dfischer/tokmeshmetal-4-epoch 🔢📝❓✓🖼️ → 🖼️

Random seed set to: 3744984327
⚠️  Adjusted dimensions from 640x360 to 640x368 to satisfy model requirements
�� USING REPLICATE WEIGHTS (preferred method)
🎯 USING REPLICATE WEIGHTS TAR FILE 🎯
----------------------------------------
📦 Processing replicate weights tar file...
🔄 Will rename LoRA to: replicate_c1e3b4ab-b782-4c5c-b284-17e206bee09f.safetensors
📂 Extracting tar contents...
✅ Found lora_comfyui.safetensors in tar
✨ Successfully copied LoRA to: ComfyUI/models/loras/replicate_c1e3b4ab-b782-4c5c-b284-17e206bee09f.safetensors
----------------------------------------
Checking inputs
====================================
Checking weights
✅ hunyuan_video_720_fp8_e4m3fn.safetensors exists in ComfyUI/models/diffusion_models
✅ hunyuan_video_vae_bf16.safetensors exists in ComfyUI/models/vae
====================================
Running workflow
[ComfyUI] got prompt
Executing node 7, title: HunyuanVideo VAE Loader, class type: HyVideoVAELoader
[ComfyUI] Loading text encoder model (clipL) from: /src/ComfyUI/models/clip/clip-vit-large-patch14
Executing node 42, title: HunyuanVideo Enhance A Video, class type: HyVideoEnhanceAVideo
Executing node 16, title: (Down)Load HunyuanVideo TextEncoder, class type: DownloadAndLoadHyVideoTextEncoder
[ComfyUI] Text encoder to dtype: torch.float16
[ComfyUI] Loading tokenizer (clipL) from: /src/ComfyUI/models/clip/clip-vit-large-patch14
[ComfyUI] Loading text encoder model (llm) from: /src/ComfyUI/models/LLM/llava-llama-3-8b-text-encoder-tokenizer
[ComfyUI]
[ComfyUI] Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]
[ComfyUI] Loading checkpoint shards:  25%|██▌       | 1/4 [00:00<00:01,  1.55it/s]
[ComfyUI] Loading checkpoint shards:  50%|█████     | 2/4 [00:01<00:01,  1.60it/s]
[ComfyUI] Loading checkpoint shards:  75%|███████▌  | 3/4 [00:01<00:00,  1.63it/s]
[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00,  2.39it/s]
[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00,  2.03it/s]
[ComfyUI] Text encoder to dtype: torch.float16
[ComfyUI] Loading tokenizer (llm) from: /src/ComfyUI/models/LLM/llava-llama-3-8b-text-encoder-tokenizer
Executing node 30, title: HunyuanVideo TextEncode, class type: HyVideoTextEncode
[ComfyUI] llm prompt attention_mask shape: torch.Size([1, 161]), masked tokens: 47
[ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 48
Executing node 41, title: HunyuanVideo Lora Select, class type: HyVideoLoraSelect
Executing node 1, title: HunyuanVideo Model Loader, class type: HyVideoModelLoader
[ComfyUI] model_type FLOW
[ComfyUI] The config attributes {'use_flow_sigmas': True, 'prediction_type': 'flow_prediction'} were passed to FlowMatchDiscreteScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.
[ComfyUI] Using accelerate to load and assign model weights to device...
[ComfyUI] Loading LoRA: replicate_c1e3b4ab-b782-4c5c-b284-17e206bee09f with strength: 1.0
[ComfyUI] Requested to load HyVideoModel
[ComfyUI] loaded completely 9.5367431640625e+25 12555.953247070312 True
[ComfyUI] Input (height, width, video_length) = (368, 640, 33)
Executing node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler
[ComfyUI] The config attributes {'reverse': True, 'solver': 'euler'} were passed to DPMSolverMultistepScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.
[ComfyUI] Sampling 33 frames in 9 latents at 640x368 with 50 inference steps
[ComfyUI] Scheduler config: FrozenDict([('num_train_timesteps', 1000), ('flow_shift', 9.0), ('reverse', True), ('solver', 'euler'), ('n_tokens', None), ('_use_default_values', ['n_tokens', 'num_train_timesteps'])])[ComfyUI]
[ComfyUI] 0%|          | 0/50 [00:00<?, ?it/s]
[ComfyUI] 2%|▏         | 1/50 [00:01<00:49,  1.01s/it]
[ComfyUI] 4%|▍         | 2/50 [00:01<00:39,  1.21it/s]
[ComfyUI] 6%|▌         | 3/50 [00:02<00:40,  1.17it/s]
[ComfyUI] 8%|▊         | 4/50 [00:03<00:39,  1.16it/s]
[ComfyUI] 10%|█         | 5/50 [00:04<00:39,  1.15it/s]
[ComfyUI] 12%|█▏        | 6/50 [00:05<00:38,  1.14it/s]
[ComfyUI] 14%|█▍        | 7/50 [00:06<00:37,  1.14it/s]
[ComfyUI] 16%|█▌        | 8/50 [00:07<00:36,  1.14it/s]
[ComfyUI] 18%|█▊        | 9/50 [00:07<00:36,  1.14it/s]
[ComfyUI] 20%|██        | 10/50 [00:08<00:35,  1.14it/s]
[ComfyUI] 22%|██▏       | 11/50 [00:09<00:34,  1.13it/s]
[ComfyUI] 24%|██▍       | 12/50 [00:10<00:33,  1.13it/s]
[ComfyUI] 26%|██▌       | 13/50 [00:11<00:32,  1.13it/s]
[ComfyUI] 28%|██▊       | 14/50 [00:12<00:31,  1.13it/s]
[ComfyUI] 30%|███       | 15/50 [00:13<00:30,  1.13it/s]
[ComfyUI] 32%|███▏      | 16/50 [00:14<00:29,  1.13it/s]
[ComfyUI] 34%|███▍      | 17/50 [00:14<00:29,  1.13it/s]
[ComfyUI] 36%|███▌      | 18/50 [00:15<00:28,  1.13it/s]
[ComfyUI] 38%|███▊      | 19/50 [00:16<00:27,  1.13it/s]
[ComfyUI] 40%|████      | 20/50 [00:17<00:26,  1.13it/s]
[ComfyUI] 42%|████▏     | 21/50 [00:18<00:25,  1.13it/s]
[ComfyUI] 44%|████▍     | 22/50 [00:19<00:24,  1.13it/s]
[ComfyUI] 46%|████▌     | 23/50 [00:20<00:23,  1.13it/s]
[ComfyUI] 48%|████▊     | 24/50 [00:21<00:22,  1.13it/s]
[ComfyUI] 50%|█████     | 25/50 [00:22<00:22,  1.13it/s]
[ComfyUI] 52%|█████▏    | 26/50 [00:22<00:21,  1.13it/s]
[ComfyUI] 54%|█████▍    | 27/50 [00:23<00:20,  1.13it/s]
[ComfyUI] 56%|█████▌    | 28/50 [00:24<00:19,  1.13it/s]
[ComfyUI] 58%|█████▊    | 29/50 [00:25<00:18,  1.13it/s]
[ComfyUI] 60%|██████    | 30/50 [00:26<00:17,  1.13it/s]
[ComfyUI] 62%|██████▏   | 31/50 [00:27<00:16,  1.13it/s]
[ComfyUI] 64%|██████▍   | 32/50 [00:28<00:15,  1.13it/s]
[ComfyUI] 66%|██████▌   | 33/50 [00:29<00:15,  1.13it/s]
[ComfyUI] 68%|██████▊   | 34/50 [00:29<00:14,  1.13it/s]
[ComfyUI] 70%|███████   | 35/50 [00:30<00:13,  1.13it/s]
[ComfyUI] 72%|███████▏  | 36/50 [00:31<00:12,  1.13it/s]
[ComfyUI] 74%|███████▍  | 37/50 [00:32<00:11,  1.13it/s]
[ComfyUI] 76%|███████▌  | 38/50 [00:33<00:10,  1.13it/s]
[ComfyUI] 78%|███████▊  | 39/50 [00:34<00:09,  1.13it/s]
[ComfyUI] 80%|████████  | 40/50 [00:35<00:08,  1.13it/s]
[ComfyUI] 82%|████████▏ | 41/50 [00:36<00:07,  1.13it/s]
[ComfyUI] 84%|████████▍ | 42/50 [00:37<00:07,  1.13it/s]
[ComfyUI] 86%|████████▌ | 43/50 [00:37<00:06,  1.13it/s]
[ComfyUI] 88%|████████▊ | 44/50 [00:38<00:05,  1.13it/s]
[ComfyUI] 90%|█████████ | 45/50 [00:39<00:04,  1.13it/s]
[ComfyUI] 92%|█████████▏| 46/50 [00:40<00:03,  1.13it/s]
[ComfyUI] 94%|█████████▍| 47/50 [00:41<00:02,  1.13it/s]
[ComfyUI] 96%|█████████▌| 48/50 [00:42<00:01,  1.13it/s]
[ComfyUI] 98%|█████████▊| 49/50 [00:43<00:00,  1.13it/s]
[ComfyUI] 100%|██████████| 50/50 [00:44<00:00,  1.13it/s]
[ComfyUI] 100%|██████████| 50/50 [00:44<00:00,  1.13it/s]
[ComfyUI] Allocated memory: memory=12.757 GB
[ComfyUI] Max allocated memory: max_memory=14.180 GB
[ComfyUI] Max reserved memory: max_reserved=14.688 GB
Executing node 5, title: HunyuanVideo Decode, class type: HyVideoDecode
[ComfyUI]
[ComfyUI] Decoding rows:   0%|          | 0/2 [00:00<?, ?it/s]
[ComfyUI] Decoding rows:  50%|█████     | 1/2 [00:00<00:00,  1.24it/s]
[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:01<00:00,  1.52it/s]
[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:01<00:00,  1.47it/s]
[ComfyUI]
[ComfyUI] Blending tiles:   0%|          | 0/2 [00:00<?, ?it/s]
Executing node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine
[ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 51.90it/s]
[ComfyUI] Prompt executed in 77.52 seconds
outputs:  {'34': {'gifs': [{'filename': 'HunyuanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 16.0, 'workflow': 'HunyuanVideo_00001.png', 'fullpath': '/tmp/outputs/HunyuanVideo_00001.mp4'}]}}
====================================
HunyuanVideo_00001.png
HunyuanVideo_00001.mp4