If you drag and drop these three videos into the browser and run them, it takes 0 seconds. That means it's the exact same workflow. But do you see the different file sizes? Video 1 is a very smooth video, Video 2 has the same content but isn't smooth, and Video 3 has completely different content. How can something like this happen?
The workflow might look complicated, but since I turned off all the features, the video was just generated in 4 steps using Euler/simple.
This just happens when experimenting with workflow settings. Rebooting Windows won't help. Neither will ck or sage.
I simply alternated bypassing the ModelSamplingMiniMaxH3 node like this with the same seed. All four results are different. Is this normal?
D:\AI\ComfyUI_windows_portable>.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --disable-api-nodes --fast-disk --use-ck-attention --output-directory E:\output --temp-directory E:\output --disable-all-custom-nodes
[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
[INFO] setup plugin alembic.autogenerate.checkconstraint_byname
[INFO] Setting output directory to: E:\output
[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_', 'convrot_w4a4_linear', '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', 'gemv_awq_w4a16', 'int8_linear', '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', 'stochastic_rounding_fp8', 'w4a8_int8_linear']}
[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', 'gemv_awq_w4a16', 'int8_linear', '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_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8', 'w4a8_int8_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 12282 MB, total RAM 32085 MB
[INFO] pytorch version: 2.13.0+cu130
[INFO] Set vram state to: NORMAL_VRAM
[INFO] Device: cuda:0 NVIDIA GeForce RTX 4070 SUPER : cudaMallocAsync
[INFO] Using async weight offloading with 2 streams
[INFO] Enabled pinned memory 12834.0
[INFO] Using pytorch attention
[INFO] Using Comfy Kitchen attention
[INFO] aimdo: src-win/cuda-detour.c:38:INFO:aimdo_setup_hooks: installing 6 hooks
[INFO] aimdo: src/control.c:262:INFO:comfy-aimdo NVML pressure enabled
[INFO] aimdo: src-win/shmem-detect.c:80:INFO:comfy-aimdo WDDM adapter match: NVIDIA GeForce RTX 4070 SUPER runtime_luid=00000000:0000d8eb dxgi_luid=00000000:0000d8eb
[INFO] aimdo: src/control.c:277:INFO:comfy-aimdo inited for GPU: NVIDIA GeForce RTX 4070 SUPER (VRAM: 12281 MB)
[INFO] DynamicVRAM support detected and enabled
[INFO] Python version: 3.13.12 (tags/v3.13.12:1cbe481, Feb 3 2026, 18:22:25) [MSC v.1944 64 bit (AMD64)]
[INFO] ComfyUI version: 0.32.0
[INFO] comfy-aimdo version: 0.4.13
[INFO] comfy-kitchen version: 0.2.30
[INFO] Setting temp directory to: E:\output\temp
[INFO] comfyui-frontend-package version: 1.48.7
[INFO] comfyui-workflow-templates version: 0.11.40
[INFO] comfyui-embedded-docs version: 0.5.9
[INFO] comfy-kitchen version: 0.2.30
[INFO] comfy-aimdo version: 0.4.13
[INFO] [Prompt Server] web root: D:\AI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\comfyui_frontend_package\static
[INFO] Asset seeder disabled
[INFO] No OpenGL_accelerate module loaded: No module named 'OpenGL_accelerate'
[INFO] Skipping loading of custom nodes
[INFO] Context impl SQLiteImpl.
[INFO] Will assume non-transactional DDL.
[INFO] Using RAM pressure cache.
[INFO] Starting server
[INFO] To see the GUI go to: http://127.0.0.1:8188
[INFO] got prompt
[INFO] VAE load device: cuda:0, offload device: cpu, dtype: torch.float32
[INFO] Found quantization metadata version 1
[INFO] VAE load device: cuda:0, offload device: cpu, dtype: torch.float16
[INFO] Found quantization metadata version 1
[INFO] Using MixedPrecisionOps for text encoder
[INFO] CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
[INFO] Requested to load MiniMaxH3VideoVAE
[INFO] Model MiniMaxH3VideoVAE prepared for dynamic VRAM loading. 2677MB Staged. 0 patches attached. Force pre-loaded 128 weights: 692 KB.
[INFO] Requested to load MiniMaxH3TEModel_
[INFO] Model MiniMaxH3TEModel_ prepared for dynamic VRAM loading. 25882MB Staged. 0 patches attached. Force pre-loaded 310 weights: 1272 KB.
[INFO] Found quantization metadata version 1
[INFO] Detected mixed precision quantization
[INFO] Using mixed precision operations
[INFO] Native ops: convrot_w4a4, float8_e4m3fn, asym_w4a8_int8, float8_e5m2, int8_tensorwise , emulated ops: nvfp4, mxfp8
[INFO] model weight dtype torch.bfloat16, manual cast: torch.bfloat16
[INFO] model_type FLOW_AV
[INFO] Requested to load MiniMaxH3
[INFO] 0 models unloaded.
[INFO] Model MiniMaxH3 prepared for dynamic VRAM loading. 19995MB Staged. 208 patches attached. Force pre-loaded 210 weights: 1175 KB.
100%|████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:47<00:00, 11.98s/it]
[INFO] Requested to load MiniMaxH3AudioVAE
[INFO] Model MiniMaxH3AudioVAE prepared for dynamic VRAM loading. 576MB Staged. 0 patches attached. Force pre-loaded 401 weights: 539 KB.
[INFO] Model MiniMaxH3VideoVAE prepared for dynamic VRAM loading. 2677MB Staged. 0 patches attached. Force pre-loaded 128 weights: 692 KB.
[INFO] Prompt executed in 85.34 seconds
Custom Node Testing
Your question
https://github.com/user-attachments/assets/65b78165-c6c0-417e-8e46-0d8a6ad31c4d
https://github.com/user-attachments/assets/7b21f00e-608c-4a36-9b4d-a6b35bc0a844
https://github.com/user-attachments/assets/83de2468-0e28-4f91-8ef8-a091e6a9b6ac
If you drag and drop these three videos into the browser and run them, it takes 0 seconds. That means it's the exact same workflow. But do you see the different file sizes? Video 1 is a very smooth video, Video 2 has the same content but isn't smooth, and Video 3 has completely different content. How can something like this happen?
The workflow might look complicated, but since I turned off all the features, the video was just generated in 4 steps using Euler/simple.
This just happens when experimenting with workflow settings. Rebooting Windows won't help. Neither will ck or sage.
Logs
Other
No response