deepfates
/
hunyuan-once-upon-a-time-in-hollywood
Hunyuan-Video model finetuned on Once Upon a Time in Hollywood (2019). Trigger word is "NCPNT". Use "A video in the style of NCPNT, NCPNT" at the beginning of your prompt for best results.
- Public
- 72 runs
-
H100
- Fine-tune
Prediction
deepfates/hunyuan-once-upon-a-time-in-hollywood:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3IDt5m3ene361rme0cmjs38sschn4StatusSucceededSourceAPIHardwareH100Total durationCreatedInput
- seed
- 12345
- steps
- 50
- width
- 640
- height
- 360
- prompt
- A video in the style of NCPNT, NCPNT The video clip depicts a cozy and serene interior scene. The focal point of the room is a bed with white bedding, positioned against a wall with two open windows. Through the windows, a stunning view of a sunlit hillside covered in green grass can be seen. On the wall above the bed, there are two picturesque paintings: one showing a mountainous landscape and the other depicting an abstract blue pattern. A person, possibly a man or a woman, is lying on the bed, their face turned away from the camera. The individual is wearing a long-sleeved, striped shirt and has long, sandy-colored hair. The lighting in the room
- frame_rate
- 16
- num_frames
- 66
- lora_strength
- 1
- guidance_scale
- 6
{ "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts a cozy and serene interior scene. The focal point of the room is a bed with white bedding, positioned against a wall with two open windows. Through the windows, a stunning view of a sunlit hillside covered in green grass can be seen. On the wall above the bed, there are two picturesque paintings: one showing a mountainous landscape and the other depicting an abstract blue pattern.\nA person, possibly a man or a woman, is lying on the bed, their face turned away from the camera. The individual is wearing a long-sleeved, striped shirt and has long, sandy-colored hair. The lighting in the room", "frame_rate": 16, "num_frames": 66, "lora_strength": 1, "guidance_scale": 6 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run deepfates/hunyuan-once-upon-a-time-in-hollywood using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "deepfates/hunyuan-once-upon-a-time-in-hollywood:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3", { input: { seed: 12345, steps: 50, width: 640, height: 360, prompt: "A video in the style of NCPNT, NCPNT The video clip depicts a cozy and serene interior scene. The focal point of the room is a bed with white bedding, positioned against a wall with two open windows. Through the windows, a stunning view of a sunlit hillside covered in green grass can be seen. On the wall above the bed, there are two picturesque paintings: one showing a mountainous landscape and the other depicting an abstract blue pattern.\nA person, possibly a man or a woman, is lying on the bed, their face turned away from the camera. The individual is wearing a long-sleeved, striped shirt and has long, sandy-colored hair. The lighting in the room", frame_rate: 16, num_frames: 66, lora_strength: 1, guidance_scale: 6 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun deepfates/hunyuan-once-upon-a-time-in-hollywood using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "deepfates/hunyuan-once-upon-a-time-in-hollywood:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3", input={ "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts a cozy and serene interior scene. The focal point of the room is a bed with white bedding, positioned against a wall with two open windows. Through the windows, a stunning view of a sunlit hillside covered in green grass can be seen. On the wall above the bed, there are two picturesque paintings: one showing a mountainous landscape and the other depicting an abstract blue pattern.\nA person, possibly a man or a woman, is lying on the bed, their face turned away from the camera. The individual is wearing a long-sleeved, striped shirt and has long, sandy-colored hair. The lighting in the room", "frame_rate": 16, "num_frames": 66, "lora_strength": 1, "guidance_scale": 6 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run deepfates/hunyuan-once-upon-a-time-in-hollywood using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3", "input": { "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts a cozy and serene interior scene. The focal point of the room is a bed with white bedding, positioned against a wall with two open windows. Through the windows, a stunning view of a sunlit hillside covered in green grass can be seen. On the wall above the bed, there are two picturesque paintings: one showing a mountainous landscape and the other depicting an abstract blue pattern.\\nA person, possibly a man or a woman, is lying on the bed, their face turned away from the camera. The individual is wearing a long-sleeved, striped shirt and has long, sandy-colored hair. The lighting in the room", "frame_rate": 16, "num_frames": 66, "lora_strength": 1, "guidance_scale": 6 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/deepfates/hunyuan-once-upon-a-time-in-hollywood@sha256:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3 \ -i 'seed=12345' \ -i 'steps=50' \ -i 'width=640' \ -i 'height=360' \ -i $'prompt="A video in the style of NCPNT, NCPNT The video clip depicts a cozy and serene interior scene. The focal point of the room is a bed with white bedding, positioned against a wall with two open windows. Through the windows, a stunning view of a sunlit hillside covered in green grass can be seen. On the wall above the bed, there are two picturesque paintings: one showing a mountainous landscape and the other depicting an abstract blue pattern.\\nA person, possibly a man or a woman, is lying on the bed, their face turned away from the camera. The individual is wearing a long-sleeved, striped shirt and has long, sandy-colored hair. The lighting in the room"' \ -i 'frame_rate=16' \ -i 'num_frames=66' \ -i 'lora_strength=1' \ -i 'guidance_scale=6'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/deepfates/hunyuan-once-upon-a-time-in-hollywood@sha256:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts a cozy and serene interior scene. The focal point of the room is a bed with white bedding, positioned against a wall with two open windows. Through the windows, a stunning view of a sunlit hillside covered in green grass can be seen. On the wall above the bed, there are two picturesque paintings: one showing a mountainous landscape and the other depicting an abstract blue pattern.\\nA person, possibly a man or a woman, is lying on the bed, their face turned away from the camera. The individual is wearing a long-sleeved, striped shirt and has long, sandy-colored hair. The lighting in the room", "frame_rate": 16, "num_frames": 66, "lora_strength": 1, "guidance_scale": 6 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2025-01-24T03:43:22.676560Z", "created_at": "2025-01-24T03:06:47.472000Z", "data_removed": false, "error": null, "id": "t5m3ene361rme0cmjs38sschn4", "input": { "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts a cozy and serene interior scene. The focal point of the room is a bed with white bedding, positioned against a wall with two open windows. Through the windows, a stunning view of a sunlit hillside covered in green grass can be seen. On the wall above the bed, there are two picturesque paintings: one showing a mountainous landscape and the other depicting an abstract blue pattern.\nA person, possibly a man or a woman, is lying on the bed, their face turned away from the camera. The individual is wearing a long-sleeved, striped shirt and has long, sandy-colored hair. The lighting in the room", "frame_rate": 16, "num_frames": 66, "lora_strength": 1, "guidance_scale": 6 }, "logs": "Seed set to: 12345\n⚠️ Adjusted dimensions from 640x360 to 640x368 to satisfy model requirements\n⚠️ Adjusted frame count from 66 to 65 to satisfy model requirements\nChecking inputs\n====================================\nChecking weights\n✅ hunyuan_video_720_fp8_e4m3fn.safetensors exists in ComfyUI/models/diffusion_models\n✅ hunyuan_video_vae_bf16.safetensors exists in ComfyUI/models/vae\n====================================\nRunning workflow\n[ComfyUI] got prompt\nExecuting node 30, title: HunyuanVideo TextEncode, class type: HyVideoTextEncode\n[ComfyUI] llm prompt attention_mask shape: torch.Size([1, 161]), masked tokens: 145\n[ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 77\n[ComfyUI] Input (height, width, video_length) = (368, 640, 65)\nExecuting node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler\n[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.\n[ComfyUI] Sampling 65 frames in 17 latents at 640x368 with 50 inference steps\n[ComfyUI]\n[ComfyUI] 0%| | 0/50 [00:00<?, ?it/s]\n[ComfyUI] 2%|▏ | 1/50 [00:02<01:52, 2.29s/it]\n[ComfyUI] 4%|▍ | 2/50 [00:04<01:36, 2.02s/it]\n[ComfyUI] 6%|▌ | 3/50 [00:06<01:40, 2.15s/it]\n[ComfyUI] 8%|▊ | 4/50 [00:08<01:41, 2.21s/it]\n[ComfyUI] 10%|█ | 5/50 [00:11<01:40, 2.24s/it]\n[ComfyUI] 12%|█▏ | 6/50 [00:13<01:39, 2.26s/it]\n[ComfyUI] 14%|█▍ | 7/50 [00:15<01:37, 2.28s/it]\n[ComfyUI] 16%|█▌ | 8/50 [00:17<01:35, 2.28s/it]\n[ComfyUI] 18%|█▊ | 9/50 [00:20<01:33, 2.29s/it]\n[ComfyUI] 20%|██ | 10/50 [00:22<01:31, 2.29s/it]\n[ComfyUI] 22%|██▏ | 11/50 [00:24<01:29, 2.29s/it]\n[ComfyUI] 24%|██▍ | 12/50 [00:27<01:27, 2.29s/it]\n[ComfyUI] 26%|██▌ | 13/50 [00:29<01:24, 2.29s/it]\n[ComfyUI] 28%|██▊ | 14/50 [00:31<01:22, 2.29s/it]\n[ComfyUI] 30%|███ | 15/50 [00:34<01:20, 2.30s/it]\n[ComfyUI] 32%|███▏ | 16/50 [00:36<01:18, 2.29s/it]\n[ComfyUI] 34%|███▍ | 17/50 [00:38<01:15, 2.29s/it]\n[ComfyUI] 36%|███▌ | 18/50 [00:40<01:13, 2.30s/it]\n[ComfyUI] 38%|███▊ | 19/50 [00:43<01:11, 2.30s/it]\n[ComfyUI] 40%|████ | 20/50 [00:45<01:08, 2.29s/it]\n[ComfyUI] 42%|████▏ | 21/50 [00:47<01:06, 2.29s/it]\n[ComfyUI] 44%|████▍ | 22/50 [00:50<01:04, 2.30s/it]\n[ComfyUI] 46%|████▌ | 23/50 [00:52<01:01, 2.29s/it]\n[ComfyUI] 48%|████▊ | 24/50 [00:54<00:59, 2.29s/it]\n[ComfyUI] 50%|█████ | 25/50 [00:56<00:57, 2.30s/it]\n[ComfyUI] 52%|█████▏ | 26/50 [00:59<00:55, 2.30s/it]\n[ComfyUI] 54%|█████▍ | 27/50 [01:01<00:52, 2.30s/it]\n[ComfyUI] 56%|█████▌ | 28/50 [01:03<00:50, 2.29s/it]\n[ComfyUI] 58%|█████▊ | 29/50 [01:06<00:48, 2.29s/it]\n[ComfyUI] 60%|██████ | 30/50 [01:08<00:45, 2.29s/it]\n[ComfyUI] 62%|██████▏ | 31/50 [01:10<00:43, 2.29s/it]\n[ComfyUI] 64%|██████▍ | 32/50 [01:13<00:41, 2.29s/it]\n[ComfyUI] 66%|██████▌ | 33/50 [01:15<00:38, 2.29s/it]\n[ComfyUI] 68%|██████▊ | 34/50 [01:17<00:36, 2.29s/it]\n[ComfyUI] 70%|███████ | 35/50 [01:19<00:34, 2.29s/it]\n[ComfyUI] 72%|███████▏ | 36/50 [01:22<00:32, 2.29s/it]\n[ComfyUI] 74%|███████▍ | 37/50 [01:24<00:29, 2.29s/it]\n[ComfyUI] 76%|███████▌ | 38/50 [01:26<00:27, 2.29s/it]\n[ComfyUI] 78%|███████▊ | 39/50 [01:29<00:25, 2.29s/it]\n[ComfyUI] 80%|████████ | 40/50 [01:31<00:22, 2.29s/it]\n[ComfyUI] 82%|████████▏ | 41/50 [01:33<00:20, 2.29s/it]\n[ComfyUI] 84%|████████▍ | 42/50 [01:35<00:18, 2.29s/it]\n[ComfyUI] 86%|████████▌ | 43/50 [01:38<00:16, 2.29s/it]\n[ComfyUI] 88%|████████▊ | 44/50 [01:40<00:13, 2.29s/it]\n[ComfyUI] 90%|█████████ | 45/50 [01:42<00:11, 2.29s/it]\n[ComfyUI] 92%|█████████▏| 46/50 [01:45<00:09, 2.29s/it]\n[ComfyUI] 94%|█████████▍| 47/50 [01:47<00:06, 2.29s/it]\n[ComfyUI] 96%|█████████▌| 48/50 [01:49<00:04, 2.29s/it]\n[ComfyUI] 98%|█████████▊| 49/50 [01:51<00:02, 2.29s/it]\n[ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.29s/it]\n[ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.29s/it]\n[ComfyUI] Allocated memory: memory=12.300 GB\n[ComfyUI] Max allocated memory: max_memory=15.099 GB\n[ComfyUI] Max reserved memory: max_reserved=16.312 GB\nExecuting node 5, title: HunyuanVideo Decode, class type: HyVideoDecode\n[ComfyUI]\n[ComfyUI] Decoding rows: 0%| | 0/2 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows: 50%|█████ | 1/2 [00:01<00:01, 1.46s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.24s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.27s/it]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/2 [00:00<?, ?it/s]\n[ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 25.97it/s]\n[ComfyUI]\n[ComfyUI] Decoding rows: 0%| | 0/2 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows: 50%|█████ | 1/2 [00:00<00:00, 2.55it/s]\n[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 3.03it/s]\n[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 2.95it/s]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/2 [00:00<?, ?it/s]\nExecuting node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine\n[ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 64.25it/s]\n[ComfyUI] Prompt executed in 130.74 seconds\noutputs: {'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'}]}}\n====================================\nHunyuanVideo_00001.png\nHunyuanVideo_00001.mp4", "metrics": { "predict_time": 132.152345091, "total_time": 2195.20456 }, "output": "https://replicate.delivery/xezq/sWer5fWMwZuS0k9qmDdeHzBeqdYbfN1yyZFyjHxtbvZULfCCF/HunyuanVideo_00001.mp4", "started_at": "2025-01-24T03:41:10.524215Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bsvm-5o5ho3r3cyfs3k3dz34fpcbkfxnvabrneglhtvd5r7ducmay5a3q", "get": "https://api.replicate.com/v1/predictions/t5m3ene361rme0cmjs38sschn4", "cancel": "https://api.replicate.com/v1/predictions/t5m3ene361rme0cmjs38sschn4/cancel" }, "version": "47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3" }Generated inSeed set to: 12345 ⚠️ Adjusted dimensions from 640x360 to 640x368 to satisfy model requirements ⚠️ Adjusted frame count from 66 to 65 to satisfy model requirements 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 30, title: HunyuanVideo TextEncode, class type: HyVideoTextEncode [ComfyUI] llm prompt attention_mask shape: torch.Size([1, 161]), masked tokens: 145 [ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 77 [ComfyUI] Input (height, width, video_length) = (368, 640, 65) 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 65 frames in 17 latents at 640x368 with 50 inference steps [ComfyUI] [ComfyUI] 0%| | 0/50 [00:00<?, ?it/s] [ComfyUI] 2%|▏ | 1/50 [00:02<01:52, 2.29s/it] [ComfyUI] 4%|▍ | 2/50 [00:04<01:36, 2.02s/it] [ComfyUI] 6%|▌ | 3/50 [00:06<01:40, 2.15s/it] [ComfyUI] 8%|▊ | 4/50 [00:08<01:41, 2.21s/it] [ComfyUI] 10%|█ | 5/50 [00:11<01:40, 2.24s/it] [ComfyUI] 12%|█▏ | 6/50 [00:13<01:39, 2.26s/it] [ComfyUI] 14%|█▍ | 7/50 [00:15<01:37, 2.28s/it] [ComfyUI] 16%|█▌ | 8/50 [00:17<01:35, 2.28s/it] [ComfyUI] 18%|█▊ | 9/50 [00:20<01:33, 2.29s/it] [ComfyUI] 20%|██ | 10/50 [00:22<01:31, 2.29s/it] [ComfyUI] 22%|██▏ | 11/50 [00:24<01:29, 2.29s/it] [ComfyUI] 24%|██▍ | 12/50 [00:27<01:27, 2.29s/it] [ComfyUI] 26%|██▌ | 13/50 [00:29<01:24, 2.29s/it] [ComfyUI] 28%|██▊ | 14/50 [00:31<01:22, 2.29s/it] [ComfyUI] 30%|███ | 15/50 [00:34<01:20, 2.30s/it] [ComfyUI] 32%|███▏ | 16/50 [00:36<01:18, 2.29s/it] [ComfyUI] 34%|███▍ | 17/50 [00:38<01:15, 2.29s/it] [ComfyUI] 36%|███▌ | 18/50 [00:40<01:13, 2.30s/it] [ComfyUI] 38%|███▊ | 19/50 [00:43<01:11, 2.30s/it] [ComfyUI] 40%|████ | 20/50 [00:45<01:08, 2.29s/it] [ComfyUI] 42%|████▏ | 21/50 [00:47<01:06, 2.29s/it] [ComfyUI] 44%|████▍ | 22/50 [00:50<01:04, 2.30s/it] [ComfyUI] 46%|████▌ | 23/50 [00:52<01:01, 2.29s/it] [ComfyUI] 48%|████▊ | 24/50 [00:54<00:59, 2.29s/it] [ComfyUI] 50%|█████ | 25/50 [00:56<00:57, 2.30s/it] [ComfyUI] 52%|█████▏ | 26/50 [00:59<00:55, 2.30s/it] [ComfyUI] 54%|█████▍ | 27/50 [01:01<00:52, 2.30s/it] [ComfyUI] 56%|█████▌ | 28/50 [01:03<00:50, 2.29s/it] [ComfyUI] 58%|█████▊ | 29/50 [01:06<00:48, 2.29s/it] [ComfyUI] 60%|██████ | 30/50 [01:08<00:45, 2.29s/it] [ComfyUI] 62%|██████▏ | 31/50 [01:10<00:43, 2.29s/it] [ComfyUI] 64%|██████▍ | 32/50 [01:13<00:41, 2.29s/it] [ComfyUI] 66%|██████▌ | 33/50 [01:15<00:38, 2.29s/it] [ComfyUI] 68%|██████▊ | 34/50 [01:17<00:36, 2.29s/it] [ComfyUI] 70%|███████ | 35/50 [01:19<00:34, 2.29s/it] [ComfyUI] 72%|███████▏ | 36/50 [01:22<00:32, 2.29s/it] [ComfyUI] 74%|███████▍ | 37/50 [01:24<00:29, 2.29s/it] [ComfyUI] 76%|███████▌ | 38/50 [01:26<00:27, 2.29s/it] [ComfyUI] 78%|███████▊ | 39/50 [01:29<00:25, 2.29s/it] [ComfyUI] 80%|████████ | 40/50 [01:31<00:22, 2.29s/it] [ComfyUI] 82%|████████▏ | 41/50 [01:33<00:20, 2.29s/it] [ComfyUI] 84%|████████▍ | 42/50 [01:35<00:18, 2.29s/it] [ComfyUI] 86%|████████▌ | 43/50 [01:38<00:16, 2.29s/it] [ComfyUI] 88%|████████▊ | 44/50 [01:40<00:13, 2.29s/it] [ComfyUI] 90%|█████████ | 45/50 [01:42<00:11, 2.29s/it] [ComfyUI] 92%|█████████▏| 46/50 [01:45<00:09, 2.29s/it] [ComfyUI] 94%|█████████▍| 47/50 [01:47<00:06, 2.29s/it] [ComfyUI] 96%|█████████▌| 48/50 [01:49<00:04, 2.29s/it] [ComfyUI] 98%|█████████▊| 49/50 [01:51<00:02, 2.29s/it] [ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.29s/it] [ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.29s/it] [ComfyUI] Allocated memory: memory=12.300 GB [ComfyUI] Max allocated memory: max_memory=15.099 GB [ComfyUI] Max reserved memory: max_reserved=16.312 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 [00:01<00:01, 1.46s/it] [ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.24s/it] [ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.27s/it] [ComfyUI] [ComfyUI] Blending tiles: 0%| | 0/2 [00:00<?, ?it/s] [ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 25.97it/s] [ComfyUI] [ComfyUI] Decoding rows: 0%| | 0/2 [00:00<?, ?it/s] [ComfyUI] Decoding rows: 50%|█████ | 1/2 [00:00<00:00, 2.55it/s] [ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 3.03it/s] [ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 2.95it/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, 64.25it/s] [ComfyUI] Prompt executed in 130.74 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.mp4Prediction
deepfates/hunyuan-once-upon-a-time-in-hollywood:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3IDg9fg55g03srma0cmk5x8zdb8f8StatusSucceededSourceAPIHardwareH100Total durationCreatedInput
- seed
- 12345
- steps
- 50
- width
- 640
- height
- 360
- prompt
- A video in the style of NCPNT, NCPNT The video clip depicts a high-speed chase scene set in a desert environment. The primary focus is on a vehicle, which appears to be a modified off-road truck, speeding across the sandy terrain. The truck is kicking up a large cloud of sand and dust, indicating its high speed and the rough terrain it is traversing. The vehicle is equipped with a large, mounted weapon system on its back, suggesting it is part of a military or law enforcement operation. The background features a vast desert landscape with sand dunes stretching into the distance. The sky is clear with a few scattered clouds, and the overall lighting suggests it is daytime. The
- frame_rate
- 16
- num_frames
- 66
- lora_strength
- 1
- guidance_scale
- 6
{ "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts a high-speed chase scene set in a desert environment. The primary focus is on a vehicle, which appears to be a modified off-road truck, speeding across the sandy terrain. The truck is kicking up a large cloud of sand and dust, indicating its high speed and the rough terrain it is traversing. The vehicle is equipped with a large, mounted weapon system on its back, suggesting it is part of a military or law enforcement operation.\nThe background features a vast desert landscape with sand dunes stretching into the distance. The sky is clear with a few scattered clouds, and the overall lighting suggests it is daytime. The", "frame_rate": 16, "num_frames": 66, "lora_strength": 1, "guidance_scale": 6 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run deepfates/hunyuan-once-upon-a-time-in-hollywood using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "deepfates/hunyuan-once-upon-a-time-in-hollywood:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3", { input: { seed: 12345, steps: 50, width: 640, height: 360, prompt: "A video in the style of NCPNT, NCPNT The video clip depicts a high-speed chase scene set in a desert environment. The primary focus is on a vehicle, which appears to be a modified off-road truck, speeding across the sandy terrain. The truck is kicking up a large cloud of sand and dust, indicating its high speed and the rough terrain it is traversing. The vehicle is equipped with a large, mounted weapon system on its back, suggesting it is part of a military or law enforcement operation.\nThe background features a vast desert landscape with sand dunes stretching into the distance. The sky is clear with a few scattered clouds, and the overall lighting suggests it is daytime. The", frame_rate: 16, num_frames: 66, lora_strength: 1, guidance_scale: 6 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun deepfates/hunyuan-once-upon-a-time-in-hollywood using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "deepfates/hunyuan-once-upon-a-time-in-hollywood:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3", input={ "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts a high-speed chase scene set in a desert environment. The primary focus is on a vehicle, which appears to be a modified off-road truck, speeding across the sandy terrain. The truck is kicking up a large cloud of sand and dust, indicating its high speed and the rough terrain it is traversing. The vehicle is equipped with a large, mounted weapon system on its back, suggesting it is part of a military or law enforcement operation.\nThe background features a vast desert landscape with sand dunes stretching into the distance. The sky is clear with a few scattered clouds, and the overall lighting suggests it is daytime. The", "frame_rate": 16, "num_frames": 66, "lora_strength": 1, "guidance_scale": 6 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run deepfates/hunyuan-once-upon-a-time-in-hollywood using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3", "input": { "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts a high-speed chase scene set in a desert environment. The primary focus is on a vehicle, which appears to be a modified off-road truck, speeding across the sandy terrain. The truck is kicking up a large cloud of sand and dust, indicating its high speed and the rough terrain it is traversing. The vehicle is equipped with a large, mounted weapon system on its back, suggesting it is part of a military or law enforcement operation.\\nThe background features a vast desert landscape with sand dunes stretching into the distance. The sky is clear with a few scattered clouds, and the overall lighting suggests it is daytime. The", "frame_rate": 16, "num_frames": 66, "lora_strength": 1, "guidance_scale": 6 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/deepfates/hunyuan-once-upon-a-time-in-hollywood@sha256:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3 \ -i 'seed=12345' \ -i 'steps=50' \ -i 'width=640' \ -i 'height=360' \ -i $'prompt="A video in the style of NCPNT, NCPNT The video clip depicts a high-speed chase scene set in a desert environment. The primary focus is on a vehicle, which appears to be a modified off-road truck, speeding across the sandy terrain. The truck is kicking up a large cloud of sand and dust, indicating its high speed and the rough terrain it is traversing. The vehicle is equipped with a large, mounted weapon system on its back, suggesting it is part of a military or law enforcement operation.\\nThe background features a vast desert landscape with sand dunes stretching into the distance. The sky is clear with a few scattered clouds, and the overall lighting suggests it is daytime. The"' \ -i 'frame_rate=16' \ -i 'num_frames=66' \ -i 'lora_strength=1' \ -i 'guidance_scale=6'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/deepfates/hunyuan-once-upon-a-time-in-hollywood@sha256:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts a high-speed chase scene set in a desert environment. The primary focus is on a vehicle, which appears to be a modified off-road truck, speeding across the sandy terrain. The truck is kicking up a large cloud of sand and dust, indicating its high speed and the rough terrain it is traversing. The vehicle is equipped with a large, mounted weapon system on its back, suggesting it is part of a military or law enforcement operation.\\nThe background features a vast desert landscape with sand dunes stretching into the distance. The sky is clear with a few scattered clouds, and the overall lighting suggests it is daytime. The", "frame_rate": 16, "num_frames": 66, "lora_strength": 1, "guidance_scale": 6 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2025-01-24T18:08:40.106100Z", "created_at": "2025-01-24T18:01:37.054000Z", "data_removed": false, "error": null, "id": "g9fg55g03srma0cmk5x8zdb8f8", "input": { "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts a high-speed chase scene set in a desert environment. The primary focus is on a vehicle, which appears to be a modified off-road truck, speeding across the sandy terrain. The truck is kicking up a large cloud of sand and dust, indicating its high speed and the rough terrain it is traversing. The vehicle is equipped with a large, mounted weapon system on its back, suggesting it is part of a military or law enforcement operation.\nThe background features a vast desert landscape with sand dunes stretching into the distance. The sky is clear with a few scattered clouds, and the overall lighting suggests it is daytime. The", "frame_rate": 16, "num_frames": 66, "lora_strength": 1, "guidance_scale": 6 }, "logs": "Seed set to: 12345\n⚠️ Adjusted dimensions from 640x360 to 640x368 to satisfy model requirements\n⚠️ Adjusted frame count from 66 to 65 to satisfy model requirements\n�� USING REPLICATE WEIGHTS (preferred method)\n🎯 USING REPLICATE WEIGHTS TAR FILE 🎯\n----------------------------------------\n📦 Processing replicate weights tar file...\n🔄 Will rename LoRA to: replicate_5b5ba5a0-f36e-4e68-ad92-dcd936d11379.safetensors\n📂 Extracting tar contents...\n✅ Found lora_comfyui.safetensors in tar\n✨ Successfully copied LoRA to: ComfyUI/models/loras/replicate_5b5ba5a0-f36e-4e68-ad92-dcd936d11379.safetensors\n----------------------------------------\nChecking inputs\n====================================\nChecking weights\n✅ hunyuan_video_vae_bf16.safetensors exists in ComfyUI/models/vae\n✅ hunyuan_video_720_fp8_e4m3fn.safetensors exists in ComfyUI/models/diffusion_models\n====================================\nRunning workflow\n[ComfyUI] got prompt\nExecuting node 30, title: HunyuanVideo TextEncode, class type: HyVideoTextEncode\n[ComfyUI] llm prompt attention_mask shape: torch.Size([1, 161]), masked tokens: 142\n[ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 77\nExecuting node 41, title: HunyuanVideo Lora Select, class type: HyVideoLoraSelect\nExecuting node 1, title: HunyuanVideo Model Loader, class type: HyVideoModelLoader\n[ComfyUI] model_type FLOW\n[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.\n[ComfyUI] Using accelerate to load and assign model weights to device...\n[ComfyUI] Loading LoRA: replicate_5b5ba5a0-f36e-4e68-ad92-dcd936d11379 with strength: 1.0\n[ComfyUI] Requested to load HyVideoModel\n[ComfyUI] loaded completely 9.5367431640625e+25 12555.953247070312 True\n[ComfyUI] Input (height, width, video_length) = (368, 640, 65)\nExecuting node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler\n[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.\n[ComfyUI] Sampling 65 frames in 17 latents at 640x368 with 50 inference steps\n[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'])])\n[ComfyUI]\n[ComfyUI] 0%| | 0/50 [00:00<?, ?it/s]\n[ComfyUI] 2%|▏ | 1/50 [00:02<01:52, 2.30s/it]\n[ComfyUI] 4%|▍ | 2/50 [00:04<01:36, 2.02s/it]\n[ComfyUI] 6%|▌ | 3/50 [00:06<01:41, 2.15s/it]\n[ComfyUI] 8%|▊ | 4/50 [00:08<01:41, 2.21s/it]\n[ComfyUI] 10%|█ | 5/50 [00:11<01:40, 2.24s/it]\n[ComfyUI] 12%|█▏ | 6/50 [00:13<01:39, 2.26s/it]\n[ComfyUI] 14%|█▍ | 7/50 [00:15<01:37, 2.27s/it]\n[ComfyUI] 16%|█▌ | 8/50 [00:17<01:35, 2.28s/it]\n[ComfyUI] 18%|█▊ | 9/50 [00:20<01:33, 2.28s/it]\n[ComfyUI] 20%|██ | 10/50 [00:22<01:31, 2.29s/it]\n[ComfyUI] 22%|██▏ | 11/50 [00:24<01:29, 2.29s/it]\n[ComfyUI] 24%|██▍ | 12/50 [00:27<01:27, 2.29s/it]\n[ComfyUI] 26%|██▌ | 13/50 [00:29<01:24, 2.29s/it]\n[ComfyUI] 28%|██▊ | 14/50 [00:31<01:22, 2.29s/it]\n[ComfyUI] 30%|███ | 15/50 [00:33<01:20, 2.29s/it]\n[ComfyUI] 32%|███▏ | 16/50 [00:36<01:17, 2.29s/it]\n[ComfyUI] 34%|███▍ | 17/50 [00:38<01:15, 2.29s/it]\n[ComfyUI] 36%|███▌ | 18/50 [00:40<01:13, 2.29s/it]\n[ComfyUI] 38%|███▊ | 19/50 [00:43<01:11, 2.29s/it]\n[ComfyUI] 40%|████ | 20/50 [00:45<01:08, 2.29s/it]\n[ComfyUI] 42%|████▏ | 21/50 [00:47<01:06, 2.29s/it]\n[ComfyUI] 44%|████▍ | 22/50 [00:50<01:04, 2.29s/it]\n[ComfyUI] 46%|████▌ | 23/50 [00:52<01:01, 2.29s/it]\n[ComfyUI] 48%|████▊ | 24/50 [00:54<00:59, 2.29s/it]\n[ComfyUI] 50%|█████ | 25/50 [00:56<00:57, 2.29s/it]\n[ComfyUI] 52%|█████▏ | 26/50 [00:59<00:55, 2.29s/it]\n[ComfyUI] 54%|█████▍ | 27/50 [01:01<00:52, 2.29s/it]\n[ComfyUI] 56%|█████▌ | 28/50 [01:03<00:50, 2.29s/it]\n[ComfyUI] 58%|█████▊ | 29/50 [01:06<00:48, 2.29s/it]\n[ComfyUI] 60%|██████ | 30/50 [01:08<00:45, 2.29s/it]\n[ComfyUI] 62%|██████▏ | 31/50 [01:10<00:43, 2.29s/it]\n[ComfyUI] 64%|██████▍ | 32/50 [01:12<00:41, 2.29s/it]\n[ComfyUI] 66%|██████▌ | 33/50 [01:15<00:39, 2.29s/it]\n[ComfyUI] 68%|██████▊ | 34/50 [01:17<00:36, 2.29s/it]\n[ComfyUI] 70%|███████ | 35/50 [01:19<00:34, 2.29s/it]\n[ComfyUI] 72%|███████▏ | 36/50 [01:22<00:32, 2.29s/it]\n[ComfyUI] 74%|███████▍ | 37/50 [01:24<00:29, 2.29s/it]\n[ComfyUI] 76%|███████▌ | 38/50 [01:26<00:27, 2.29s/it]\n[ComfyUI] 78%|███████▊ | 39/50 [01:29<00:25, 2.29s/it]\n[ComfyUI] 80%|████████ | 40/50 [01:31<00:22, 2.29s/it]\n[ComfyUI] 82%|████████▏ | 41/50 [01:33<00:20, 2.29s/it]\n[ComfyUI] 84%|████████▍ | 42/50 [01:35<00:18, 2.29s/it]\n[ComfyUI] 86%|████████▌ | 43/50 [01:38<00:16, 2.29s/it]\n[ComfyUI] 88%|████████▊ | 44/50 [01:40<00:13, 2.29s/it]\n[ComfyUI] 90%|█████████ | 45/50 [01:42<00:11, 2.29s/it]\n[ComfyUI] 92%|█████████▏| 46/50 [01:45<00:09, 2.29s/it]\n[ComfyUI] 94%|█████████▍| 47/50 [01:47<00:06, 2.29s/it]\n[ComfyUI] 96%|█████████▌| 48/50 [01:49<00:04, 2.29s/it]\n[ComfyUI] 98%|█████████▊| 49/50 [01:51<00:02, 2.29s/it]\n[ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.29s/it]\n[ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.29s/it]\n[ComfyUI] Allocated memory: memory=12.300 GB\n[ComfyUI] Max allocated memory: max_memory=15.099 GB\n[ComfyUI] Max reserved memory: max_reserved=16.281 GB\nExecuting node 5, title: HunyuanVideo Decode, class type: HyVideoDecode\n[ComfyUI]\n[ComfyUI] Decoding rows: 0%| | 0/2 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows: 50%|█████ | 1/2 [00:01<00:01, 1.46s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.24s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.27s/it]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/2 [00:00<?, ?it/s]\n[ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 26.06it/s]\n[ComfyUI]\n[ComfyUI] Decoding rows: 0%| | 0/2 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows: 50%|█████ | 1/2 [00:00<00:00, 2.55it/s]\n[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 3.03it/s]\n[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 2.94it/s]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/2 [00:00<?, ?it/s]\nExecuting node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine\n[ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 64.37it/s]\n[ComfyUI] Prompt executed in 141.63 seconds\noutputs: {'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'}]}}\n====================================\nHunyuanVideo_00001.png\nHunyuanVideo_00001.mp4", "metrics": { "predict_time": 146.597234619, "total_time": 423.0521 }, "output": "https://replicate.delivery/xezq/fcJXXeh9JZsKCkGBqLXiBnlTvMbpfZPZSeQJSjQFy70iSihQB/HunyuanVideo_00001.mp4", "started_at": "2025-01-24T18:06:13.508865Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bsvm-2mlefijugph6dyqbsgozmsdn7uvx6helt66r5sxivgqlvor2yx4a", "get": "https://api.replicate.com/v1/predictions/g9fg55g03srma0cmk5x8zdb8f8", "cancel": "https://api.replicate.com/v1/predictions/g9fg55g03srma0cmk5x8zdb8f8/cancel" }, "version": "47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3" }Generated inSeed set to: 12345 ⚠️ Adjusted dimensions from 640x360 to 640x368 to satisfy model requirements ⚠️ Adjusted frame count from 66 to 65 to satisfy model requirements �� USING REPLICATE WEIGHTS (preferred method) 🎯 USING REPLICATE WEIGHTS TAR FILE 🎯 ---------------------------------------- 📦 Processing replicate weights tar file... 🔄 Will rename LoRA to: replicate_5b5ba5a0-f36e-4e68-ad92-dcd936d11379.safetensors 📂 Extracting tar contents... ✅ Found lora_comfyui.safetensors in tar ✨ Successfully copied LoRA to: ComfyUI/models/loras/replicate_5b5ba5a0-f36e-4e68-ad92-dcd936d11379.safetensors ---------------------------------------- Checking inputs ==================================== Checking weights ✅ hunyuan_video_vae_bf16.safetensors exists in ComfyUI/models/vae ✅ hunyuan_video_720_fp8_e4m3fn.safetensors exists in ComfyUI/models/diffusion_models ==================================== Running workflow [ComfyUI] got prompt Executing node 30, title: HunyuanVideo TextEncode, class type: HyVideoTextEncode [ComfyUI] llm prompt attention_mask shape: torch.Size([1, 161]), masked tokens: 142 [ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 77 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_5b5ba5a0-f36e-4e68-ad92-dcd936d11379 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, 65) 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 65 frames in 17 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 [00:02<01:52, 2.30s/it] [ComfyUI] 4%|▍ | 2/50 [00:04<01:36, 2.02s/it] [ComfyUI] 6%|▌ | 3/50 [00:06<01:41, 2.15s/it] [ComfyUI] 8%|▊ | 4/50 [00:08<01:41, 2.21s/it] [ComfyUI] 10%|█ | 5/50 [00:11<01:40, 2.24s/it] [ComfyUI] 12%|█▏ | 6/50 [00:13<01:39, 2.26s/it] [ComfyUI] 14%|█▍ | 7/50 [00:15<01:37, 2.27s/it] [ComfyUI] 16%|█▌ | 8/50 [00:17<01:35, 2.28s/it] [ComfyUI] 18%|█▊ | 9/50 [00:20<01:33, 2.28s/it] [ComfyUI] 20%|██ | 10/50 [00:22<01:31, 2.29s/it] [ComfyUI] 22%|██▏ | 11/50 [00:24<01:29, 2.29s/it] [ComfyUI] 24%|██▍ | 12/50 [00:27<01:27, 2.29s/it] [ComfyUI] 26%|██▌ | 13/50 [00:29<01:24, 2.29s/it] [ComfyUI] 28%|██▊ | 14/50 [00:31<01:22, 2.29s/it] [ComfyUI] 30%|███ | 15/50 [00:33<01:20, 2.29s/it] [ComfyUI] 32%|███▏ | 16/50 [00:36<01:17, 2.29s/it] [ComfyUI] 34%|███▍ | 17/50 [00:38<01:15, 2.29s/it] [ComfyUI] 36%|███▌ | 18/50 [00:40<01:13, 2.29s/it] [ComfyUI] 38%|███▊ | 19/50 [00:43<01:11, 2.29s/it] [ComfyUI] 40%|████ | 20/50 [00:45<01:08, 2.29s/it] [ComfyUI] 42%|████▏ | 21/50 [00:47<01:06, 2.29s/it] [ComfyUI] 44%|████▍ | 22/50 [00:50<01:04, 2.29s/it] [ComfyUI] 46%|████▌ | 23/50 [00:52<01:01, 2.29s/it] [ComfyUI] 48%|████▊ | 24/50 [00:54<00:59, 2.29s/it] [ComfyUI] 50%|█████ | 25/50 [00:56<00:57, 2.29s/it] [ComfyUI] 52%|█████▏ | 26/50 [00:59<00:55, 2.29s/it] [ComfyUI] 54%|█████▍ | 27/50 [01:01<00:52, 2.29s/it] [ComfyUI] 56%|█████▌ | 28/50 [01:03<00:50, 2.29s/it] [ComfyUI] 58%|█████▊ | 29/50 [01:06<00:48, 2.29s/it] [ComfyUI] 60%|██████ | 30/50 [01:08<00:45, 2.29s/it] [ComfyUI] 62%|██████▏ | 31/50 [01:10<00:43, 2.29s/it] [ComfyUI] 64%|██████▍ | 32/50 [01:12<00:41, 2.29s/it] [ComfyUI] 66%|██████▌ | 33/50 [01:15<00:39, 2.29s/it] [ComfyUI] 68%|██████▊ | 34/50 [01:17<00:36, 2.29s/it] [ComfyUI] 70%|███████ | 35/50 [01:19<00:34, 2.29s/it] [ComfyUI] 72%|███████▏ | 36/50 [01:22<00:32, 2.29s/it] [ComfyUI] 74%|███████▍ | 37/50 [01:24<00:29, 2.29s/it] [ComfyUI] 76%|███████▌ | 38/50 [01:26<00:27, 2.29s/it] [ComfyUI] 78%|███████▊ | 39/50 [01:29<00:25, 2.29s/it] [ComfyUI] 80%|████████ | 40/50 [01:31<00:22, 2.29s/it] [ComfyUI] 82%|████████▏ | 41/50 [01:33<00:20, 2.29s/it] [ComfyUI] 84%|████████▍ | 42/50 [01:35<00:18, 2.29s/it] [ComfyUI] 86%|████████▌ | 43/50 [01:38<00:16, 2.29s/it] [ComfyUI] 88%|████████▊ | 44/50 [01:40<00:13, 2.29s/it] [ComfyUI] 90%|█████████ | 45/50 [01:42<00:11, 2.29s/it] [ComfyUI] 92%|█████████▏| 46/50 [01:45<00:09, 2.29s/it] [ComfyUI] 94%|█████████▍| 47/50 [01:47<00:06, 2.29s/it] [ComfyUI] 96%|█████████▌| 48/50 [01:49<00:04, 2.29s/it] [ComfyUI] 98%|█████████▊| 49/50 [01:51<00:02, 2.29s/it] [ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.29s/it] [ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.29s/it] [ComfyUI] Allocated memory: memory=12.300 GB [ComfyUI] Max allocated memory: max_memory=15.099 GB [ComfyUI] Max reserved memory: max_reserved=16.281 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 [00:01<00:01, 1.46s/it] [ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.24s/it] [ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.27s/it] [ComfyUI] [ComfyUI] Blending tiles: 0%| | 0/2 [00:00<?, ?it/s] [ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 26.06it/s] [ComfyUI] [ComfyUI] Decoding rows: 0%| | 0/2 [00:00<?, ?it/s] [ComfyUI] Decoding rows: 50%|█████ | 1/2 [00:00<00:00, 2.55it/s] [ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 3.03it/s] [ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 2.94it/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, 64.37it/s] [ComfyUI] Prompt executed in 141.63 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.mp4Prediction
deepfates/hunyuan-once-upon-a-time-in-hollywood:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3IDnrwdpg6fvnrme0cmk6hrkgddm4StatusSucceededSourceAPIHardwareH100Total durationCreatedInput
- seed
- 12345
- steps
- 50
- width
- 640
- height
- 360
- prompt
- A video in the style of NCPNT, NCPNT The video clip depicts a dimly lit jazz club with a cozy, intimate atmosphere. The stage is set with a piano and a saxophone player, both engrossed in their performance. The saxophonist is positioned in the center, playing with a focused expression, while the pianist sits at the back, immersed in his music. The club is filled with patrons seated at tables, engaged in conversation and enjoying the live music. The audience appears to be a mix of men and women, dressed in casual to semi-formal attire. The lighting is warm and subdued, with a neon sign on the right side of the stage reading
- frame_rate
- 16
- num_frames
- 66
- lora_strength
- 1
- guidance_scale
- 6
{ "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts a dimly lit jazz club with a cozy, intimate atmosphere. The stage is set with a piano and a saxophone player, both engrossed in their performance. The saxophonist is positioned in the center, playing with a focused expression, while the pianist sits at the back, immersed in his music. The club is filled with patrons seated at tables, engaged in conversation and enjoying the live music. The audience appears to be a mix of men and women, dressed in casual to semi-formal attire. The lighting is warm and subdued, with a neon sign on the right side of the stage reading ", "frame_rate": 16, "num_frames": 66, "lora_strength": 1, "guidance_scale": 6 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run deepfates/hunyuan-once-upon-a-time-in-hollywood using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "deepfates/hunyuan-once-upon-a-time-in-hollywood:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3", { input: { seed: 12345, steps: 50, width: 640, height: 360, prompt: "A video in the style of NCPNT, NCPNT The video clip depicts a dimly lit jazz club with a cozy, intimate atmosphere. The stage is set with a piano and a saxophone player, both engrossed in their performance. The saxophonist is positioned in the center, playing with a focused expression, while the pianist sits at the back, immersed in his music. The club is filled with patrons seated at tables, engaged in conversation and enjoying the live music. The audience appears to be a mix of men and women, dressed in casual to semi-formal attire. The lighting is warm and subdued, with a neon sign on the right side of the stage reading ", frame_rate: 16, num_frames: 66, lora_strength: 1, guidance_scale: 6 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun deepfates/hunyuan-once-upon-a-time-in-hollywood using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "deepfates/hunyuan-once-upon-a-time-in-hollywood:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3", input={ "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts a dimly lit jazz club with a cozy, intimate atmosphere. The stage is set with a piano and a saxophone player, both engrossed in their performance. The saxophonist is positioned in the center, playing with a focused expression, while the pianist sits at the back, immersed in his music. The club is filled with patrons seated at tables, engaged in conversation and enjoying the live music. The audience appears to be a mix of men and women, dressed in casual to semi-formal attire. The lighting is warm and subdued, with a neon sign on the right side of the stage reading ", "frame_rate": 16, "num_frames": 66, "lora_strength": 1, "guidance_scale": 6 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run deepfates/hunyuan-once-upon-a-time-in-hollywood using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3", "input": { "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts a dimly lit jazz club with a cozy, intimate atmosphere. The stage is set with a piano and a saxophone player, both engrossed in their performance. The saxophonist is positioned in the center, playing with a focused expression, while the pianist sits at the back, immersed in his music. The club is filled with patrons seated at tables, engaged in conversation and enjoying the live music. The audience appears to be a mix of men and women, dressed in casual to semi-formal attire. The lighting is warm and subdued, with a neon sign on the right side of the stage reading ", "frame_rate": 16, "num_frames": 66, "lora_strength": 1, "guidance_scale": 6 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/deepfates/hunyuan-once-upon-a-time-in-hollywood@sha256:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3 \ -i 'seed=12345' \ -i 'steps=50' \ -i 'width=640' \ -i 'height=360' \ -i 'prompt="A video in the style of NCPNT, NCPNT The video clip depicts a dimly lit jazz club with a cozy, intimate atmosphere. The stage is set with a piano and a saxophone player, both engrossed in their performance. The saxophonist is positioned in the center, playing with a focused expression, while the pianist sits at the back, immersed in his music. The club is filled with patrons seated at tables, engaged in conversation and enjoying the live music. The audience appears to be a mix of men and women, dressed in casual to semi-formal attire. The lighting is warm and subdued, with a neon sign on the right side of the stage reading "' \ -i 'frame_rate=16' \ -i 'num_frames=66' \ -i 'lora_strength=1' \ -i 'guidance_scale=6'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/deepfates/hunyuan-once-upon-a-time-in-hollywood@sha256:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts a dimly lit jazz club with a cozy, intimate atmosphere. The stage is set with a piano and a saxophone player, both engrossed in their performance. The saxophonist is positioned in the center, playing with a focused expression, while the pianist sits at the back, immersed in his music. The club is filled with patrons seated at tables, engaged in conversation and enjoying the live music. The audience appears to be a mix of men and women, dressed in casual to semi-formal attire. The lighting is warm and subdued, with a neon sign on the right side of the stage reading ", "frame_rate": 16, "num_frames": 66, "lora_strength": 1, "guidance_scale": 6 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2025-01-24T18:52:27.357534Z", "created_at": "2025-01-24T18:47:17.213000Z", "data_removed": false, "error": null, "id": "nrwdpg6fvnrme0cmk6hrkgddm4", "input": { "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts a dimly lit jazz club with a cozy, intimate atmosphere. The stage is set with a piano and a saxophone player, both engrossed in their performance. The saxophonist is positioned in the center, playing with a focused expression, while the pianist sits at the back, immersed in his music. The club is filled with patrons seated at tables, engaged in conversation and enjoying the live music. The audience appears to be a mix of men and women, dressed in casual to semi-formal attire. The lighting is warm and subdued, with a neon sign on the right side of the stage reading ", "frame_rate": 16, "num_frames": 66, "lora_strength": 1, "guidance_scale": 6 }, "logs": "Seed set to: 12345\n⚠️ Adjusted dimensions from 640x360 to 640x368 to satisfy model requirements\n⚠️ Adjusted frame count from 66 to 65 to satisfy model requirements\n�� USING REPLICATE WEIGHTS (preferred method)\n🎯 USING REPLICATE WEIGHTS TAR FILE 🎯\n----------------------------------------\n📦 Processing replicate weights tar file...\n🔄 Will rename LoRA to: replicate_9fda3c62-41dc-43bf-adeb-1d83016c8c1d.safetensors\n📂 Extracting tar contents...\n✅ Found lora_comfyui.safetensors in tar\n✨ Successfully copied LoRA to: ComfyUI/models/loras/replicate_9fda3c62-41dc-43bf-adeb-1d83016c8c1d.safetensors\n----------------------------------------\nChecking inputs\n====================================\nChecking weights\n✅ hunyuan_video_720_fp8_e4m3fn.safetensors exists in ComfyUI/models/diffusion_models\n✅ hunyuan_video_vae_bf16.safetensors exists in ComfyUI/models/vae\n====================================\nRunning workflow\n[ComfyUI] got prompt\nExecuting node 7, title: HunyuanVideo VAE Loader, class type: HyVideoVAELoader\nExecuting node 42, title: HunyuanVideo Enhance A Video, class type: HyVideoEnhanceAVideo\nExecuting node 16, title: (Down)Load HunyuanVideo TextEncoder, class type: DownloadAndLoadHyVideoTextEncoder\n[ComfyUI] Loading text encoder model (clipL) from: /src/ComfyUI/models/clip/clip-vit-large-patch14\n[ComfyUI] Text encoder to dtype: torch.float16\n[ComfyUI] Loading tokenizer (clipL) from: /src/ComfyUI/models/clip/clip-vit-large-patch14\n[ComfyUI] Loading text encoder model (llm) from: /src/ComfyUI/models/LLM/llava-llama-3-8b-text-encoder-tokenizer\n[ComfyUI]\n[ComfyUI] Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s]\n[ComfyUI] Loading checkpoint shards: 25%|██▌ | 1/4 [00:00<00:02, 1.15it/s]\n[ComfyUI] Loading checkpoint shards: 50%|█████ | 2/4 [00:01<00:01, 1.20it/s]\n[ComfyUI] Loading checkpoint shards: 75%|███████▌ | 3/4 [00:02<00:00, 1.33it/s]\n[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 1.99it/s]\n[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 1.63it/s]\n[ComfyUI] Text encoder to dtype: torch.float16\n[ComfyUI] Loading tokenizer (llm) from: /src/ComfyUI/models/LLM/llava-llama-3-8b-text-encoder-tokenizer\nExecuting node 30, title: HunyuanVideo TextEncode, class type: HyVideoTextEncode\n[ComfyUI] llm prompt attention_mask shape: torch.Size([1, 161]), masked tokens: 142\n[ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 77\nExecuting node 41, title: HunyuanVideo Lora Select, class type: HyVideoLoraSelect\nExecuting node 1, title: HunyuanVideo Model Loader, class type: HyVideoModelLoader\n[ComfyUI] model_type FLOW\n[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.\n[ComfyUI] Using accelerate to load and assign model weights to device...\n[ComfyUI] Loading LoRA: replicate_9fda3c62-41dc-43bf-adeb-1d83016c8c1d with strength: 1.0\n[ComfyUI] Requested to load HyVideoModel\n[ComfyUI] loaded completely 9.5367431640625e+25 12555.953247070312 True\n[ComfyUI] Input (height, width, video_length) = (368, 640, 65)\nExecuting node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler\n[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.\n[ComfyUI] Sampling 65 frames in 17 latents at 640x368 with 50 inference steps\n[ComfyUI] Scheduler config: FrozenDict([('num_train_timesteps', 1000), ('flow_shift', 9.0), ('reverse', True), ('solver', 'euler'), ('n_tokens', None), ('_use_default_values', ['num_train_timesteps', 'n_tokens'])])\n[ComfyUI]\n[ComfyUI] 0%| | 0/50 [00:00<?, ?it/s]\n[ComfyUI] 2%|▏ | 1/50 [00:02<01:58, 2.43s/it]\n[ComfyUI] 4%|▍ | 2/50 [00:04<01:39, 2.07s/it]\n[ComfyUI] 6%|▌ | 3/50 [00:06<01:42, 2.18s/it]\n[ComfyUI] 8%|▊ | 4/50 [00:08<01:42, 2.22s/it]\n[ComfyUI] 10%|█ | 5/50 [00:11<01:41, 2.25s/it]\n[ComfyUI] 12%|█▏ | 6/50 [00:13<01:39, 2.27s/it]\n[ComfyUI] 14%|█▍ | 7/50 [00:15<01:37, 2.28s/it]\n[ComfyUI] 16%|█▌ | 8/50 [00:18<01:35, 2.28s/it]\n[ComfyUI] 18%|█▊ | 9/50 [00:20<01:33, 2.29s/it]\n[ComfyUI] 20%|██ | 10/50 [00:22<01:31, 2.29s/it]\n[ComfyUI] 22%|██▏ | 11/50 [00:24<01:29, 2.29s/it]\n[ComfyUI] 24%|██▍ | 12/50 [00:27<01:27, 2.29s/it]\n[ComfyUI] 26%|██▌ | 13/50 [00:29<01:24, 2.29s/it]\n[ComfyUI] 28%|██▊ | 14/50 [00:31<01:22, 2.29s/it]\n[ComfyUI] 30%|███ | 15/50 [00:34<01:20, 2.30s/it]\n[ComfyUI] 32%|███▏ | 16/50 [00:36<01:18, 2.30s/it]\n[ComfyUI] 34%|███▍ | 17/50 [00:38<01:15, 2.30s/it]\n[ComfyUI] 36%|███▌ | 18/50 [00:40<01:13, 2.30s/it]\n[ComfyUI] 38%|███▊ | 19/50 [00:43<01:11, 2.30s/it]\n[ComfyUI] 40%|████ | 20/50 [00:45<01:08, 2.30s/it]\n[ComfyUI] 42%|████▏ | 21/50 [00:47<01:06, 2.30s/it]\n[ComfyUI] 44%|████▍ | 22/50 [00:50<01:04, 2.30s/it]\n[ComfyUI] 46%|████▌ | 23/50 [00:52<01:02, 2.30s/it]\n[ComfyUI] 48%|████▊ | 24/50 [00:54<00:59, 2.30s/it]\n[ComfyUI] 50%|█████ | 25/50 [00:57<00:57, 2.30s/it]\n[ComfyUI] 52%|█████▏ | 26/50 [00:59<00:55, 2.30s/it]\n[ComfyUI] 54%|█████▍ | 27/50 [01:01<00:52, 2.30s/it]\n[ComfyUI] 56%|█████▌ | 28/50 [01:03<00:50, 2.30s/it]\n[ComfyUI] 58%|█████▊ | 29/50 [01:06<00:48, 2.30s/it]\n[ComfyUI] 60%|██████ | 30/50 [01:08<00:45, 2.30s/it]\n[ComfyUI] 62%|██████▏ | 31/50 [01:10<00:43, 2.30s/it]\n[ComfyUI] 64%|██████▍ | 32/50 [01:13<00:41, 2.30s/it]\n[ComfyUI] 66%|██████▌ | 33/50 [01:15<00:39, 2.30s/it]\n[ComfyUI] 68%|██████▊ | 34/50 [01:17<00:36, 2.30s/it]\n[ComfyUI] 70%|███████ | 35/50 [01:20<00:34, 2.30s/it]\n[ComfyUI] 72%|███████▏ | 36/50 [01:22<00:32, 2.30s/it]\n[ComfyUI] 74%|███████▍ | 37/50 [01:24<00:29, 2.30s/it]\n[ComfyUI] 76%|███████▌ | 38/50 [01:26<00:27, 2.30s/it]\n[ComfyUI] 78%|███████▊ | 39/50 [01:29<00:25, 2.30s/it]\n[ComfyUI] 80%|████████ | 40/50 [01:31<00:22, 2.30s/it]\n[ComfyUI] 82%|████████▏ | 41/50 [01:33<00:20, 2.30s/it]\n[ComfyUI] 84%|████████▍ | 42/50 [01:36<00:18, 2.30s/it]\n[ComfyUI] 86%|████████▌ | 43/50 [01:38<00:16, 2.30s/it]\n[ComfyUI] 88%|████████▊ | 44/50 [01:40<00:13, 2.30s/it]\n[ComfyUI] 90%|█████████ | 45/50 [01:43<00:11, 2.30s/it]\n[ComfyUI] 92%|█████████▏| 46/50 [01:45<00:09, 2.30s/it]\n[ComfyUI] 94%|█████████▍| 47/50 [01:47<00:06, 2.30s/it]\n[ComfyUI] 96%|█████████▌| 48/50 [01:49<00:04, 2.30s/it]\n[ComfyUI] 98%|█████████▊| 49/50 [01:52<00:02, 2.30s/it]\n[ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.30s/it]\n[ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.29s/it]\n[ComfyUI] Allocated memory: memory=12.760 GB\n[ComfyUI] Max allocated memory: max_memory=15.559 GB\n[ComfyUI] Max reserved memory: max_reserved=16.875 GB\n[ComfyUI]\nExecuting node 5, title: HunyuanVideo Decode, class type: HyVideoDecode\n[ComfyUI] Decoding rows: 0%| | 0/2 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows: 50%|█████ | 1/2 [00:01<00:01, 1.50s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.26s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.29s/it]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/2 [00:00<?, ?it/s]\n[ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 28.50it/s]\n[ComfyUI]\n[ComfyUI] Decoding rows: 0%| | 0/2 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows: 50%|█████ | 1/2 [00:00<00:00, 2.48it/s]\n[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 2.94it/s]\n[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 2.85it/s]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/2 [00:00<?, ?it/s]\nExecuting node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine\n[ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 39.06it/s]\n[ComfyUI] Prompt executed in 152.18 seconds\noutputs: {'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'}]}}\n====================================\nHunyuanVideo_00001.png\nHunyuanVideo_00001.mp4", "metrics": { "predict_time": 157.124447691, "total_time": 310.144534 }, "output": "https://replicate.delivery/xezq/eVeK5uDOzlvKwU0kfISce9CAfX9R3pfp62bhL7SjVUi0aTGCF/HunyuanVideo_00001.mp4", "started_at": "2025-01-24T18:49:50.233087Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bsvm-og7cajjyof5q22n2iiukghsuz4moebhxaydb3rxhn5gjatusfspq", "get": "https://api.replicate.com/v1/predictions/nrwdpg6fvnrme0cmk6hrkgddm4", "cancel": "https://api.replicate.com/v1/predictions/nrwdpg6fvnrme0cmk6hrkgddm4/cancel" }, "version": "47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3" }Generated inSeed set to: 12345 ⚠️ Adjusted dimensions from 640x360 to 640x368 to satisfy model requirements ⚠️ Adjusted frame count from 66 to 65 to satisfy model requirements �� USING REPLICATE WEIGHTS (preferred method) 🎯 USING REPLICATE WEIGHTS TAR FILE 🎯 ---------------------------------------- 📦 Processing replicate weights tar file... 🔄 Will rename LoRA to: replicate_9fda3c62-41dc-43bf-adeb-1d83016c8c1d.safetensors 📂 Extracting tar contents... ✅ Found lora_comfyui.safetensors in tar ✨ Successfully copied LoRA to: ComfyUI/models/loras/replicate_9fda3c62-41dc-43bf-adeb-1d83016c8c1d.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 Executing node 42, title: HunyuanVideo Enhance A Video, class type: HyVideoEnhanceAVideo Executing node 16, title: (Down)Load HunyuanVideo TextEncoder, class type: DownloadAndLoadHyVideoTextEncoder [ComfyUI] Loading text encoder model (clipL) from: /src/ComfyUI/models/clip/clip-vit-large-patch14 [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<00:02, 1.15it/s] [ComfyUI] Loading checkpoint shards: 50%|█████ | 2/4 [00:01<00:01, 1.20it/s] [ComfyUI] Loading checkpoint shards: 75%|███████▌ | 3/4 [00:02<00:00, 1.33it/s] [ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 1.99it/s] [ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 1.63it/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: 142 [ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 77 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_9fda3c62-41dc-43bf-adeb-1d83016c8c1d 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, 65) 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 65 frames in 17 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', ['num_train_timesteps', 'n_tokens'])]) [ComfyUI] [ComfyUI] 0%| | 0/50 [00:00<?, ?it/s] [ComfyUI] 2%|▏ | 1/50 [00:02<01:58, 2.43s/it] [ComfyUI] 4%|▍ | 2/50 [00:04<01:39, 2.07s/it] [ComfyUI] 6%|▌ | 3/50 [00:06<01:42, 2.18s/it] [ComfyUI] 8%|▊ | 4/50 [00:08<01:42, 2.22s/it] [ComfyUI] 10%|█ | 5/50 [00:11<01:41, 2.25s/it] [ComfyUI] 12%|█▏ | 6/50 [00:13<01:39, 2.27s/it] [ComfyUI] 14%|█▍ | 7/50 [00:15<01:37, 2.28s/it] [ComfyUI] 16%|█▌ | 8/50 [00:18<01:35, 2.28s/it] [ComfyUI] 18%|█▊ | 9/50 [00:20<01:33, 2.29s/it] [ComfyUI] 20%|██ | 10/50 [00:22<01:31, 2.29s/it] [ComfyUI] 22%|██▏ | 11/50 [00:24<01:29, 2.29s/it] [ComfyUI] 24%|██▍ | 12/50 [00:27<01:27, 2.29s/it] [ComfyUI] 26%|██▌ | 13/50 [00:29<01:24, 2.29s/it] [ComfyUI] 28%|██▊ | 14/50 [00:31<01:22, 2.29s/it] [ComfyUI] 30%|███ | 15/50 [00:34<01:20, 2.30s/it] [ComfyUI] 32%|███▏ | 16/50 [00:36<01:18, 2.30s/it] [ComfyUI] 34%|███▍ | 17/50 [00:38<01:15, 2.30s/it] [ComfyUI] 36%|███▌ | 18/50 [00:40<01:13, 2.30s/it] [ComfyUI] 38%|███▊ | 19/50 [00:43<01:11, 2.30s/it] [ComfyUI] 40%|████ | 20/50 [00:45<01:08, 2.30s/it] [ComfyUI] 42%|████▏ | 21/50 [00:47<01:06, 2.30s/it] [ComfyUI] 44%|████▍ | 22/50 [00:50<01:04, 2.30s/it] [ComfyUI] 46%|████▌ | 23/50 [00:52<01:02, 2.30s/it] [ComfyUI] 48%|████▊ | 24/50 [00:54<00:59, 2.30s/it] [ComfyUI] 50%|█████ | 25/50 [00:57<00:57, 2.30s/it] [ComfyUI] 52%|█████▏ | 26/50 [00:59<00:55, 2.30s/it] [ComfyUI] 54%|█████▍ | 27/50 [01:01<00:52, 2.30s/it] [ComfyUI] 56%|█████▌ | 28/50 [01:03<00:50, 2.30s/it] [ComfyUI] 58%|█████▊ | 29/50 [01:06<00:48, 2.30s/it] [ComfyUI] 60%|██████ | 30/50 [01:08<00:45, 2.30s/it] [ComfyUI] 62%|██████▏ | 31/50 [01:10<00:43, 2.30s/it] [ComfyUI] 64%|██████▍ | 32/50 [01:13<00:41, 2.30s/it] [ComfyUI] 66%|██████▌ | 33/50 [01:15<00:39, 2.30s/it] [ComfyUI] 68%|██████▊ | 34/50 [01:17<00:36, 2.30s/it] [ComfyUI] 70%|███████ | 35/50 [01:20<00:34, 2.30s/it] [ComfyUI] 72%|███████▏ | 36/50 [01:22<00:32, 2.30s/it] [ComfyUI] 74%|███████▍ | 37/50 [01:24<00:29, 2.30s/it] [ComfyUI] 76%|███████▌ | 38/50 [01:26<00:27, 2.30s/it] [ComfyUI] 78%|███████▊ | 39/50 [01:29<00:25, 2.30s/it] [ComfyUI] 80%|████████ | 40/50 [01:31<00:22, 2.30s/it] [ComfyUI] 82%|████████▏ | 41/50 [01:33<00:20, 2.30s/it] [ComfyUI] 84%|████████▍ | 42/50 [01:36<00:18, 2.30s/it] [ComfyUI] 86%|████████▌ | 43/50 [01:38<00:16, 2.30s/it] [ComfyUI] 88%|████████▊ | 44/50 [01:40<00:13, 2.30s/it] [ComfyUI] 90%|█████████ | 45/50 [01:43<00:11, 2.30s/it] [ComfyUI] 92%|█████████▏| 46/50 [01:45<00:09, 2.30s/it] [ComfyUI] 94%|█████████▍| 47/50 [01:47<00:06, 2.30s/it] [ComfyUI] 96%|█████████▌| 48/50 [01:49<00:04, 2.30s/it] [ComfyUI] 98%|█████████▊| 49/50 [01:52<00:02, 2.30s/it] [ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.30s/it] [ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.29s/it] [ComfyUI] Allocated memory: memory=12.760 GB [ComfyUI] Max allocated memory: max_memory=15.559 GB [ComfyUI] Max reserved memory: max_reserved=16.875 GB [ComfyUI] Executing node 5, title: HunyuanVideo Decode, class type: HyVideoDecode [ComfyUI] Decoding rows: 0%| | 0/2 [00:00<?, ?it/s] [ComfyUI] Decoding rows: 50%|█████ | 1/2 [00:01<00:01, 1.50s/it] [ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.26s/it] [ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.29s/it] [ComfyUI] [ComfyUI] Blending tiles: 0%| | 0/2 [00:00<?, ?it/s] [ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 28.50it/s] [ComfyUI] [ComfyUI] Decoding rows: 0%| | 0/2 [00:00<?, ?it/s] [ComfyUI] Decoding rows: 50%|█████ | 1/2 [00:00<00:00, 2.48it/s] [ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 2.94it/s] [ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 2.85it/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, 39.06it/s] [ComfyUI] Prompt executed in 152.18 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.mp4Prediction
deepfates/hunyuan-once-upon-a-time-in-hollywood:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3IDhp96c3mq4xrm80cmn4ab15w1b4StatusSucceededSourceAPIHardwareH100Total durationCreatedInput
- seed
- 12345
- steps
- 50
- width
- 640
- height
- 360
- prompt
- A video in the style of NCPNT, NCPNT The video clip depicts A detective's weathered face emerging from darkness as they step into a single shaft of light, cigarette smoke curling upward
- frame_rate
- 16
- num_frames
- 66
- lora_strength
- 1.2
- guidance_scale
- 6
{ "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts A detective's weathered face emerging from darkness as they step into a single shaft of light, cigarette smoke curling upward", "frame_rate": 16, "num_frames": 66, "lora_strength": 1.2, "guidance_scale": 6 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run deepfates/hunyuan-once-upon-a-time-in-hollywood using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "deepfates/hunyuan-once-upon-a-time-in-hollywood:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3", { input: { seed: 12345, steps: 50, width: 640, height: 360, prompt: "A video in the style of NCPNT, NCPNT The video clip depicts A detective's weathered face emerging from darkness as they step into a single shaft of light, cigarette smoke curling upward", frame_rate: 16, num_frames: 66, lora_strength: 1.2, guidance_scale: 6 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun deepfates/hunyuan-once-upon-a-time-in-hollywood using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "deepfates/hunyuan-once-upon-a-time-in-hollywood:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3", input={ "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts A detective's weathered face emerging from darkness as they step into a single shaft of light, cigarette smoke curling upward", "frame_rate": 16, "num_frames": 66, "lora_strength": 1.2, "guidance_scale": 6 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run deepfates/hunyuan-once-upon-a-time-in-hollywood using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3", "input": { "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts A detective\'s weathered face emerging from darkness as they step into a single shaft of light, cigarette smoke curling upward", "frame_rate": 16, "num_frames": 66, "lora_strength": 1.2, "guidance_scale": 6 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/deepfates/hunyuan-once-upon-a-time-in-hollywood@sha256:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3 \ -i 'seed=12345' \ -i 'steps=50' \ -i 'width=640' \ -i 'height=360' \ -i $'prompt="A video in the style of NCPNT, NCPNT The video clip depicts A detective\'s weathered face emerging from darkness as they step into a single shaft of light, cigarette smoke curling upward"' \ -i 'frame_rate=16' \ -i 'num_frames=66' \ -i 'lora_strength=1.2' \ -i 'guidance_scale=6'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/deepfates/hunyuan-once-upon-a-time-in-hollywood@sha256:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts A detective\'s weathered face emerging from darkness as they step into a single shaft of light, cigarette smoke curling upward", "frame_rate": 16, "num_frames": 66, "lora_strength": 1.2, "guidance_scale": 6 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2025-01-27T18:55:38.476921Z", "created_at": "2025-01-27T18:44:46.503000Z", "data_removed": false, "error": null, "id": "hp96c3mq4xrm80cmn4ab15w1b4", "input": { "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts A detective's weathered face emerging from darkness as they step into a single shaft of light, cigarette smoke curling upward", "frame_rate": 16, "num_frames": 66, "lora_strength": 1.2, "guidance_scale": 6 }, "logs": "Seed set to: 12345\n⚠️ Adjusted dimensions from 640x360 to 640x368 to satisfy model requirements\n⚠️ Adjusted frame count from 66 to 65 to satisfy model requirements\n�� USING REPLICATE WEIGHTS (preferred method)\n🎯 USING REPLICATE WEIGHTS TAR FILE 🎯\n----------------------------------------\n📦 Processing replicate weights tar file...\n🔄 Will rename LoRA to: replicate_af1261ba-b934-44a3-91d9-47287f4fd289.safetensors\n📂 Extracting tar contents...\n✅ Found lora_comfyui.safetensors in tar\n✨ Successfully copied LoRA to: ComfyUI/models/loras/replicate_af1261ba-b934-44a3-91d9-47287f4fd289.safetensors\n----------------------------------------\nChecking inputs\n====================================\nChecking weights\n✅ hunyuan_video_720_fp8_e4m3fn.safetensors exists in ComfyUI/models/diffusion_models\n✅ hunyuan_video_vae_bf16.safetensors exists in ComfyUI/models/vae\n====================================\nRunning workflow\n[ComfyUI] got prompt\nExecuting node 30, title: HunyuanVideo TextEncode, class type: HyVideoTextEncode\n[ComfyUI] llm prompt attention_mask shape: torch.Size([1, 161]), masked tokens: 42\n[ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 42\nExecuting node 41, title: HunyuanVideo Lora Select, class type: HyVideoLoraSelect\nExecuting node 1, title: HunyuanVideo Model Loader, class type: HyVideoModelLoader\n[ComfyUI] model_type FLOW\n[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.\n[ComfyUI] Using accelerate to load and assign model weights to device...\n[ComfyUI] Loading LoRA: replicate_af1261ba-b934-44a3-91d9-47287f4fd289 with strength: 1.2\n[ComfyUI] Requested to load HyVideoModel\n[ComfyUI] loaded completely 9.5367431640625e+25 12555.953247070312 True\n[ComfyUI] Input (height, width, video_length) = (368, 640, 65)\nExecuting node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler\n[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.\n[ComfyUI] Sampling 65 frames in 17 latents at 640x368 with 50 inference steps\n[ComfyUI] Scheduler config: FrozenDict([('num_train_timesteps', 1000), ('flow_shift', 9.0), ('reverse', True), ('solver', 'euler'), ('n_tokens', None), ('_use_default_values', ['num_train_timesteps', 'n_tokens'])])\n[ComfyUI]\n[ComfyUI] 0%| | 0/50 [00:00<?, ?it/s]\n[ComfyUI] 2%|▏ | 1/50 [00:02<01:52, 2.30s/it]\n[ComfyUI] 4%|▍ | 2/50 [00:04<01:37, 2.02s/it]\n[ComfyUI] 6%|▌ | 3/50 [00:06<01:41, 2.15s/it]\n[ComfyUI] 8%|▊ | 4/50 [00:08<01:41, 2.21s/it]\n[ComfyUI] 10%|█ | 5/50 [00:11<01:40, 2.24s/it]\n[ComfyUI] 12%|█▏ | 6/50 [00:13<01:39, 2.26s/it]\n[ComfyUI] 14%|█▍ | 7/50 [00:15<01:37, 2.28s/it]\n[ComfyUI] 16%|█▌ | 8/50 [00:17<01:35, 2.29s/it]\n[ComfyUI] 18%|█▊ | 9/50 [00:20<01:33, 2.29s/it]\n[ComfyUI] 20%|██ | 10/50 [00:22<01:31, 2.29s/it]\n[ComfyUI] 22%|██▏ | 11/50 [00:24<01:29, 2.29s/it]\n[ComfyUI] 24%|██▍ | 12/50 [00:27<01:27, 2.29s/it]\n[ComfyUI] 26%|██▌ | 13/50 [00:29<01:24, 2.29s/it]\n[ComfyUI] 28%|██▊ | 14/50 [00:31<01:22, 2.29s/it]\n[ComfyUI] 30%|███ | 15/50 [00:34<01:20, 2.29s/it]\n[ComfyUI] 32%|███▏ | 16/50 [00:36<01:17, 2.29s/it]\n[ComfyUI] 34%|███▍ | 17/50 [00:38<01:15, 2.29s/it]\n[ComfyUI] 36%|███▌ | 18/50 [00:40<01:13, 2.29s/it]\n[ComfyUI] 38%|███▊ | 19/50 [00:43<01:11, 2.29s/it]\n[ComfyUI] 40%|████ | 20/50 [00:45<01:08, 2.29s/it]\n[ComfyUI] 42%|████▏ | 21/50 [00:47<01:06, 2.29s/it]\n[ComfyUI] 44%|████▍ | 22/50 [00:50<01:04, 2.29s/it]\n[ComfyUI] 46%|████▌ | 23/50 [00:52<01:01, 2.29s/it]\n[ComfyUI] 48%|████▊ | 24/50 [00:54<00:59, 2.29s/it]\n[ComfyUI] 50%|█████ | 25/50 [00:56<00:57, 2.30s/it]\n[ComfyUI] 52%|█████▏ | 26/50 [00:59<00:55, 2.30s/it]\n[ComfyUI] 54%|█████▍ | 27/50 [01:01<00:52, 2.30s/it]\n[ComfyUI] 56%|█████▌ | 28/50 [01:03<00:50, 2.30s/it]\n[ComfyUI] 58%|█████▊ | 29/50 [01:06<00:48, 2.30s/it]\n[ComfyUI] 60%|██████ | 30/50 [01:08<00:45, 2.30s/it]\n[ComfyUI] 62%|██████▏ | 31/50 [01:10<00:43, 2.30s/it]\n[ComfyUI] 64%|██████▍ | 32/50 [01:13<00:41, 2.30s/it]\n[ComfyUI] 66%|██████▌ | 33/50 [01:15<00:39, 2.30s/it]\n[ComfyUI] 68%|██████▊ | 34/50 [01:17<00:36, 2.29s/it]\n[ComfyUI] 70%|███████ | 35/50 [01:19<00:34, 2.29s/it]\n[ComfyUI] 72%|███████▏ | 36/50 [01:22<00:32, 2.29s/it]\n[ComfyUI] 74%|███████▍ | 37/50 [01:24<00:29, 2.29s/it]\n[ComfyUI] 76%|███████▌ | 38/50 [01:26<00:27, 2.29s/it]\n[ComfyUI] 78%|███████▊ | 39/50 [01:29<00:25, 2.29s/it]\n[ComfyUI] 80%|████████ | 40/50 [01:31<00:22, 2.29s/it]\n[ComfyUI] 82%|████████▏ | 41/50 [01:33<00:20, 2.29s/it]\n[ComfyUI] 84%|████████▍ | 42/50 [01:35<00:18, 2.29s/it]\n[ComfyUI] 86%|████████▌ | 43/50 [01:38<00:16, 2.29s/it]\n[ComfyUI] 88%|████████▊ | 44/50 [01:40<00:13, 2.29s/it]\n[ComfyUI] 90%|█████████ | 45/50 [01:42<00:11, 2.29s/it]\n[ComfyUI] 92%|█████████▏| 46/50 [01:45<00:09, 2.29s/it]\n[ComfyUI] 94%|█████████▍| 47/50 [01:47<00:06, 2.29s/it]\n[ComfyUI] 96%|█████████▌| 48/50 [01:49<00:04, 2.29s/it]\n[ComfyUI] 98%|█████████▊| 49/50 [01:52<00:02, 2.29s/it]\n[ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.29s/it]\n[ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.29s/it]\n[ComfyUI] Allocated memory: memory=12.300 GB\n[ComfyUI] Max allocated memory: max_memory=15.099 GB\n[ComfyUI] Max reserved memory: max_reserved=16.344 GB\nExecuting node 5, title: HunyuanVideo Decode, class type: HyVideoDecode\n[ComfyUI]\n[ComfyUI] Decoding rows: 0%| | 0/2 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows: 50%|█████ | 1/2 [00:01<00:01, 1.46s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.24s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.27s/it]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/2 [00:00<?, ?it/s]\n[ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 26.02it/s]\n[ComfyUI]\n[ComfyUI] Decoding rows: 0%| | 0/2 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows: 50%|█████ | 1/2 [00:00<00:00, 2.55it/s]\n[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 3.04it/s]\n[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 2.95it/s]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/2 [00:00<?, ?it/s]\nExecuting node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine\n[ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 65.63it/s]\n[ComfyUI] Prompt executed in 141.84 seconds\noutputs: {'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'}]}}\n====================================\nHunyuanVideo_00001.png\nHunyuanVideo_00001.mp4", "metrics": { "predict_time": 148.656313145, "total_time": 651.973921 }, "output": "https://replicate.delivery/xezq/fxg8anMKrIThKapIegofYYqOL3gcHVnefbaMfSkqHfcRVRsEKA/HunyuanVideo_00001.mp4", "started_at": "2025-01-27T18:53:09.820608Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bsvm-5n4eobtnq6eis6lv7c7p2qetrawb62tf5fgalwjgbhfscbj5cota", "get": "https://api.replicate.com/v1/predictions/hp96c3mq4xrm80cmn4ab15w1b4", "cancel": "https://api.replicate.com/v1/predictions/hp96c3mq4xrm80cmn4ab15w1b4/cancel" }, "version": "47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3" }Generated inSeed set to: 12345 ⚠️ Adjusted dimensions from 640x360 to 640x368 to satisfy model requirements ⚠️ Adjusted frame count from 66 to 65 to satisfy model requirements �� USING REPLICATE WEIGHTS (preferred method) 🎯 USING REPLICATE WEIGHTS TAR FILE 🎯 ---------------------------------------- 📦 Processing replicate weights tar file... 🔄 Will rename LoRA to: replicate_af1261ba-b934-44a3-91d9-47287f4fd289.safetensors 📂 Extracting tar contents... ✅ Found lora_comfyui.safetensors in tar ✨ Successfully copied LoRA to: ComfyUI/models/loras/replicate_af1261ba-b934-44a3-91d9-47287f4fd289.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 30, title: HunyuanVideo TextEncode, class type: HyVideoTextEncode [ComfyUI] llm prompt attention_mask shape: torch.Size([1, 161]), masked tokens: 42 [ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 42 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_af1261ba-b934-44a3-91d9-47287f4fd289 with strength: 1.2 [ComfyUI] Requested to load HyVideoModel [ComfyUI] loaded completely 9.5367431640625e+25 12555.953247070312 True [ComfyUI] Input (height, width, video_length) = (368, 640, 65) 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 65 frames in 17 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', ['num_train_timesteps', 'n_tokens'])]) [ComfyUI] [ComfyUI] 0%| | 0/50 [00:00<?, ?it/s] [ComfyUI] 2%|▏ | 1/50 [00:02<01:52, 2.30s/it] [ComfyUI] 4%|▍ | 2/50 [00:04<01:37, 2.02s/it] [ComfyUI] 6%|▌ | 3/50 [00:06<01:41, 2.15s/it] [ComfyUI] 8%|▊ | 4/50 [00:08<01:41, 2.21s/it] [ComfyUI] 10%|█ | 5/50 [00:11<01:40, 2.24s/it] [ComfyUI] 12%|█▏ | 6/50 [00:13<01:39, 2.26s/it] [ComfyUI] 14%|█▍ | 7/50 [00:15<01:37, 2.28s/it] [ComfyUI] 16%|█▌ | 8/50 [00:17<01:35, 2.29s/it] [ComfyUI] 18%|█▊ | 9/50 [00:20<01:33, 2.29s/it] [ComfyUI] 20%|██ | 10/50 [00:22<01:31, 2.29s/it] [ComfyUI] 22%|██▏ | 11/50 [00:24<01:29, 2.29s/it] [ComfyUI] 24%|██▍ | 12/50 [00:27<01:27, 2.29s/it] [ComfyUI] 26%|██▌ | 13/50 [00:29<01:24, 2.29s/it] [ComfyUI] 28%|██▊ | 14/50 [00:31<01:22, 2.29s/it] [ComfyUI] 30%|███ | 15/50 [00:34<01:20, 2.29s/it] [ComfyUI] 32%|███▏ | 16/50 [00:36<01:17, 2.29s/it] [ComfyUI] 34%|███▍ | 17/50 [00:38<01:15, 2.29s/it] [ComfyUI] 36%|███▌ | 18/50 [00:40<01:13, 2.29s/it] [ComfyUI] 38%|███▊ | 19/50 [00:43<01:11, 2.29s/it] [ComfyUI] 40%|████ | 20/50 [00:45<01:08, 2.29s/it] [ComfyUI] 42%|████▏ | 21/50 [00:47<01:06, 2.29s/it] [ComfyUI] 44%|████▍ | 22/50 [00:50<01:04, 2.29s/it] [ComfyUI] 46%|████▌ | 23/50 [00:52<01:01, 2.29s/it] [ComfyUI] 48%|████▊ | 24/50 [00:54<00:59, 2.29s/it] [ComfyUI] 50%|█████ | 25/50 [00:56<00:57, 2.30s/it] [ComfyUI] 52%|█████▏ | 26/50 [00:59<00:55, 2.30s/it] [ComfyUI] 54%|█████▍ | 27/50 [01:01<00:52, 2.30s/it] [ComfyUI] 56%|█████▌ | 28/50 [01:03<00:50, 2.30s/it] [ComfyUI] 58%|█████▊ | 29/50 [01:06<00:48, 2.30s/it] [ComfyUI] 60%|██████ | 30/50 [01:08<00:45, 2.30s/it] [ComfyUI] 62%|██████▏ | 31/50 [01:10<00:43, 2.30s/it] [ComfyUI] 64%|██████▍ | 32/50 [01:13<00:41, 2.30s/it] [ComfyUI] 66%|██████▌ | 33/50 [01:15<00:39, 2.30s/it] [ComfyUI] 68%|██████▊ | 34/50 [01:17<00:36, 2.29s/it] [ComfyUI] 70%|███████ | 35/50 [01:19<00:34, 2.29s/it] [ComfyUI] 72%|███████▏ | 36/50 [01:22<00:32, 2.29s/it] [ComfyUI] 74%|███████▍ | 37/50 [01:24<00:29, 2.29s/it] [ComfyUI] 76%|███████▌ | 38/50 [01:26<00:27, 2.29s/it] [ComfyUI] 78%|███████▊ | 39/50 [01:29<00:25, 2.29s/it] [ComfyUI] 80%|████████ | 40/50 [01:31<00:22, 2.29s/it] [ComfyUI] 82%|████████▏ | 41/50 [01:33<00:20, 2.29s/it] [ComfyUI] 84%|████████▍ | 42/50 [01:35<00:18, 2.29s/it] [ComfyUI] 86%|████████▌ | 43/50 [01:38<00:16, 2.29s/it] [ComfyUI] 88%|████████▊ | 44/50 [01:40<00:13, 2.29s/it] [ComfyUI] 90%|█████████ | 45/50 [01:42<00:11, 2.29s/it] [ComfyUI] 92%|█████████▏| 46/50 [01:45<00:09, 2.29s/it] [ComfyUI] 94%|█████████▍| 47/50 [01:47<00:06, 2.29s/it] [ComfyUI] 96%|█████████▌| 48/50 [01:49<00:04, 2.29s/it] [ComfyUI] 98%|█████████▊| 49/50 [01:52<00:02, 2.29s/it] [ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.29s/it] [ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.29s/it] [ComfyUI] Allocated memory: memory=12.300 GB [ComfyUI] Max allocated memory: max_memory=15.099 GB [ComfyUI] Max reserved memory: max_reserved=16.344 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 [00:01<00:01, 1.46s/it] [ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.24s/it] [ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.27s/it] [ComfyUI] [ComfyUI] Blending tiles: 0%| | 0/2 [00:00<?, ?it/s] [ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 26.02it/s] [ComfyUI] [ComfyUI] Decoding rows: 0%| | 0/2 [00:00<?, ?it/s] [ComfyUI] Decoding rows: 50%|█████ | 1/2 [00:00<00:00, 2.55it/s] [ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 3.04it/s] [ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 2.95it/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, 65.63it/s] [ComfyUI] Prompt executed in 141.84 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.mp4Prediction
deepfates/hunyuan-once-upon-a-time-in-hollywood:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3IDgyvatsey89rma0cmn4qvvwbtecStatusSucceededSourceAPIHardwareH100Total durationCreatedInput
- seed
- 12345
- steps
- 50
- width
- 640
- height
- 360
- prompt
- A video in the style of NCPNT, NCPNT The video clip depicts A warrior woman with long dark hair standing on a cliff edge, her black cloak billowing in the storm wind
- frame_rate
- 16
- num_frames
- 66
- lora_strength
- 1.2
- guidance_scale
- 6
{ "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts A warrior woman with long dark hair standing on a cliff edge, her black cloak billowing in the storm wind", "frame_rate": 16, "num_frames": 66, "lora_strength": 1.2, "guidance_scale": 6 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run deepfates/hunyuan-once-upon-a-time-in-hollywood using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "deepfates/hunyuan-once-upon-a-time-in-hollywood:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3", { input: { seed: 12345, steps: 50, width: 640, height: 360, prompt: "A video in the style of NCPNT, NCPNT The video clip depicts A warrior woman with long dark hair standing on a cliff edge, her black cloak billowing in the storm wind", frame_rate: 16, num_frames: 66, lora_strength: 1.2, guidance_scale: 6 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun deepfates/hunyuan-once-upon-a-time-in-hollywood using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "deepfates/hunyuan-once-upon-a-time-in-hollywood:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3", input={ "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts A warrior woman with long dark hair standing on a cliff edge, her black cloak billowing in the storm wind", "frame_rate": 16, "num_frames": 66, "lora_strength": 1.2, "guidance_scale": 6 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run deepfates/hunyuan-once-upon-a-time-in-hollywood using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3", "input": { "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts A warrior woman with long dark hair standing on a cliff edge, her black cloak billowing in the storm wind", "frame_rate": 16, "num_frames": 66, "lora_strength": 1.2, "guidance_scale": 6 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/deepfates/hunyuan-once-upon-a-time-in-hollywood@sha256:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3 \ -i 'seed=12345' \ -i 'steps=50' \ -i 'width=640' \ -i 'height=360' \ -i 'prompt="A video in the style of NCPNT, NCPNT The video clip depicts A warrior woman with long dark hair standing on a cliff edge, her black cloak billowing in the storm wind"' \ -i 'frame_rate=16' \ -i 'num_frames=66' \ -i 'lora_strength=1.2' \ -i 'guidance_scale=6'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/deepfates/hunyuan-once-upon-a-time-in-hollywood@sha256:47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts A warrior woman with long dark hair standing on a cliff edge, her black cloak billowing in the storm wind", "frame_rate": 16, "num_frames": 66, "lora_strength": 1.2, "guidance_scale": 6 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2025-01-27T19:17:01.959687Z", "created_at": "2025-01-27T19:14:34.178000Z", "data_removed": false, "error": null, "id": "gyvatsey89rma0cmn4qvvwbtec", "input": { "seed": 12345, "steps": 50, "width": 640, "height": 360, "prompt": "A video in the style of NCPNT, NCPNT The video clip depicts A warrior woman with long dark hair standing on a cliff edge, her black cloak billowing in the storm wind", "frame_rate": 16, "num_frames": 66, "lora_strength": 1.2, "guidance_scale": 6 }, "logs": "Seed set to: 12345\n⚠️ Adjusted dimensions from 640x360 to 640x368 to satisfy model requirements\n⚠️ Adjusted frame count from 66 to 65 to satisfy model requirements\n�� USING REPLICATE WEIGHTS (preferred method)\n🎯 USING REPLICATE WEIGHTS TAR FILE 🎯\n----------------------------------------\n📦 Processing replicate weights tar file...\n🔄 Will rename LoRA to: replicate_4427c977-cfdb-4538-a7f8-8465734af383.safetensors\n📂 Extracting tar contents...\n✅ Found lora_comfyui.safetensors in tar\n✨ Successfully copied LoRA to: ComfyUI/models/loras/replicate_4427c977-cfdb-4538-a7f8-8465734af383.safetensors\n----------------------------------------\nChecking inputs\n====================================\nChecking weights\n✅ hunyuan_video_vae_bf16.safetensors exists in ComfyUI/models/vae\n✅ hunyuan_video_720_fp8_e4m3fn.safetensors exists in ComfyUI/models/diffusion_models\n====================================\nRunning workflow\n[ComfyUI] got prompt\nExecuting node 30, title: HunyuanVideo TextEncode, class type: HyVideoTextEncode\n[ComfyUI] llm prompt attention_mask shape: torch.Size([1, 161]), masked tokens: 40\n[ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 41\nExecuting node 41, title: HunyuanVideo Lora Select, class type: HyVideoLoraSelect\nExecuting node 1, title: HunyuanVideo Model Loader, class type: HyVideoModelLoader\n[ComfyUI] model_type FLOW\n[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.\n[ComfyUI] Using accelerate to load and assign model weights to device...\n[ComfyUI] Loading LoRA: replicate_4427c977-cfdb-4538-a7f8-8465734af383 with strength: 1.2\n[ComfyUI] Requested to load HyVideoModel\n[ComfyUI] loaded completely 9.5367431640625e+25 12555.953247070312 True\n[ComfyUI] Input (height, width, video_length) = (368, 640, 65)\n[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.\nExecuting node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler\n[ComfyUI] Sampling 65 frames in 17 latents at 640x368 with 50 inference steps\n[ComfyUI] Scheduler config: FrozenDict([('num_train_timesteps', 1000), ('flow_shift', 9.0), ('reverse', True), ('solver', 'euler'), ('n_tokens', None), ('_use_default_values', ['num_train_timesteps', 'n_tokens'])])\n[ComfyUI]\n[ComfyUI] 0%| | 0/50 [00:00<?, ?it/s]\n[ComfyUI] 2%|▏ | 1/50 [00:02<01:52, 2.30s/it]\n[ComfyUI] 4%|▍ | 2/50 [00:04<01:36, 2.02s/it]\n[ComfyUI] 6%|▌ | 3/50 [00:06<01:41, 2.15s/it]\n[ComfyUI] 8%|▊ | 4/50 [00:08<01:41, 2.21s/it]\n[ComfyUI] 10%|█ | 5/50 [00:11<01:40, 2.24s/it]\n[ComfyUI] 12%|█▏ | 6/50 [00:13<01:39, 2.26s/it]\n[ComfyUI] 14%|█▍ | 7/50 [00:15<01:37, 2.27s/it]\n[ComfyUI] 16%|█▌ | 8/50 [00:17<01:35, 2.28s/it]\n[ComfyUI] 18%|█▊ | 9/50 [00:20<01:33, 2.28s/it]\n[ComfyUI] 20%|██ | 10/50 [00:22<01:31, 2.29s/it]\n[ComfyUI] 22%|██▏ | 11/50 [00:24<01:29, 2.29s/it]\n[ComfyUI] 24%|██▍ | 12/50 [00:27<01:27, 2.29s/it]\n[ComfyUI] 26%|██▌ | 13/50 [00:29<01:24, 2.29s/it]\n[ComfyUI] 28%|██▊ | 14/50 [00:31<01:22, 2.29s/it]\n[ComfyUI] 30%|███ | 15/50 [00:33<01:20, 2.29s/it]\n[ComfyUI] 32%|███▏ | 16/50 [00:36<01:17, 2.29s/it]\n[ComfyUI] 34%|███▍ | 17/50 [00:38<01:15, 2.29s/it]\n[ComfyUI] 36%|███▌ | 18/50 [00:40<01:13, 2.29s/it]\n[ComfyUI] 38%|███▊ | 19/50 [00:43<01:11, 2.29s/it]\n[ComfyUI] 40%|████ | 20/50 [00:45<01:08, 2.29s/it]\n[ComfyUI] 42%|████▏ | 21/50 [00:47<01:06, 2.29s/it]\n[ComfyUI] 44%|████▍ | 22/50 [00:50<01:04, 2.29s/it]\n[ComfyUI] 46%|████▌ | 23/50 [00:52<01:01, 2.29s/it]\n[ComfyUI] 48%|████▊ | 24/50 [00:54<00:59, 2.29s/it]\n[ComfyUI] 50%|█████ | 25/50 [00:56<00:57, 2.29s/it]\n[ComfyUI] 52%|█████▏ | 26/50 [00:59<00:55, 2.29s/it]\n[ComfyUI] 54%|█████▍ | 27/50 [01:01<00:52, 2.29s/it]\n[ComfyUI] 56%|█████▌ | 28/50 [01:03<00:50, 2.29s/it]\n[ComfyUI] 58%|█████▊ | 29/50 [01:06<00:48, 2.29s/it]\n[ComfyUI] 60%|██████ | 30/50 [01:08<00:45, 2.29s/it]\n[ComfyUI] 62%|██████▏ | 31/50 [01:10<00:43, 2.29s/it]\n[ComfyUI] 64%|██████▍ | 32/50 [01:12<00:41, 2.29s/it]\n[ComfyUI] 66%|██████▌ | 33/50 [01:15<00:39, 2.29s/it]\n[ComfyUI] 68%|██████▊ | 34/50 [01:17<00:36, 2.29s/it]\n[ComfyUI] 70%|███████ | 35/50 [01:19<00:34, 2.29s/it]\n[ComfyUI] 72%|███████▏ | 36/50 [01:22<00:32, 2.29s/it]\n[ComfyUI] 74%|███████▍ | 37/50 [01:24<00:29, 2.29s/it]\n[ComfyUI] 76%|███████▌ | 38/50 [01:26<00:27, 2.29s/it]\n[ComfyUI] 78%|███████▊ | 39/50 [01:29<00:25, 2.29s/it]\n[ComfyUI] 80%|████████ | 40/50 [01:31<00:22, 2.29s/it]\n[ComfyUI] 82%|████████▏ | 41/50 [01:33<00:20, 2.29s/it]\n[ComfyUI] 84%|████████▍ | 42/50 [01:35<00:18, 2.29s/it]\n[ComfyUI] 86%|████████▌ | 43/50 [01:38<00:16, 2.29s/it]\n[ComfyUI] 88%|████████▊ | 44/50 [01:40<00:13, 2.29s/it]\n[ComfyUI] 90%|█████████ | 45/50 [01:42<00:11, 2.29s/it]\n[ComfyUI] 92%|█████████▏| 46/50 [01:45<00:09, 2.29s/it]\n[ComfyUI] 94%|█████████▍| 47/50 [01:47<00:06, 2.29s/it]\n[ComfyUI] 96%|█████████▌| 48/50 [01:49<00:04, 2.29s/it]\n[ComfyUI] 98%|█████████▊| 49/50 [01:51<00:02, 2.29s/it]\n[ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.29s/it]\n[ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.29s/it]\n[ComfyUI] Allocated memory: memory=12.300 GB\n[ComfyUI] Max allocated memory: max_memory=15.099 GB\n[ComfyUI] Max reserved memory: max_reserved=16.281 GB\nExecuting node 5, title: HunyuanVideo Decode, class type: HyVideoDecode\n[ComfyUI]\n[ComfyUI] Decoding rows: 0%| | 0/2 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows: 50%|█████ | 1/2 [00:01<00:01, 1.46s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.24s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.27s/it]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/2 [00:00<?, ?it/s]\n[ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 25.85it/s]\n[ComfyUI]\n[ComfyUI] Decoding rows: 0%| | 0/2 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows: 50%|█████ | 1/2 [00:00<00:00, 2.49it/s]\n[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 2.99it/s]\n[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 2.90it/s]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/2 [00:00<?, ?it/s]\nExecuting node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine\n[ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 64.73it/s]\n[ComfyUI] Prompt executed in 141.44 seconds\noutputs: {'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'}]}}\n====================================\nHunyuanVideo_00001.png\nHunyuanVideo_00001.mp4", "metrics": { "predict_time": 147.773267132, "total_time": 147.781687 }, "output": "https://replicate.delivery/xezq/RWNfeuXgkqmOXkEjBcFTu1TV5Rf790uDffoegqdoRTlTrNWCF/HunyuanVideo_00001.mp4", "started_at": "2025-01-27T19:14:34.186419Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bsvm-zakguvmt2zczvpmhqfrupweejoti3swi4x3ibpptzgqxfclvml4q", "get": "https://api.replicate.com/v1/predictions/gyvatsey89rma0cmn4qvvwbtec", "cancel": "https://api.replicate.com/v1/predictions/gyvatsey89rma0cmn4qvvwbtec/cancel" }, "version": "47e048cf3de47305fccb9410f2d9c9f89e626a38e1d6dc08561698c5d8ffa2b3" }Generated inSeed set to: 12345 ⚠️ Adjusted dimensions from 640x360 to 640x368 to satisfy model requirements ⚠️ Adjusted frame count from 66 to 65 to satisfy model requirements �� USING REPLICATE WEIGHTS (preferred method) 🎯 USING REPLICATE WEIGHTS TAR FILE 🎯 ---------------------------------------- 📦 Processing replicate weights tar file... 🔄 Will rename LoRA to: replicate_4427c977-cfdb-4538-a7f8-8465734af383.safetensors 📂 Extracting tar contents... ✅ Found lora_comfyui.safetensors in tar ✨ Successfully copied LoRA to: ComfyUI/models/loras/replicate_4427c977-cfdb-4538-a7f8-8465734af383.safetensors ---------------------------------------- Checking inputs ==================================== Checking weights ✅ hunyuan_video_vae_bf16.safetensors exists in ComfyUI/models/vae ✅ hunyuan_video_720_fp8_e4m3fn.safetensors exists in ComfyUI/models/diffusion_models ==================================== Running workflow [ComfyUI] got prompt Executing node 30, title: HunyuanVideo TextEncode, class type: HyVideoTextEncode [ComfyUI] llm prompt attention_mask shape: torch.Size([1, 161]), masked tokens: 40 [ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 41 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_4427c977-cfdb-4538-a7f8-8465734af383 with strength: 1.2 [ComfyUI] Requested to load HyVideoModel [ComfyUI] loaded completely 9.5367431640625e+25 12555.953247070312 True [ComfyUI] Input (height, width, video_length) = (368, 640, 65) [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. Executing node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler [ComfyUI] Sampling 65 frames in 17 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', ['num_train_timesteps', 'n_tokens'])]) [ComfyUI] [ComfyUI] 0%| | 0/50 [00:00<?, ?it/s] [ComfyUI] 2%|▏ | 1/50 [00:02<01:52, 2.30s/it] [ComfyUI] 4%|▍ | 2/50 [00:04<01:36, 2.02s/it] [ComfyUI] 6%|▌ | 3/50 [00:06<01:41, 2.15s/it] [ComfyUI] 8%|▊ | 4/50 [00:08<01:41, 2.21s/it] [ComfyUI] 10%|█ | 5/50 [00:11<01:40, 2.24s/it] [ComfyUI] 12%|█▏ | 6/50 [00:13<01:39, 2.26s/it] [ComfyUI] 14%|█▍ | 7/50 [00:15<01:37, 2.27s/it] [ComfyUI] 16%|█▌ | 8/50 [00:17<01:35, 2.28s/it] [ComfyUI] 18%|█▊ | 9/50 [00:20<01:33, 2.28s/it] [ComfyUI] 20%|██ | 10/50 [00:22<01:31, 2.29s/it] [ComfyUI] 22%|██▏ | 11/50 [00:24<01:29, 2.29s/it] [ComfyUI] 24%|██▍ | 12/50 [00:27<01:27, 2.29s/it] [ComfyUI] 26%|██▌ | 13/50 [00:29<01:24, 2.29s/it] [ComfyUI] 28%|██▊ | 14/50 [00:31<01:22, 2.29s/it] [ComfyUI] 30%|███ | 15/50 [00:33<01:20, 2.29s/it] [ComfyUI] 32%|███▏ | 16/50 [00:36<01:17, 2.29s/it] [ComfyUI] 34%|███▍ | 17/50 [00:38<01:15, 2.29s/it] [ComfyUI] 36%|███▌ | 18/50 [00:40<01:13, 2.29s/it] [ComfyUI] 38%|███▊ | 19/50 [00:43<01:11, 2.29s/it] [ComfyUI] 40%|████ | 20/50 [00:45<01:08, 2.29s/it] [ComfyUI] 42%|████▏ | 21/50 [00:47<01:06, 2.29s/it] [ComfyUI] 44%|████▍ | 22/50 [00:50<01:04, 2.29s/it] [ComfyUI] 46%|████▌ | 23/50 [00:52<01:01, 2.29s/it] [ComfyUI] 48%|████▊ | 24/50 [00:54<00:59, 2.29s/it] [ComfyUI] 50%|█████ | 25/50 [00:56<00:57, 2.29s/it] [ComfyUI] 52%|█████▏ | 26/50 [00:59<00:55, 2.29s/it] [ComfyUI] 54%|█████▍ | 27/50 [01:01<00:52, 2.29s/it] [ComfyUI] 56%|█████▌ | 28/50 [01:03<00:50, 2.29s/it] [ComfyUI] 58%|█████▊ | 29/50 [01:06<00:48, 2.29s/it] [ComfyUI] 60%|██████ | 30/50 [01:08<00:45, 2.29s/it] [ComfyUI] 62%|██████▏ | 31/50 [01:10<00:43, 2.29s/it] [ComfyUI] 64%|██████▍ | 32/50 [01:12<00:41, 2.29s/it] [ComfyUI] 66%|██████▌ | 33/50 [01:15<00:39, 2.29s/it] [ComfyUI] 68%|██████▊ | 34/50 [01:17<00:36, 2.29s/it] [ComfyUI] 70%|███████ | 35/50 [01:19<00:34, 2.29s/it] [ComfyUI] 72%|███████▏ | 36/50 [01:22<00:32, 2.29s/it] [ComfyUI] 74%|███████▍ | 37/50 [01:24<00:29, 2.29s/it] [ComfyUI] 76%|███████▌ | 38/50 [01:26<00:27, 2.29s/it] [ComfyUI] 78%|███████▊ | 39/50 [01:29<00:25, 2.29s/it] [ComfyUI] 80%|████████ | 40/50 [01:31<00:22, 2.29s/it] [ComfyUI] 82%|████████▏ | 41/50 [01:33<00:20, 2.29s/it] [ComfyUI] 84%|████████▍ | 42/50 [01:35<00:18, 2.29s/it] [ComfyUI] 86%|████████▌ | 43/50 [01:38<00:16, 2.29s/it] [ComfyUI] 88%|████████▊ | 44/50 [01:40<00:13, 2.29s/it] [ComfyUI] 90%|█████████ | 45/50 [01:42<00:11, 2.29s/it] [ComfyUI] 92%|█████████▏| 46/50 [01:45<00:09, 2.29s/it] [ComfyUI] 94%|█████████▍| 47/50 [01:47<00:06, 2.29s/it] [ComfyUI] 96%|█████████▌| 48/50 [01:49<00:04, 2.29s/it] [ComfyUI] 98%|█████████▊| 49/50 [01:51<00:02, 2.29s/it] [ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.29s/it] [ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.29s/it] [ComfyUI] Allocated memory: memory=12.300 GB [ComfyUI] Max allocated memory: max_memory=15.099 GB [ComfyUI] Max reserved memory: max_reserved=16.281 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 [00:01<00:01, 1.46s/it] [ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.24s/it] [ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.27s/it] [ComfyUI] [ComfyUI] Blending tiles: 0%| | 0/2 [00:00<?, ?it/s] [ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 25.85it/s] [ComfyUI] [ComfyUI] Decoding rows: 0%| | 0/2 [00:00<?, ?it/s] [ComfyUI] Decoding rows: 50%|█████ | 1/2 [00:00<00:00, 2.49it/s] [ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 2.99it/s] [ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 2.90it/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, 64.73it/s] [ComfyUI] Prompt executed in 141.44 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
Want to make some of these yourself?
Run this model