8/8 [00:01<00:00,  6.39it/s]
100%|██████████| 8/8 [00:01<00:00,  6.48it/s]
[INFO] Model AutoencodingEngine prepared for dynamic VRAM loading. 159MB Staged. 0 patches attached. Force pre-loaded 108 weights: 182 KB.
[INFO] Prompt executed in 1.55 seconds