lucataco / hunyuan-heygen-woman
HunyuanVideo finetune of an AI avatar from Heygen
- Public
- 109 runs
-
H100
- Fine-tune
Prediction
lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37bIDxhkfvtertsrma0cmbfv80n8dtgStatusSucceededSourceWebHardwareH100Total durationCreatedInput
- crf
- 19
- steps
- 30
- width
- 960
- height
- 544
- prompt
- HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient blue background, appearing calm and composed, possibly in a casual setting or an interview scenario.
- lora_url
- flow_shift
- 9
- frame_rate
- 20
- num_frames
- 49
- force_offload
- lora_strength
- 1
- guidance_scale
- 6
- denoise_strength
- 1
{ "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient blue background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 }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 lucataco/hunyuan-heygen-woman using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b", { input: { crf: 19, steps: 30, width: 960, height: 544, prompt: "HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient blue background, appearing calm and composed, possibly in a casual setting or an interview scenario.", lora_url: "", flow_shift: 9, frame_rate: 20, num_frames: 49, force_offload: true, lora_strength: 1, guidance_scale: 6, denoise_strength: 1 } } ); // 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 lucataco/hunyuan-heygen-woman using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b", input={ "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient blue background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": True, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run lucataco/hunyuan-heygen-woman 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": "lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b", "input": { "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient blue background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 } }' \ 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/lucataco/hunyuan-heygen-woman@sha256:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b \ -i 'crf=19' \ -i 'steps=30' \ -i 'width=960' \ -i 'height=544' \ -i 'prompt="HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient blue background, appearing calm and composed, possibly in a casual setting or an interview scenario."' \ -i 'lora_url=""' \ -i 'flow_shift=9' \ -i 'frame_rate=20' \ -i 'num_frames=49' \ -i 'force_offload=true' \ -i 'lora_strength=1' \ -i 'guidance_scale=6' \ -i 'denoise_strength=1'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/lucataco/hunyuan-heygen-woman@sha256:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37bcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient blue background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2025-01-12T19:25:26.870683Z", "created_at": "2025-01-12T19:21:31.606000Z", "data_removed": false, "error": null, "id": "xhkfvtertsrma0cmbfv80n8dtg", "input": { "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient blue background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 }, "logs": "Random seed set to: 238810062\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 7, title: HunyuanVideo VAE Loader, class type: HyVideoVAELoader\n[ComfyUI] Loading text encoder model (clipL) from: /src/ComfyUI/models/clip/clip-vit-large-patch14\nExecuting node 16, title: (Down)Load HunyuanVideo TextEncoder, class type: DownloadAndLoadHyVideoTextEncoder\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<00:01, 1.66it/s]\n[ComfyUI] Loading checkpoint shards: 50%|█████ | 2/4 [00:01<00:01, 1.72it/s]\n[ComfyUI] Loading checkpoint shards: 75%|███████▌ | 3/4 [00:01<00:00, 1.74it/s]\n[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00, 2.54it/s]\n[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00, 2.16it/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: 48\n[ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 50\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] Using accelerate to load and assign model weights to device...\n[ComfyUI] Loading LoRA: lora_comfyui with strength: 1.0\n[ComfyUI] Requested to load HyVideoModel\n[ComfyUI] Loading 1 new model\n[ComfyUI] loaded completely 0.0 12555.953247070312 True\n[ComfyUI] Input (height, width, video_length) = (544, 960, 49)\nExecuting node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler\n[ComfyUI] Sampling 49 frames in 13 latents at 960x544 with 30 inference steps\n[ComfyUI] Scheduler config: FrozenDict([('num_train_timesteps', 1000), ('shift', 9.0), ('reverse', True), ('solver', 'euler'), ('n_tokens', None), ('_use_default_values', ['num_train_timesteps', 'n_tokens'])])\n[ComfyUI]\n[ComfyUI] 0%| | 0/30 [00:00<?, ?it/s]\n[ComfyUI] 3%|▎ | 1/30 [00:04<01:59, 4.12s/it]\n[ComfyUI] 7%|▋ | 2/30 [00:09<02:18, 4.95s/it]\n[ComfyUI] 10%|█ | 3/30 [00:15<02:20, 5.21s/it]\n[ComfyUI] 13%|█▎ | 4/30 [00:20<02:18, 5.34s/it]\n[ComfyUI] 17%|█▋ | 5/30 [00:26<02:15, 5.41s/it]\n[ComfyUI] 20%|██ | 6/30 [00:31<02:10, 5.45s/it]\n[ComfyUI] 23%|██▎ | 7/30 [00:37<02:05, 5.47s/it]\n[ComfyUI] 27%|██▋ | 8/30 [00:42<02:00, 5.49s/it]\n[ComfyUI] 30%|███ | 9/30 [00:48<01:55, 5.50s/it]\n[ComfyUI] 33%|███▎ | 10/30 [00:53<01:50, 5.50s/it]\n[ComfyUI] 37%|███▋ | 11/30 [00:59<01:44, 5.51s/it]\n[ComfyUI] 40%|████ | 12/30 [01:04<01:39, 5.51s/it]\n[ComfyUI] 43%|████▎ | 13/30 [01:10<01:33, 5.52s/it]\n[ComfyUI] 47%|████▋ | 14/30 [01:15<01:28, 5.52s/it]\n[ComfyUI] 50%|█████ | 15/30 [01:21<01:22, 5.52s/it]\n[ComfyUI] 53%|█████▎ | 16/30 [01:26<01:17, 5.52s/it]\n[ComfyUI] 57%|█████▋ | 17/30 [01:32<01:11, 5.52s/it]\n[ComfyUI] 60%|██████ | 18/30 [01:38<01:06, 5.52s/it]\n[ComfyUI] 63%|██████▎ | 19/30 [01:43<01:00, 5.52s/it]\n[ComfyUI] 67%|██████▋ | 20/30 [01:49<00:55, 5.52s/it]\n[ComfyUI] 70%|███████ | 21/30 [01:54<00:49, 5.52s/it]\n[ComfyUI] 73%|███████▎ | 22/30 [02:00<00:44, 5.52s/it]\n[ComfyUI] 77%|███████▋ | 23/30 [02:05<00:38, 5.52s/it]\n[ComfyUI] 80%|████████ | 24/30 [02:11<00:33, 5.52s/it]\n[ComfyUI] 83%|████████▎ | 25/30 [02:16<00:27, 5.52s/it]\n[ComfyUI] 87%|████████▋ | 26/30 [02:22<00:22, 5.52s/it]\n[ComfyUI] 90%|█████████ | 27/30 [02:27<00:16, 5.52s/it]\n[ComfyUI] 93%|█████████▎| 28/30 [02:33<00:11, 5.52s/it]\n[ComfyUI] 97%|█████████▋| 29/30 [02:38<00:05, 5.52s/it]\n[ComfyUI] 100%|██████████| 30/30 [02:44<00:00, 5.52s/it]\n[ComfyUI] 100%|██████████| 30/30 [02:44<00:00, 5.48s/it]\n[ComfyUI] Allocated memory: memory=12.760 GB\n[ComfyUI] Max allocated memory: max_memory=18.839 GB\n[ComfyUI] Max reserved memory: max_reserved=20.719 GB\nExecuting node 5, title: HunyuanVideo Decode, class type: HyVideoDecode\n[ComfyUI]\n[ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:01<00:03, 1.52s/it]\n[ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:03<00:01, 1.63s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.41s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.46s/it]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Blending tiles: 33%|███▎ | 1/3 [00:00<00:00, 7.80it/s]\nExecuting node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine\n[ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 18.11it/s]\n[ComfyUI] Prompt executed in 201.68 seconds\noutputs: {'34': {'gifs': [{'filename': 'HunyuanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 20.0, 'workflow': 'HunyuanVideo_00001.png', 'fullpath': '/tmp/outputs/HunyuanVideo_00001.mp4'}]}}\n====================================\nHunyuanVideo_00001.png\nHunyuanVideo_00001.mp4", "metrics": { "predict_time": 207.732066712, "total_time": 235.264683 }, "output": "https://replicate.delivery/xezq/Dtwe7FsPfVpT5kBj7KK9exLfgONY1JQjyaGCfH1kHK5zkkjgC/HunyuanVideo_00001.mp4", "started_at": "2025-01-12T19:21:59.138616Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-ygewqh3lttmvsnpa2vtxdf5ux7yksixm2s5xmb6cws56xfjeplmq", "get": "https://api.replicate.com/v1/predictions/xhkfvtertsrma0cmbfv80n8dtg", "cancel": "https://api.replicate.com/v1/predictions/xhkfvtertsrma0cmbfv80n8dtg/cancel" }, "version": "ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b" }Generated inRandom seed set to: 238810062 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 7, title: HunyuanVideo VAE Loader, class type: HyVideoVAELoader [ComfyUI] Loading text encoder model (clipL) from: /src/ComfyUI/models/clip/clip-vit-large-patch14 Executing node 16, title: (Down)Load HunyuanVideo TextEncoder, class type: DownloadAndLoadHyVideoTextEncoder [ComfyUI] Text encoder to dtype: torch.float16 [ComfyUI] Loading tokenizer (clipL) from: /src/ComfyUI/models/clip/clip-vit-large-patch14 [ComfyUI] Loading text encoder model (llm) from: /src/ComfyUI/models/LLM/llava-llama-3-8b-text-encoder-tokenizer [ComfyUI] [ComfyUI] Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s] [ComfyUI] Loading checkpoint shards: 25%|██▌ | 1/4 [00:00<00:01, 1.66it/s] [ComfyUI] Loading checkpoint shards: 50%|█████ | 2/4 [00:01<00:01, 1.72it/s] [ComfyUI] Loading checkpoint shards: 75%|███████▌ | 3/4 [00:01<00:00, 1.74it/s] [ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00, 2.54it/s] [ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00, 2.16it/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: 48 [ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 50 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] Using accelerate to load and assign model weights to device... [ComfyUI] Loading LoRA: lora_comfyui with strength: 1.0 [ComfyUI] Requested to load HyVideoModel [ComfyUI] Loading 1 new model [ComfyUI] loaded completely 0.0 12555.953247070312 True [ComfyUI] Input (height, width, video_length) = (544, 960, 49) Executing node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler [ComfyUI] Sampling 49 frames in 13 latents at 960x544 with 30 inference steps [ComfyUI] Scheduler config: FrozenDict([('num_train_timesteps', 1000), ('shift', 9.0), ('reverse', True), ('solver', 'euler'), ('n_tokens', None), ('_use_default_values', ['num_train_timesteps', 'n_tokens'])]) [ComfyUI] [ComfyUI] 0%| | 0/30 [00:00<?, ?it/s] [ComfyUI] 3%|▎ | 1/30 [00:04<01:59, 4.12s/it] [ComfyUI] 7%|▋ | 2/30 [00:09<02:18, 4.95s/it] [ComfyUI] 10%|█ | 3/30 [00:15<02:20, 5.21s/it] [ComfyUI] 13%|█▎ | 4/30 [00:20<02:18, 5.34s/it] [ComfyUI] 17%|█▋ | 5/30 [00:26<02:15, 5.41s/it] [ComfyUI] 20%|██ | 6/30 [00:31<02:10, 5.45s/it] [ComfyUI] 23%|██▎ | 7/30 [00:37<02:05, 5.47s/it] [ComfyUI] 27%|██▋ | 8/30 [00:42<02:00, 5.49s/it] [ComfyUI] 30%|███ | 9/30 [00:48<01:55, 5.50s/it] [ComfyUI] 33%|███▎ | 10/30 [00:53<01:50, 5.50s/it] [ComfyUI] 37%|███▋ | 11/30 [00:59<01:44, 5.51s/it] [ComfyUI] 40%|████ | 12/30 [01:04<01:39, 5.51s/it] [ComfyUI] 43%|████▎ | 13/30 [01:10<01:33, 5.52s/it] [ComfyUI] 47%|████▋ | 14/30 [01:15<01:28, 5.52s/it] [ComfyUI] 50%|█████ | 15/30 [01:21<01:22, 5.52s/it] [ComfyUI] 53%|█████▎ | 16/30 [01:26<01:17, 5.52s/it] [ComfyUI] 57%|█████▋ | 17/30 [01:32<01:11, 5.52s/it] [ComfyUI] 60%|██████ | 18/30 [01:38<01:06, 5.52s/it] [ComfyUI] 63%|██████▎ | 19/30 [01:43<01:00, 5.52s/it] [ComfyUI] 67%|██████▋ | 20/30 [01:49<00:55, 5.52s/it] [ComfyUI] 70%|███████ | 21/30 [01:54<00:49, 5.52s/it] [ComfyUI] 73%|███████▎ | 22/30 [02:00<00:44, 5.52s/it] [ComfyUI] 77%|███████▋ | 23/30 [02:05<00:38, 5.52s/it] [ComfyUI] 80%|████████ | 24/30 [02:11<00:33, 5.52s/it] [ComfyUI] 83%|████████▎ | 25/30 [02:16<00:27, 5.52s/it] [ComfyUI] 87%|████████▋ | 26/30 [02:22<00:22, 5.52s/it] [ComfyUI] 90%|█████████ | 27/30 [02:27<00:16, 5.52s/it] [ComfyUI] 93%|█████████▎| 28/30 [02:33<00:11, 5.52s/it] [ComfyUI] 97%|█████████▋| 29/30 [02:38<00:05, 5.52s/it] [ComfyUI] 100%|██████████| 30/30 [02:44<00:00, 5.52s/it] [ComfyUI] 100%|██████████| 30/30 [02:44<00:00, 5.48s/it] [ComfyUI] Allocated memory: memory=12.760 GB [ComfyUI] Max allocated memory: max_memory=18.839 GB [ComfyUI] Max reserved memory: max_reserved=20.719 GB Executing node 5, title: HunyuanVideo Decode, class type: HyVideoDecode [ComfyUI] [ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s] [ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:01<00:03, 1.52s/it] [ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:03<00:01, 1.63s/it] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.41s/it] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.46s/it] [ComfyUI] [ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s] [ComfyUI] Blending tiles: 33%|███▎ | 1/3 [00:00<00:00, 7.80it/s] Executing node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine [ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 18.11it/s] [ComfyUI] Prompt executed in 201.68 seconds outputs: {'34': {'gifs': [{'filename': 'HunyuanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 20.0, 'workflow': 'HunyuanVideo_00001.png', 'fullpath': '/tmp/outputs/HunyuanVideo_00001.mp4'}]}} ==================================== HunyuanVideo_00001.png HunyuanVideo_00001.mp4Prediction
lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37bIDrjwtazpgmdrme0cmbfxtg1sm08StatusSucceededSourceWebHardwareH100Total durationCreatedInput
- crf
- 19
- steps
- 30
- width
- 960
- height
- 544
- prompt
- HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient blue background, appearing calm and composed, possibly in a casual setting or an interview scenario.
- lora_url
- flow_shift
- 9
- frame_rate
- 20
- num_frames
- 49
- force_offload
- lora_strength
- 1
- guidance_scale
- 6
- denoise_strength
- 1
{ "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient blue background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 }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 lucataco/hunyuan-heygen-woman using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b", { input: { crf: 19, steps: 30, width: 960, height: 544, prompt: "HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient blue background, appearing calm and composed, possibly in a casual setting or an interview scenario.", lora_url: "", flow_shift: 9, frame_rate: 20, num_frames: 49, force_offload: true, lora_strength: 1, guidance_scale: 6, denoise_strength: 1 } } ); // 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 lucataco/hunyuan-heygen-woman using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b", input={ "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient blue background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": True, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run lucataco/hunyuan-heygen-woman 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": "lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b", "input": { "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient blue background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 } }' \ 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/lucataco/hunyuan-heygen-woman@sha256:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b \ -i 'crf=19' \ -i 'steps=30' \ -i 'width=960' \ -i 'height=544' \ -i 'prompt="HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient blue background, appearing calm and composed, possibly in a casual setting or an interview scenario."' \ -i 'lora_url=""' \ -i 'flow_shift=9' \ -i 'frame_rate=20' \ -i 'num_frames=49' \ -i 'force_offload=true' \ -i 'lora_strength=1' \ -i 'guidance_scale=6' \ -i 'denoise_strength=1'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/lucataco/hunyuan-heygen-woman@sha256:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37bcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient blue background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2025-01-12T19:30:07.227524Z", "created_at": "2025-01-12T19:26:57.187000Z", "data_removed": false, "error": null, "id": "rjwtazpgmdrme0cmbfxtg1sm08", "input": { "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient blue background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 }, "logs": "Random seed set to: 4268352253\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\n[ComfyUI] Input (height, width, video_length) = (544, 960, 49)\nExecuting node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler\n[ComfyUI] Sampling 49 frames in 13 latents at 960x544 with 30 inference steps\n[ComfyUI]\n[ComfyUI] 0%| | 0/30 [00:00<?, ?it/s]\n[ComfyUI] 3%|▎ | 1/30 [00:04<01:56, 4.00s/it]\n[ComfyUI] 7%|▋ | 2/30 [00:09<02:17, 4.91s/it]\n[ComfyUI] 10%|█ | 3/30 [00:15<02:20, 5.20s/it]\n[ComfyUI] 13%|█▎ | 4/30 [00:20<02:18, 5.32s/it]\n[ComfyUI] 17%|█▋ | 5/30 [00:26<02:14, 5.39s/it]\n[ComfyUI] 20%|██ | 6/30 [00:31<02:10, 5.44s/it]\n[ComfyUI] 23%|██▎ | 7/30 [00:37<02:05, 5.46s/it]\n[ComfyUI] 27%|██▋ | 8/30 [00:42<02:00, 5.48s/it]\n[ComfyUI] 30%|███ | 9/30 [00:48<01:55, 5.50s/it]\n[ComfyUI] 33%|███▎ | 10/30 [00:53<01:50, 5.50s/it]\n[ComfyUI] 37%|███▋ | 11/30 [00:59<01:44, 5.51s/it]\n[ComfyUI] 40%|████ | 12/30 [01:04<01:39, 5.51s/it]\n[ComfyUI] 43%|████▎ | 13/30 [01:10<01:33, 5.52s/it]\n[ComfyUI] 47%|████▋ | 14/30 [01:15<01:28, 5.52s/it]\n[ComfyUI] 50%|█████ | 15/30 [01:21<01:22, 5.52s/it]\n[ComfyUI] 53%|█████▎ | 16/30 [01:26<01:17, 5.52s/it]\n[ComfyUI] 57%|█████▋ | 17/30 [01:32<01:11, 5.52s/it]\n[ComfyUI] 60%|██████ | 18/30 [01:37<01:06, 5.52s/it]\n[ComfyUI] 63%|██████▎ | 19/30 [01:43<01:00, 5.52s/it]\n[ComfyUI] 67%|██████▋ | 20/30 [01:48<00:55, 5.52s/it]\n[ComfyUI] 70%|███████ | 21/30 [01:54<00:49, 5.52s/it]\n[ComfyUI] 73%|███████▎ | 22/30 [02:00<00:44, 5.52s/it]\n[ComfyUI] 77%|███████▋ | 23/30 [02:05<00:38, 5.52s/it]\n[ComfyUI] 80%|████████ | 24/30 [02:11<00:33, 5.52s/it]\n[ComfyUI] 83%|████████▎ | 25/30 [02:16<00:27, 5.52s/it]\n[ComfyUI] 87%|████████▋ | 26/30 [02:22<00:22, 5.52s/it]\n[ComfyUI] 90%|█████████ | 27/30 [02:27<00:16, 5.52s/it]\n[ComfyUI] 93%|█████████▎| 28/30 [02:33<00:11, 5.52s/it]\n[ComfyUI] 97%|█████████▋| 29/30 [02:38<00:05, 5.52s/it]\n[ComfyUI] 100%|██████████| 30/30 [02:44<00:00, 5.52s/it]\n[ComfyUI] 100%|██████████| 30/30 [02:44<00:00, 5.47s/it]\n[ComfyUI] Allocated memory: memory=12.301 GB\n[ComfyUI] Max allocated memory: max_memory=18.380 GB\n[ComfyUI] Max reserved memory: max_reserved=21.719 GB\nExecuting node 5, title: HunyuanVideo Decode, class type: HyVideoDecode\n[ComfyUI]\n[ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:01<00:02, 1.49s/it]\n[ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:03<00:01, 1.62s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.40s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.45s/it]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Blending tiles: 33%|███▎ | 1/3 [00:00<00:00, 7.37it/s]\nExecuting node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine\n[ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 17.31it/s]\n[ComfyUI] Prompt executed in 178.28 seconds\noutputs: {'34': {'gifs': [{'filename': 'HunyuanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 20.0, 'workflow': 'HunyuanVideo_00001.png', 'fullpath': '/tmp/outputs/HunyuanVideo_00001.mp4'}]}}\n====================================\nHunyuanVideo_00001.png\nHunyuanVideo_00001.mp4", "metrics": { "predict_time": 190.032328931, "total_time": 190.040524 }, "output": "https://replicate.delivery/xezq/w83oRelF1x1DTS0oS0ftqQKrpUlM3QC48weJkW8HJuIfjyRQB/HunyuanVideo_00001.mp4", "started_at": "2025-01-12T19:26:57.195195Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-r2zkbpj6uibomgscucgl57iixpgx7bo57igrnputzyivegfbchia", "get": "https://api.replicate.com/v1/predictions/rjwtazpgmdrme0cmbfxtg1sm08", "cancel": "https://api.replicate.com/v1/predictions/rjwtazpgmdrme0cmbfxtg1sm08/cancel" }, "version": "ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b" }Generated inRandom seed set to: 4268352253 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 [ComfyUI] Input (height, width, video_length) = (544, 960, 49) Executing node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler [ComfyUI] Sampling 49 frames in 13 latents at 960x544 with 30 inference steps [ComfyUI] [ComfyUI] 0%| | 0/30 [00:00<?, ?it/s] [ComfyUI] 3%|▎ | 1/30 [00:04<01:56, 4.00s/it] [ComfyUI] 7%|▋ | 2/30 [00:09<02:17, 4.91s/it] [ComfyUI] 10%|█ | 3/30 [00:15<02:20, 5.20s/it] [ComfyUI] 13%|█▎ | 4/30 [00:20<02:18, 5.32s/it] [ComfyUI] 17%|█▋ | 5/30 [00:26<02:14, 5.39s/it] [ComfyUI] 20%|██ | 6/30 [00:31<02:10, 5.44s/it] [ComfyUI] 23%|██▎ | 7/30 [00:37<02:05, 5.46s/it] [ComfyUI] 27%|██▋ | 8/30 [00:42<02:00, 5.48s/it] [ComfyUI] 30%|███ | 9/30 [00:48<01:55, 5.50s/it] [ComfyUI] 33%|███▎ | 10/30 [00:53<01:50, 5.50s/it] [ComfyUI] 37%|███▋ | 11/30 [00:59<01:44, 5.51s/it] [ComfyUI] 40%|████ | 12/30 [01:04<01:39, 5.51s/it] [ComfyUI] 43%|████▎ | 13/30 [01:10<01:33, 5.52s/it] [ComfyUI] 47%|████▋ | 14/30 [01:15<01:28, 5.52s/it] [ComfyUI] 50%|█████ | 15/30 [01:21<01:22, 5.52s/it] [ComfyUI] 53%|█████▎ | 16/30 [01:26<01:17, 5.52s/it] [ComfyUI] 57%|█████▋ | 17/30 [01:32<01:11, 5.52s/it] [ComfyUI] 60%|██████ | 18/30 [01:37<01:06, 5.52s/it] [ComfyUI] 63%|██████▎ | 19/30 [01:43<01:00, 5.52s/it] [ComfyUI] 67%|██████▋ | 20/30 [01:48<00:55, 5.52s/it] [ComfyUI] 70%|███████ | 21/30 [01:54<00:49, 5.52s/it] [ComfyUI] 73%|███████▎ | 22/30 [02:00<00:44, 5.52s/it] [ComfyUI] 77%|███████▋ | 23/30 [02:05<00:38, 5.52s/it] [ComfyUI] 80%|████████ | 24/30 [02:11<00:33, 5.52s/it] [ComfyUI] 83%|████████▎ | 25/30 [02:16<00:27, 5.52s/it] [ComfyUI] 87%|████████▋ | 26/30 [02:22<00:22, 5.52s/it] [ComfyUI] 90%|█████████ | 27/30 [02:27<00:16, 5.52s/it] [ComfyUI] 93%|█████████▎| 28/30 [02:33<00:11, 5.52s/it] [ComfyUI] 97%|█████████▋| 29/30 [02:38<00:05, 5.52s/it] [ComfyUI] 100%|██████████| 30/30 [02:44<00:00, 5.52s/it] [ComfyUI] 100%|██████████| 30/30 [02:44<00:00, 5.47s/it] [ComfyUI] Allocated memory: memory=12.301 GB [ComfyUI] Max allocated memory: max_memory=18.380 GB [ComfyUI] Max reserved memory: max_reserved=21.719 GB Executing node 5, title: HunyuanVideo Decode, class type: HyVideoDecode [ComfyUI] [ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s] [ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:01<00:02, 1.49s/it] [ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:03<00:01, 1.62s/it] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.40s/it] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.45s/it] [ComfyUI] [ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s] [ComfyUI] Blending tiles: 33%|███▎ | 1/3 [00:00<00:00, 7.37it/s] Executing node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine [ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 17.31it/s] [ComfyUI] Prompt executed in 178.28 seconds outputs: {'34': {'gifs': [{'filename': 'HunyuanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 20.0, 'workflow': 'HunyuanVideo_00001.png', 'fullpath': '/tmp/outputs/HunyuanVideo_00001.mp4'}]}} ==================================== HunyuanVideo_00001.png HunyuanVideo_00001.mp4Prediction
lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37bID0dh7qapz81rm80cmbg18519yd4StatusSucceededSourceWebHardwareH100Total durationCreatedInput
- crf
- 19
- steps
- 30
- width
- 960
- height
- 544
- prompt
- HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient orange background, appearing calm and composed, possibly in a casual setting or an interview scenario.
- lora_url
- flow_shift
- 9
- frame_rate
- 20
- num_frames
- 49
- force_offload
- lora_strength
- 1
- guidance_scale
- 6
- denoise_strength
- 1
{ "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient orange background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 }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 lucataco/hunyuan-heygen-woman using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b", { input: { crf: 19, steps: 30, width: 960, height: 544, prompt: "HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient orange background, appearing calm and composed, possibly in a casual setting or an interview scenario.", lora_url: "", flow_shift: 9, frame_rate: 20, num_frames: 49, force_offload: true, lora_strength: 1, guidance_scale: 6, denoise_strength: 1 } } ); // 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 lucataco/hunyuan-heygen-woman using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b", input={ "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient orange background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": True, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run lucataco/hunyuan-heygen-woman 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": "lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b", "input": { "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient orange background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 } }' \ 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/lucataco/hunyuan-heygen-woman@sha256:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b \ -i 'crf=19' \ -i 'steps=30' \ -i 'width=960' \ -i 'height=544' \ -i 'prompt="HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient orange background, appearing calm and composed, possibly in a casual setting or an interview scenario."' \ -i 'lora_url=""' \ -i 'flow_shift=9' \ -i 'frame_rate=20' \ -i 'num_frames=49' \ -i 'force_offload=true' \ -i 'lora_strength=1' \ -i 'guidance_scale=6' \ -i 'denoise_strength=1'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/lucataco/hunyuan-heygen-woman@sha256:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37bcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient orange background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2025-01-12T19:38:25.062222Z", "created_at": "2025-01-12T19:34:39.680000Z", "data_removed": false, "error": null, "id": "0dh7qapz81rm80cmbg18519yd4", "input": { "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient orange background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 }, "logs": "Random seed set to: 912449032\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 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<00:01, 1.58it/s]\n[ComfyUI] Loading checkpoint shards: 50%|█████ | 2/4 [00:01<00:01, 1.61it/s]\n[ComfyUI] Loading checkpoint shards: 75%|███████▌ | 3/4 [00:01<00:00, 1.64it/s]\n[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00, 2.39it/s]\n[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00, 2.04it/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: 48\n[ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 50\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] Using accelerate to load and assign model weights to device...\n[ComfyUI] Loading LoRA: lora_comfyui with strength: 1.0\n[ComfyUI] Requested to load HyVideoModel\n[ComfyUI] Loading 1 new model\n[ComfyUI] loaded completely 0.0 12555.953247070312 True\n[ComfyUI] Input (height, width, video_length) = (544, 960, 49)\nExecuting node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler\n[ComfyUI] Sampling 49 frames in 13 latents at 960x544 with 30 inference steps\n[ComfyUI] Scheduler config: FrozenDict([('num_train_timesteps', 1000), ('shift', 9.0), ('reverse', True), ('solver', 'euler'), ('n_tokens', None), ('_use_default_values', ['num_train_timesteps', 'n_tokens'])])\n[ComfyUI]\n[ComfyUI] 0%| | 0/30 [00:00<?, ?it/s]\n[ComfyUI] 3%|▎ | 1/30 [00:04<01:59, 4.11s/it]\n[ComfyUI] 7%|▋ | 2/30 [00:09<02:18, 4.94s/it]\n[ComfyUI] 10%|█ | 3/30 [00:15<02:20, 5.21s/it]\n[ComfyUI] 13%|█▎ | 4/30 [00:20<02:18, 5.32s/it]\n[ComfyUI] 17%|█▋ | 5/30 [00:26<02:14, 5.39s/it]\n[ComfyUI] 20%|██ | 6/30 [00:31<02:10, 5.43s/it]\n[ComfyUI] 23%|██▎ | 7/30 [00:37<02:05, 5.46s/it]\n[ComfyUI] 27%|██▋ | 8/30 [00:42<02:00, 5.47s/it]\n[ComfyUI] 30%|███ | 9/30 [00:48<01:55, 5.49s/it]\n[ComfyUI] 33%|███▎ | 10/30 [00:53<01:49, 5.49s/it]\n[ComfyUI] 37%|███▋ | 11/30 [00:59<01:44, 5.50s/it]\n[ComfyUI] 40%|████ | 12/30 [01:04<01:39, 5.50s/it]\n[ComfyUI] 43%|████▎ | 13/30 [01:10<01:33, 5.51s/it]\n[ComfyUI] 47%|████▋ | 14/30 [01:15<01:28, 5.50s/it]\n[ComfyUI] 50%|█████ | 15/30 [01:21<01:22, 5.51s/it]\n[ComfyUI] 53%|█████▎ | 16/30 [01:26<01:17, 5.50s/it]\n[ComfyUI] 57%|█████▋ | 17/30 [01:32<01:11, 5.50s/it]\n[ComfyUI] 60%|██████ | 18/30 [01:37<01:06, 5.50s/it]\n[ComfyUI] 63%|██████▎ | 19/30 [01:43<01:00, 5.50s/it]\n[ComfyUI] 67%|██████▋ | 20/30 [01:48<00:55, 5.50s/it]\n[ComfyUI] 70%|███████ | 21/30 [01:54<00:49, 5.50s/it]\n[ComfyUI] 73%|███████▎ | 22/30 [01:59<00:44, 5.50s/it]\n[ComfyUI] 77%|███████▋ | 23/30 [02:05<00:38, 5.50s/it]\n[ComfyUI] 80%|████████ | 24/30 [02:10<00:33, 5.51s/it]\n[ComfyUI] 83%|████████▎ | 25/30 [02:16<00:27, 5.51s/it]\n[ComfyUI] 87%|████████▋ | 26/30 [02:21<00:22, 5.51s/it]\n[ComfyUI] 90%|█████████ | 27/30 [02:27<00:16, 5.51s/it]\n[ComfyUI] 93%|█████████▎| 28/30 [02:32<00:11, 5.51s/it]\n[ComfyUI] 97%|█████████▋| 29/30 [02:38<00:05, 5.51s/it]\n[ComfyUI] 100%|██████████| 30/30 [02:43<00:00, 5.51s/it]\n[ComfyUI] 100%|██████████| 30/30 [02:43<00:00, 5.46s/it]\n[ComfyUI] Allocated memory: memory=12.760 GB\n[ComfyUI] Max allocated memory: max_memory=18.839 GB\n[ComfyUI] Max reserved memory: max_reserved=20.719 GB\nExecuting node 5, title: HunyuanVideo Decode, class type: HyVideoDecode\n[ComfyUI]\n[ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:01<00:03, 1.60s/it]\n[ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:03<00:01, 1.65s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.42s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.48s/it]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Blending tiles: 33%|███▎ | 1/3 [00:00<00:00, 7.82it/s]\nExecuting node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine\n[ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 18.19it/s]\n[ComfyUI] Prompt executed in 200.32 seconds\noutputs: {'34': {'gifs': [{'filename': 'HunyuanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 20.0, 'workflow': 'HunyuanVideo_00001.png', 'fullpath': '/tmp/outputs/HunyuanVideo_00001.mp4'}]}}\n====================================\nHunyuanVideo_00001.png\nHunyuanVideo_00001.mp4", "metrics": { "predict_time": 203.342439949, "total_time": 225.382222 }, "output": "https://replicate.delivery/xezq/mkjkOkYLOkq6DN0KIl9quRB5cLe1BhLzui3AtNLSZ4uYYOCKA/HunyuanVideo_00001.mp4", "started_at": "2025-01-12T19:35:01.719783Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-xcrw3jnkc7qdbhjv2esvvrfql4fvvb2hnufo25mz5ylvdyr7kjva", "get": "https://api.replicate.com/v1/predictions/0dh7qapz81rm80cmbg18519yd4", "cancel": "https://api.replicate.com/v1/predictions/0dh7qapz81rm80cmbg18519yd4/cancel" }, "version": "ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b" }Generated inRandom seed set to: 912449032 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 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<00:01, 1.58it/s] [ComfyUI] Loading checkpoint shards: 50%|█████ | 2/4 [00:01<00:01, 1.61it/s] [ComfyUI] Loading checkpoint shards: 75%|███████▌ | 3/4 [00:01<00:00, 1.64it/s] [ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00, 2.39it/s] [ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00, 2.04it/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: 48 [ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 50 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] Using accelerate to load and assign model weights to device... [ComfyUI] Loading LoRA: lora_comfyui with strength: 1.0 [ComfyUI] Requested to load HyVideoModel [ComfyUI] Loading 1 new model [ComfyUI] loaded completely 0.0 12555.953247070312 True [ComfyUI] Input (height, width, video_length) = (544, 960, 49) Executing node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler [ComfyUI] Sampling 49 frames in 13 latents at 960x544 with 30 inference steps [ComfyUI] Scheduler config: FrozenDict([('num_train_timesteps', 1000), ('shift', 9.0), ('reverse', True), ('solver', 'euler'), ('n_tokens', None), ('_use_default_values', ['num_train_timesteps', 'n_tokens'])]) [ComfyUI] [ComfyUI] 0%| | 0/30 [00:00<?, ?it/s] [ComfyUI] 3%|▎ | 1/30 [00:04<01:59, 4.11s/it] [ComfyUI] 7%|▋ | 2/30 [00:09<02:18, 4.94s/it] [ComfyUI] 10%|█ | 3/30 [00:15<02:20, 5.21s/it] [ComfyUI] 13%|█▎ | 4/30 [00:20<02:18, 5.32s/it] [ComfyUI] 17%|█▋ | 5/30 [00:26<02:14, 5.39s/it] [ComfyUI] 20%|██ | 6/30 [00:31<02:10, 5.43s/it] [ComfyUI] 23%|██▎ | 7/30 [00:37<02:05, 5.46s/it] [ComfyUI] 27%|██▋ | 8/30 [00:42<02:00, 5.47s/it] [ComfyUI] 30%|███ | 9/30 [00:48<01:55, 5.49s/it] [ComfyUI] 33%|███▎ | 10/30 [00:53<01:49, 5.49s/it] [ComfyUI] 37%|███▋ | 11/30 [00:59<01:44, 5.50s/it] [ComfyUI] 40%|████ | 12/30 [01:04<01:39, 5.50s/it] [ComfyUI] 43%|████▎ | 13/30 [01:10<01:33, 5.51s/it] [ComfyUI] 47%|████▋ | 14/30 [01:15<01:28, 5.50s/it] [ComfyUI] 50%|█████ | 15/30 [01:21<01:22, 5.51s/it] [ComfyUI] 53%|█████▎ | 16/30 [01:26<01:17, 5.50s/it] [ComfyUI] 57%|█████▋ | 17/30 [01:32<01:11, 5.50s/it] [ComfyUI] 60%|██████ | 18/30 [01:37<01:06, 5.50s/it] [ComfyUI] 63%|██████▎ | 19/30 [01:43<01:00, 5.50s/it] [ComfyUI] 67%|██████▋ | 20/30 [01:48<00:55, 5.50s/it] [ComfyUI] 70%|███████ | 21/30 [01:54<00:49, 5.50s/it] [ComfyUI] 73%|███████▎ | 22/30 [01:59<00:44, 5.50s/it] [ComfyUI] 77%|███████▋ | 23/30 [02:05<00:38, 5.50s/it] [ComfyUI] 80%|████████ | 24/30 [02:10<00:33, 5.51s/it] [ComfyUI] 83%|████████▎ | 25/30 [02:16<00:27, 5.51s/it] [ComfyUI] 87%|████████▋ | 26/30 [02:21<00:22, 5.51s/it] [ComfyUI] 90%|█████████ | 27/30 [02:27<00:16, 5.51s/it] [ComfyUI] 93%|█████████▎| 28/30 [02:32<00:11, 5.51s/it] [ComfyUI] 97%|█████████▋| 29/30 [02:38<00:05, 5.51s/it] [ComfyUI] 100%|██████████| 30/30 [02:43<00:00, 5.51s/it] [ComfyUI] 100%|██████████| 30/30 [02:43<00:00, 5.46s/it] [ComfyUI] Allocated memory: memory=12.760 GB [ComfyUI] Max allocated memory: max_memory=18.839 GB [ComfyUI] Max reserved memory: max_reserved=20.719 GB Executing node 5, title: HunyuanVideo Decode, class type: HyVideoDecode [ComfyUI] [ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s] [ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:01<00:03, 1.60s/it] [ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:03<00:01, 1.65s/it] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.42s/it] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.48s/it] [ComfyUI] [ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s] [ComfyUI] Blending tiles: 33%|███▎ | 1/3 [00:00<00:00, 7.82it/s] Executing node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine [ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 18.19it/s] [ComfyUI] Prompt executed in 200.32 seconds outputs: {'34': {'gifs': [{'filename': 'HunyuanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 20.0, 'workflow': 'HunyuanVideo_00001.png', 'fullpath': '/tmp/outputs/HunyuanVideo_00001.mp4'}]}} ==================================== HunyuanVideo_00001.png HunyuanVideo_00001.mp4Prediction
lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37bID1w7w09verhrma0cmbg7r1m2db4StatusSucceededSourceWebHardwareH100Total durationCreatedInput
- crf
- 19
- steps
- 30
- width
- 960
- height
- 544
- prompt
- HGW woman with long, dark hair, tied back neatly, wearing a suit. She stands against a simple, gradient gray background, appearing calm and composed, possibly in a casual setting or an interview scenario.
- lora_url
- flow_shift
- 9
- frame_rate
- 20
- num_frames
- 49
- force_offload
- lora_strength
- 1
- guidance_scale
- 6
- denoise_strength
- 1
{ "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a suit. She stands against a simple, gradient gray background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 }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 lucataco/hunyuan-heygen-woman using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b", { input: { crf: 19, steps: 30, width: 960, height: 544, prompt: "HGW woman with long, dark hair, tied back neatly, wearing a suit. She stands against a simple, gradient gray background, appearing calm and composed, possibly in a casual setting or an interview scenario.", lora_url: "", flow_shift: 9, frame_rate: 20, num_frames: 49, force_offload: true, lora_strength: 1, guidance_scale: 6, denoise_strength: 1 } } ); // 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 lucataco/hunyuan-heygen-woman using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b", input={ "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a suit. She stands against a simple, gradient gray background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": True, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run lucataco/hunyuan-heygen-woman 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": "lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b", "input": { "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a suit. She stands against a simple, gradient gray background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 } }' \ 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/lucataco/hunyuan-heygen-woman@sha256:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b \ -i 'crf=19' \ -i 'steps=30' \ -i 'width=960' \ -i 'height=544' \ -i 'prompt="HGW woman with long, dark hair, tied back neatly, wearing a suit. She stands against a simple, gradient gray background, appearing calm and composed, possibly in a casual setting or an interview scenario."' \ -i 'lora_url=""' \ -i 'flow_shift=9' \ -i 'frame_rate=20' \ -i 'num_frames=49' \ -i 'force_offload=true' \ -i 'lora_strength=1' \ -i 'guidance_scale=6' \ -i 'denoise_strength=1'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/lucataco/hunyuan-heygen-woman@sha256:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37bcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a suit. She stands against a simple, gradient gray background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2025-01-12T19:52:26.230526Z", "created_at": "2025-01-12T19:48:22.852000Z", "data_removed": false, "error": null, "id": "1w7w09verhrma0cmbg7r1m2db4", "input": { "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a suit. She stands against a simple, gradient gray background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 }, "logs": "Random seed set to: 27947747\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 7, title: HunyuanVideo VAE Loader, class type: HyVideoVAELoader\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<00:01, 1.56it/s]\n[ComfyUI] Loading checkpoint shards: 50%|█████ | 2/4 [00:01<00:01, 1.53it/s]\n[ComfyUI] Loading checkpoint shards: 75%|███████▌ | 3/4 [00:01<00:00, 1.56it/s]\n[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 2.34it/s]\n[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 1.97it/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: 43\n[ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 45\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] Using accelerate to load and assign model weights to device...\n[ComfyUI] Loading LoRA: lora_comfyui with strength: 1.0\n[ComfyUI] Requested to load HyVideoModel\n[ComfyUI] Loading 1 new model\n[ComfyUI] loaded completely 0.0 12555.953247070312 True\n[ComfyUI] Input (height, width, video_length) = (544, 960, 49)\nExecuting node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler\n[ComfyUI] Sampling 49 frames in 13 latents at 960x544 with 30 inference steps\n[ComfyUI] Scheduler config: FrozenDict([('num_train_timesteps', 1000), ('shift', 9.0), ('reverse', True), ('solver', 'euler'), ('n_tokens', None), ('_use_default_values', ['num_train_timesteps', 'n_tokens'])])[ComfyUI]\n[ComfyUI] 0%| | 0/30 [00:00<?, ?it/s]\n[ComfyUI] 3%|▎ | 1/30 [00:04<01:59, 4.11s/it]\n[ComfyUI] 7%|▋ | 2/30 [00:09<02:18, 4.94s/it]\n[ComfyUI] 10%|█ | 3/30 [00:15<02:20, 5.20s/it]\n[ComfyUI] 13%|█▎ | 4/30 [00:20<02:18, 5.33s/it]\n[ComfyUI] 17%|█▋ | 5/30 [00:26<02:14, 5.40s/it]\n[ComfyUI] 20%|██ | 6/30 [00:31<02:10, 5.44s/it]\n[ComfyUI] 23%|██▎ | 7/30 [00:37<02:05, 5.46s/it]\n[ComfyUI] 27%|██▋ | 8/30 [00:42<02:00, 5.48s/it]\n[ComfyUI] 30%|███ | 9/30 [00:48<01:55, 5.49s/it]\n[ComfyUI] 33%|███▎ | 10/30 [00:53<01:50, 5.50s/it]\n[ComfyUI] 37%|███▋ | 11/30 [00:59<01:44, 5.51s/it]\n[ComfyUI] 40%|████ | 12/30 [01:04<01:39, 5.51s/it]\n[ComfyUI] 43%|████▎ | 13/30 [01:10<01:33, 5.51s/it]\n[ComfyUI] 47%|████▋ | 14/30 [01:15<01:28, 5.52s/it]\n[ComfyUI] 50%|█████ | 15/30 [01:21<01:22, 5.52s/it]\n[ComfyUI] 53%|█████▎ | 16/30 [01:26<01:17, 5.52s/it]\n[ComfyUI] 57%|█████▋ | 17/30 [01:32<01:11, 5.52s/it]\n[ComfyUI] 60%|██████ | 18/30 [01:37<01:06, 5.52s/it]\n[ComfyUI] 63%|██████▎ | 19/30 [01:43<01:00, 5.52s/it]\n[ComfyUI] 67%|██████▋ | 20/30 [01:48<00:55, 5.52s/it]\n[ComfyUI] 70%|███████ | 21/30 [01:54<00:49, 5.52s/it]\n[ComfyUI] 73%|███████▎ | 22/30 [02:00<00:44, 5.52s/it]\n[ComfyUI] 77%|███████▋ | 23/30 [02:05<00:38, 5.52s/it]\n[ComfyUI] 80%|████████ | 24/30 [02:11<00:33, 5.52s/it]\n[ComfyUI] 83%|████████▎ | 25/30 [02:16<00:27, 5.52s/it]\n[ComfyUI] 87%|████████▋ | 26/30 [02:22<00:22, 5.52s/it]\n[ComfyUI] 90%|█████████ | 27/30 [02:27<00:16, 5.52s/it]\n[ComfyUI] 93%|█████████▎| 28/30 [02:33<00:11, 5.52s/it]\n[ComfyUI] 97%|█████████▋| 29/30 [02:38<00:05, 5.52s/it]\n[ComfyUI] 100%|██████████| 30/30 [02:44<00:00, 5.52s/it]\n[ComfyUI] 100%|██████████| 30/30 [02:44<00:00, 5.47s/it]\n[ComfyUI] Allocated memory: memory=12.760 GB\n[ComfyUI] Max allocated memory: max_memory=18.839 GB\n[ComfyUI] Max reserved memory: max_reserved=20.719 GB\nExecuting node 5, title: HunyuanVideo Decode, class type: HyVideoDecode\n[ComfyUI]\n[ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:01<00:03, 1.56s/it]\n[ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:03<00:01, 1.65s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.42s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.47s/it]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Blending tiles: 33%|███▎ | 1/3 [00:00<00:00, 7.79it/s]\nExecuting node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine\n[ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 18.04it/s]\n[ComfyUI] Prompt executed in 201.20 seconds\noutputs: {'34': {'gifs': [{'filename': 'HunyuanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 20.0, 'workflow': 'HunyuanVideo_00001.png', 'fullpath': '/tmp/outputs/HunyuanVideo_00001.mp4'}]}}\n====================================\nHunyuanVideo_00001.png\nHunyuanVideo_00001.mp4", "metrics": { "predict_time": 213.194710064, "total_time": 243.378526 }, "output": "https://replicate.delivery/xezq/4GUVidj2HUYtKJgtapHQn3qmcScLuSqo6KNPzaP2QaseecEUA/HunyuanVideo_00001.mp4", "started_at": "2025-01-12T19:48:53.035816Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-xnzudlpt55pcfycr2lmxcgtjg7rdrbijwnedooe4bvg5fgsnnhqq", "get": "https://api.replicate.com/v1/predictions/1w7w09verhrma0cmbg7r1m2db4", "cancel": "https://api.replicate.com/v1/predictions/1w7w09verhrma0cmbg7r1m2db4/cancel" }, "version": "ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b" }Generated inRandom seed set to: 27947747 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 7, title: HunyuanVideo VAE Loader, class type: HyVideoVAELoader 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<00:01, 1.56it/s] [ComfyUI] Loading checkpoint shards: 50%|█████ | 2/4 [00:01<00:01, 1.53it/s] [ComfyUI] Loading checkpoint shards: 75%|███████▌ | 3/4 [00:01<00:00, 1.56it/s] [ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 2.34it/s] [ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 1.97it/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: 43 [ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 45 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] Using accelerate to load and assign model weights to device... [ComfyUI] Loading LoRA: lora_comfyui with strength: 1.0 [ComfyUI] Requested to load HyVideoModel [ComfyUI] Loading 1 new model [ComfyUI] loaded completely 0.0 12555.953247070312 True [ComfyUI] Input (height, width, video_length) = (544, 960, 49) Executing node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler [ComfyUI] Sampling 49 frames in 13 latents at 960x544 with 30 inference steps [ComfyUI] Scheduler config: FrozenDict([('num_train_timesteps', 1000), ('shift', 9.0), ('reverse', True), ('solver', 'euler'), ('n_tokens', None), ('_use_default_values', ['num_train_timesteps', 'n_tokens'])])[ComfyUI] [ComfyUI] 0%| | 0/30 [00:00<?, ?it/s] [ComfyUI] 3%|▎ | 1/30 [00:04<01:59, 4.11s/it] [ComfyUI] 7%|▋ | 2/30 [00:09<02:18, 4.94s/it] [ComfyUI] 10%|█ | 3/30 [00:15<02:20, 5.20s/it] [ComfyUI] 13%|█▎ | 4/30 [00:20<02:18, 5.33s/it] [ComfyUI] 17%|█▋ | 5/30 [00:26<02:14, 5.40s/it] [ComfyUI] 20%|██ | 6/30 [00:31<02:10, 5.44s/it] [ComfyUI] 23%|██▎ | 7/30 [00:37<02:05, 5.46s/it] [ComfyUI] 27%|██▋ | 8/30 [00:42<02:00, 5.48s/it] [ComfyUI] 30%|███ | 9/30 [00:48<01:55, 5.49s/it] [ComfyUI] 33%|███▎ | 10/30 [00:53<01:50, 5.50s/it] [ComfyUI] 37%|███▋ | 11/30 [00:59<01:44, 5.51s/it] [ComfyUI] 40%|████ | 12/30 [01:04<01:39, 5.51s/it] [ComfyUI] 43%|████▎ | 13/30 [01:10<01:33, 5.51s/it] [ComfyUI] 47%|████▋ | 14/30 [01:15<01:28, 5.52s/it] [ComfyUI] 50%|█████ | 15/30 [01:21<01:22, 5.52s/it] [ComfyUI] 53%|█████▎ | 16/30 [01:26<01:17, 5.52s/it] [ComfyUI] 57%|█████▋ | 17/30 [01:32<01:11, 5.52s/it] [ComfyUI] 60%|██████ | 18/30 [01:37<01:06, 5.52s/it] [ComfyUI] 63%|██████▎ | 19/30 [01:43<01:00, 5.52s/it] [ComfyUI] 67%|██████▋ | 20/30 [01:48<00:55, 5.52s/it] [ComfyUI] 70%|███████ | 21/30 [01:54<00:49, 5.52s/it] [ComfyUI] 73%|███████▎ | 22/30 [02:00<00:44, 5.52s/it] [ComfyUI] 77%|███████▋ | 23/30 [02:05<00:38, 5.52s/it] [ComfyUI] 80%|████████ | 24/30 [02:11<00:33, 5.52s/it] [ComfyUI] 83%|████████▎ | 25/30 [02:16<00:27, 5.52s/it] [ComfyUI] 87%|████████▋ | 26/30 [02:22<00:22, 5.52s/it] [ComfyUI] 90%|█████████ | 27/30 [02:27<00:16, 5.52s/it] [ComfyUI] 93%|█████████▎| 28/30 [02:33<00:11, 5.52s/it] [ComfyUI] 97%|█████████▋| 29/30 [02:38<00:05, 5.52s/it] [ComfyUI] 100%|██████████| 30/30 [02:44<00:00, 5.52s/it] [ComfyUI] 100%|██████████| 30/30 [02:44<00:00, 5.47s/it] [ComfyUI] Allocated memory: memory=12.760 GB [ComfyUI] Max allocated memory: max_memory=18.839 GB [ComfyUI] Max reserved memory: max_reserved=20.719 GB Executing node 5, title: HunyuanVideo Decode, class type: HyVideoDecode [ComfyUI] [ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s] [ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:01<00:03, 1.56s/it] [ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:03<00:01, 1.65s/it] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.42s/it] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.47s/it] [ComfyUI] [ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s] [ComfyUI] Blending tiles: 33%|███▎ | 1/3 [00:00<00:00, 7.79it/s] Executing node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine [ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 18.04it/s] [ComfyUI] Prompt executed in 201.20 seconds outputs: {'34': {'gifs': [{'filename': 'HunyuanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 20.0, 'workflow': 'HunyuanVideo_00001.png', 'fullpath': '/tmp/outputs/HunyuanVideo_00001.mp4'}]}} ==================================== HunyuanVideo_00001.png HunyuanVideo_00001.mp4Prediction
lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37bIDhzkvr4a2qsrmc0cmbgn8f8yzhgStatusSucceededSourceWebHardwareH100Total durationCreatedInput
- crf
- 19
- steps
- 30
- width
- 960
- height
- 544
- prompt
- HGW woman with long, dark hair, tied back neatly, wearing a black dress. She stands against a simple, gradient white background, appearing calm and composed, possibly in a casual setting or an interview scenario.
- lora_url
- flow_shift
- 9
- frame_rate
- 20
- num_frames
- 49
- force_offload
- lora_strength
- 1
- guidance_scale
- 6
- denoise_strength
- 1
{ "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black dress. She stands against a simple, gradient white background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 }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 lucataco/hunyuan-heygen-woman using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b", { input: { crf: 19, steps: 30, width: 960, height: 544, prompt: "HGW woman with long, dark hair, tied back neatly, wearing a black dress. She stands against a simple, gradient white background, appearing calm and composed, possibly in a casual setting or an interview scenario.", lora_url: "", flow_shift: 9, frame_rate: 20, num_frames: 49, force_offload: true, lora_strength: 1, guidance_scale: 6, denoise_strength: 1 } } ); // 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 lucataco/hunyuan-heygen-woman using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b", input={ "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black dress. She stands against a simple, gradient white background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": True, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run lucataco/hunyuan-heygen-woman 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": "lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b", "input": { "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black dress. She stands against a simple, gradient white background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 } }' \ 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/lucataco/hunyuan-heygen-woman@sha256:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b \ -i 'crf=19' \ -i 'steps=30' \ -i 'width=960' \ -i 'height=544' \ -i 'prompt="HGW woman with long, dark hair, tied back neatly, wearing a black dress. She stands against a simple, gradient white background, appearing calm and composed, possibly in a casual setting or an interview scenario."' \ -i 'lora_url=""' \ -i 'flow_shift=9' \ -i 'frame_rate=20' \ -i 'num_frames=49' \ -i 'force_offload=true' \ -i 'lora_strength=1' \ -i 'guidance_scale=6' \ -i 'denoise_strength=1'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/lucataco/hunyuan-heygen-woman@sha256:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37bcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black dress. She stands against a simple, gradient white background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2025-01-12T20:21:41.524059Z", "created_at": "2025-01-12T20:17:41.054000Z", "data_removed": false, "error": null, "id": "hzkvr4a2qsrmc0cmbgn8f8yzhg", "input": { "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black dress. She stands against a simple, gradient white background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 }, "logs": "Random seed set to: 755716563\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 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<00:01, 1.74it/s]\n[ComfyUI] Loading checkpoint shards: 50%|█████ | 2/4 [00:01<00:01, 1.77it/s]\n[ComfyUI] Loading checkpoint shards: 75%|███████▌ | 3/4 [00:01<00:00, 1.79it/s]\n[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00, 2.24it/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: 44\n[ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 46\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] Using accelerate to load and assign model weights to device...\n[ComfyUI] Loading LoRA: lora_comfyui with strength: 1.0\n[ComfyUI] Requested to load HyVideoModel\n[ComfyUI] Loading 1 new model\n[ComfyUI] loaded completely 0.0 12555.953247070312 True\n[ComfyUI] Input (height, width, video_length) = (544, 960, 49)\nExecuting node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler\n[ComfyUI] Sampling 49 frames in 13 latents at 960x544 with 30 inference steps\n[ComfyUI] Scheduler config: FrozenDict([('num_train_timesteps', 1000), ('shift', 9.0), ('reverse', True), ('solver', 'euler'), ('n_tokens', None), ('_use_default_values', ['num_train_timesteps', 'n_tokens'])])\n[ComfyUI]\n[ComfyUI] 0%| | 0/30 [00:00<?, ?it/s]\n[ComfyUI] 3%|▎ | 1/30 [00:04<01:59, 4.11s/it]\n[ComfyUI] 7%|▋ | 2/30 [00:09<02:18, 4.93s/it]\n[ComfyUI] 10%|█ | 3/30 [00:15<02:20, 5.20s/it]\n[ComfyUI] 13%|█▎ | 4/30 [00:20<02:18, 5.33s/it]\n[ComfyUI] 17%|█▋ | 5/30 [00:26<02:14, 5.40s/it]\n[ComfyUI] 20%|██ | 6/30 [00:31<02:10, 5.44s/it]\n[ComfyUI] 23%|██▎ | 7/30 [00:37<02:05, 5.47s/it]\n[ComfyUI] 27%|██▋ | 8/30 [00:42<02:00, 5.49s/it]\n[ComfyUI] 30%|███ | 9/30 [00:48<01:55, 5.50s/it]\n[ComfyUI] 33%|███▎ | 10/30 [00:53<01:50, 5.51s/it]\n[ComfyUI] 37%|███▋ | 11/30 [00:59<01:44, 5.52s/it]\n[ComfyUI] 40%|████ | 12/30 [01:04<01:39, 5.52s/it]\n[ComfyUI] 43%|████▎ | 13/30 [01:10<01:33, 5.53s/it]\n[ComfyUI] 47%|████▋ | 14/30 [01:15<01:28, 5.53s/it]\n[ComfyUI] 50%|█████ | 15/30 [01:21<01:22, 5.53s/it]\n[ComfyUI] 53%|█████▎ | 16/30 [01:27<01:17, 5.53s/it]\n[ComfyUI] 57%|█████▋ | 17/30 [01:32<01:11, 5.52s/it]\n[ComfyUI] 60%|██████ | 18/30 [01:38<01:06, 5.52s/it]\n[ComfyUI] 63%|██████▎ | 19/30 [01:43<01:00, 5.52s/it]\n[ComfyUI] 67%|██████▋ | 20/30 [01:49<00:55, 5.53s/it]\n[ComfyUI] 70%|███████ | 21/30 [01:54<00:49, 5.53s/it]\n[ComfyUI] 73%|███████▎ | 22/30 [02:00<00:44, 5.53s/it]\n[ComfyUI] 77%|███████▋ | 23/30 [02:05<00:38, 5.52s/it]\n[ComfyUI] 80%|████████ | 24/30 [02:11<00:33, 5.53s/it]\n[ComfyUI] 83%|████████▎ | 25/30 [02:16<00:27, 5.52s/it]\n[ComfyUI] 87%|████████▋ | 26/30 [02:22<00:22, 5.52s/it]\n[ComfyUI] 90%|█████████ | 27/30 [02:27<00:16, 5.51s/it]\n[ComfyUI] 93%|█████████▎| 28/30 [02:33<00:11, 5.51s/it]\n[ComfyUI] 97%|█████████▋| 29/30 [02:38<00:05, 5.51s/it]\n[ComfyUI] 100%|██████████| 30/30 [02:44<00:00, 5.52s/it]\n[ComfyUI] 100%|██████████| 30/30 [02:44<00:00, 5.48s/it]\n[ComfyUI] Allocated memory: memory=12.760 GB\n[ComfyUI] Max allocated memory: max_memory=18.839 GB\n[ComfyUI] Max reserved memory: max_reserved=20.719 GB\nExecuting node 5, title: HunyuanVideo Decode, class type: HyVideoDecode\n[ComfyUI]\n[ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:01<00:03, 1.53s/it]\n[ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:03<00:01, 1.63s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.41s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.46s/it]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Blending tiles: 33%|███▎ | 1/3 [00:00<00:00, 7.75it/s]\nExecuting node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine\n[ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 18.00it/s]\n[ComfyUI] Prompt executed in 200.39 seconds\noutputs: {'34': {'gifs': [{'filename': 'HunyuanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 20.0, 'workflow': 'HunyuanVideo_00001.png', 'fullpath': '/tmp/outputs/HunyuanVideo_00001.mp4'}]}}\n====================================\nHunyuanVideo_00001.png\nHunyuanVideo_00001.mp4", "metrics": { "predict_time": 212.787943104, "total_time": 240.470059 }, "output": "https://replicate.delivery/xezq/wdBX9xxnhiqpK5D9wPxVgHWvusIvxuJQ9I7uBuUfKHsqsOCKA/HunyuanVideo_00001.mp4", "started_at": "2025-01-12T20:18:08.736116Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-dzc6mk7puvvyhek66h2iz7myjrxhbtyelxkynxj4dfpawcvevhda", "get": "https://api.replicate.com/v1/predictions/hzkvr4a2qsrmc0cmbgn8f8yzhg", "cancel": "https://api.replicate.com/v1/predictions/hzkvr4a2qsrmc0cmbgn8f8yzhg/cancel" }, "version": "ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b" }Generated inRandom seed set to: 755716563 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 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<00:01, 1.74it/s] [ComfyUI] Loading checkpoint shards: 50%|█████ | 2/4 [00:01<00:01, 1.77it/s] [ComfyUI] Loading checkpoint shards: 75%|███████▌ | 3/4 [00:01<00:00, 1.79it/s] [ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00, 2.24it/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: 44 [ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 46 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] Using accelerate to load and assign model weights to device... [ComfyUI] Loading LoRA: lora_comfyui with strength: 1.0 [ComfyUI] Requested to load HyVideoModel [ComfyUI] Loading 1 new model [ComfyUI] loaded completely 0.0 12555.953247070312 True [ComfyUI] Input (height, width, video_length) = (544, 960, 49) Executing node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler [ComfyUI] Sampling 49 frames in 13 latents at 960x544 with 30 inference steps [ComfyUI] Scheduler config: FrozenDict([('num_train_timesteps', 1000), ('shift', 9.0), ('reverse', True), ('solver', 'euler'), ('n_tokens', None), ('_use_default_values', ['num_train_timesteps', 'n_tokens'])]) [ComfyUI] [ComfyUI] 0%| | 0/30 [00:00<?, ?it/s] [ComfyUI] 3%|▎ | 1/30 [00:04<01:59, 4.11s/it] [ComfyUI] 7%|▋ | 2/30 [00:09<02:18, 4.93s/it] [ComfyUI] 10%|█ | 3/30 [00:15<02:20, 5.20s/it] [ComfyUI] 13%|█▎ | 4/30 [00:20<02:18, 5.33s/it] [ComfyUI] 17%|█▋ | 5/30 [00:26<02:14, 5.40s/it] [ComfyUI] 20%|██ | 6/30 [00:31<02:10, 5.44s/it] [ComfyUI] 23%|██▎ | 7/30 [00:37<02:05, 5.47s/it] [ComfyUI] 27%|██▋ | 8/30 [00:42<02:00, 5.49s/it] [ComfyUI] 30%|███ | 9/30 [00:48<01:55, 5.50s/it] [ComfyUI] 33%|███▎ | 10/30 [00:53<01:50, 5.51s/it] [ComfyUI] 37%|███▋ | 11/30 [00:59<01:44, 5.52s/it] [ComfyUI] 40%|████ | 12/30 [01:04<01:39, 5.52s/it] [ComfyUI] 43%|████▎ | 13/30 [01:10<01:33, 5.53s/it] [ComfyUI] 47%|████▋ | 14/30 [01:15<01:28, 5.53s/it] [ComfyUI] 50%|█████ | 15/30 [01:21<01:22, 5.53s/it] [ComfyUI] 53%|█████▎ | 16/30 [01:27<01:17, 5.53s/it] [ComfyUI] 57%|█████▋ | 17/30 [01:32<01:11, 5.52s/it] [ComfyUI] 60%|██████ | 18/30 [01:38<01:06, 5.52s/it] [ComfyUI] 63%|██████▎ | 19/30 [01:43<01:00, 5.52s/it] [ComfyUI] 67%|██████▋ | 20/30 [01:49<00:55, 5.53s/it] [ComfyUI] 70%|███████ | 21/30 [01:54<00:49, 5.53s/it] [ComfyUI] 73%|███████▎ | 22/30 [02:00<00:44, 5.53s/it] [ComfyUI] 77%|███████▋ | 23/30 [02:05<00:38, 5.52s/it] [ComfyUI] 80%|████████ | 24/30 [02:11<00:33, 5.53s/it] [ComfyUI] 83%|████████▎ | 25/30 [02:16<00:27, 5.52s/it] [ComfyUI] 87%|████████▋ | 26/30 [02:22<00:22, 5.52s/it] [ComfyUI] 90%|█████████ | 27/30 [02:27<00:16, 5.51s/it] [ComfyUI] 93%|█████████▎| 28/30 [02:33<00:11, 5.51s/it] [ComfyUI] 97%|█████████▋| 29/30 [02:38<00:05, 5.51s/it] [ComfyUI] 100%|██████████| 30/30 [02:44<00:00, 5.52s/it] [ComfyUI] 100%|██████████| 30/30 [02:44<00:00, 5.48s/it] [ComfyUI] Allocated memory: memory=12.760 GB [ComfyUI] Max allocated memory: max_memory=18.839 GB [ComfyUI] Max reserved memory: max_reserved=20.719 GB Executing node 5, title: HunyuanVideo Decode, class type: HyVideoDecode [ComfyUI] [ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s] [ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:01<00:03, 1.53s/it] [ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:03<00:01, 1.63s/it] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.41s/it] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.46s/it] [ComfyUI] [ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s] [ComfyUI] Blending tiles: 33%|███▎ | 1/3 [00:00<00:00, 7.75it/s] Executing node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine [ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 18.00it/s] [ComfyUI] Prompt executed in 200.39 seconds outputs: {'34': {'gifs': [{'filename': 'HunyuanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 20.0, 'workflow': 'HunyuanVideo_00001.png', 'fullpath': '/tmp/outputs/HunyuanVideo_00001.mp4'}]}} ==================================== HunyuanVideo_00001.png HunyuanVideo_00001.mp4Prediction
lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37bID3bqqjyj589rme0cmc34vejvpxrStatusSucceededSourceWebHardwareH100Total durationCreatedInput
- crf
- 19
- steps
- 30
- width
- 960
- height
- 544
- prompt
- HGW woman with long, dark hair, tied back neatly, wearing a purple shirt over a light top. She stands against a simple, cafe background, appearing calm and composed, possibly in a casual setting or an interview scenario.
- lora_url
- flow_shift
- 9
- frame_rate
- 20
- num_frames
- 49
- force_offload
- lora_strength
- 1
- guidance_scale
- 6
- denoise_strength
- 1
{ "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a purple shirt over a light top. She stands against a simple, cafe background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 }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 lucataco/hunyuan-heygen-woman using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b", { input: { crf: 19, steps: 30, width: 960, height: 544, prompt: "HGW woman with long, dark hair, tied back neatly, wearing a purple shirt over a light top. She stands against a simple, cafe background, appearing calm and composed, possibly in a casual setting or an interview scenario.", lora_url: "", flow_shift: 9, frame_rate: 20, num_frames: 49, force_offload: true, lora_strength: 1, guidance_scale: 6, denoise_strength: 1 } } ); // 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 lucataco/hunyuan-heygen-woman using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b", input={ "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a purple shirt over a light top. She stands against a simple, cafe background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": True, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run lucataco/hunyuan-heygen-woman 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": "lucataco/hunyuan-heygen-woman:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b", "input": { "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a purple shirt over a light top. She stands against a simple, cafe background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 } }' \ 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/lucataco/hunyuan-heygen-woman@sha256:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b \ -i 'crf=19' \ -i 'steps=30' \ -i 'width=960' \ -i 'height=544' \ -i 'prompt="HGW woman with long, dark hair, tied back neatly, wearing a purple shirt over a light top. She stands against a simple, cafe background, appearing calm and composed, possibly in a casual setting or an interview scenario."' \ -i 'lora_url=""' \ -i 'flow_shift=9' \ -i 'frame_rate=20' \ -i 'num_frames=49' \ -i 'force_offload=true' \ -i 'lora_strength=1' \ -i 'guidance_scale=6' \ -i 'denoise_strength=1'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/lucataco/hunyuan-heygen-woman@sha256:ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37bcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a purple shirt over a light top. She stands against a simple, cafe background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2025-01-13T17:53:54.577111Z", "created_at": "2025-01-13T17:49:50.786000Z", "data_removed": false, "error": null, "id": "3bqqjyj589rme0cmc34vejvpxr", "input": { "crf": 19, "steps": 30, "width": 960, "height": 544, "prompt": "HGW woman with long, dark hair, tied back neatly, wearing a purple shirt over a light top. She stands against a simple, cafe background, appearing calm and composed, possibly in a casual setting or an interview scenario.", "lora_url": "", "flow_shift": 9, "frame_rate": 20, "num_frames": 49, "force_offload": true, "lora_strength": 1, "guidance_scale": 6, "denoise_strength": 1 }, "logs": "Random seed set to: 1903901857\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\n[ComfyUI] Loading text encoder model (clipL) from: /src/ComfyUI/models/clip/clip-vit-large-patch14\nExecuting node 16, title: (Down)Load HunyuanVideo TextEncoder, class type: DownloadAndLoadHyVideoTextEncoder\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<00:01, 1.66it/s]\n[ComfyUI] Loading checkpoint shards: 50%|█████ | 2/4 [00:01<00:01, 1.71it/s]\n[ComfyUI] Loading checkpoint shards: 75%|███████▌ | 3/4 [00:01<00:00, 1.69it/s]\n[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00, 2.52it/s]\n[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00, 2.13it/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: 47\n[ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 49\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] Using accelerate to load and assign model weights to device...\n[ComfyUI] Loading LoRA: lora_comfyui with strength: 1.0\n[ComfyUI] Requested to load HyVideoModel\n[ComfyUI] Loading 1 new model\n[ComfyUI] loaded completely 0.0 12555.953247070312 True\n[ComfyUI] Input (height, width, video_length) = (544, 960, 49)\nExecuting node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler\n[ComfyUI] Sampling 49 frames in 13 latents at 960x544 with 30 inference steps\n[ComfyUI] Scheduler config: FrozenDict([('num_train_timesteps', 1000), ('shift', 9.0), ('reverse', True), ('solver', 'euler'), ('n_tokens', None), ('_use_default_values', ['num_train_timesteps', 'n_tokens'])])\n[ComfyUI] \n[ComfyUI] 0%| | 0/30 [00:00<?, ?it/s]\n[ComfyUI] 3%|▎ | 1/30 [00:04<01:59, 4.13s/it]\n[ComfyUI] 7%|▋ | 2/30 [00:09<02:18, 4.95s/it]\n[ComfyUI] 10%|█ | 3/30 [00:15<02:20, 5.20s/it]\n[ComfyUI] 13%|█▎ | 4/30 [00:20<02:18, 5.32s/it]\n[ComfyUI] 17%|█▋ | 5/30 [00:26<02:14, 5.39s/it]\n[ComfyUI] 20%|██ | 6/30 [00:31<02:10, 5.43s/it]\n[ComfyUI] 23%|██▎ | 7/30 [00:37<02:05, 5.46s/it]\n[ComfyUI] 27%|██▋ | 8/30 [00:42<02:00, 5.47s/it]\n[ComfyUI] 30%|███ | 9/30 [00:48<01:55, 5.48s/it]\n[ComfyUI] 33%|███▎ | 10/30 [00:53<01:49, 5.49s/it]\n[ComfyUI] 37%|███▋ | 11/30 [00:59<01:44, 5.50s/it]\n[ComfyUI] 40%|████ | 12/30 [01:04<01:39, 5.50s/it]\n[ComfyUI] 43%|████▎ | 13/30 [01:10<01:33, 5.50s/it]\n[ComfyUI] 47%|████▋ | 14/30 [01:15<01:28, 5.51s/it]\n[ComfyUI] 50%|█████ | 15/30 [01:21<01:22, 5.51s/it]\n[ComfyUI] 53%|█████▎ | 16/30 [01:26<01:17, 5.51s/it]\n[ComfyUI] 57%|█████▋ | 17/30 [01:32<01:11, 5.51s/it]\n[ComfyUI] 60%|██████ | 18/30 [01:37<01:06, 5.51s/it]\n[ComfyUI] 63%|██████▎ | 19/30 [01:43<01:00, 5.51s/it]\n[ComfyUI] 67%|██████▋ | 20/30 [01:48<00:55, 5.51s/it]\n[ComfyUI] 70%|███████ | 21/30 [01:54<00:49, 5.51s/it]\n[ComfyUI] 73%|███████▎ | 22/30 [01:59<00:44, 5.51s/it]\n[ComfyUI] 77%|███████▋ | 23/30 [02:05<00:38, 5.51s/it]\n[ComfyUI] 80%|████████ | 24/30 [02:10<00:33, 5.51s/it]\n[ComfyUI] 83%|████████▎ | 25/30 [02:16<00:27, 5.51s/it]\n[ComfyUI] 87%|████████▋ | 26/30 [02:21<00:22, 5.51s/it]\n[ComfyUI] 90%|█████████ | 27/30 [02:27<00:16, 5.51s/it]\n[ComfyUI] 93%|█████████▎| 28/30 [02:32<00:11, 5.51s/it]\n[ComfyUI] 97%|█████████▋| 29/30 [02:38<00:05, 5.51s/it]\n[ComfyUI] 100%|██████████| 30/30 [02:43<00:00, 5.51s/it]\n[ComfyUI] 100%|██████████| 30/30 [02:43<00:00, 5.47s/it]\n[ComfyUI] Allocated memory: memory=12.760 GB\n[ComfyUI] Max allocated memory: max_memory=18.839 GB\n[ComfyUI] Max reserved memory: max_reserved=20.719 GB\nExecuting node 5, title: HunyuanVideo Decode, class type: HyVideoDecode\n[ComfyUI]\n[ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:01<00:03, 1.54s/it]\n[ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:03<00:01, 1.62s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.40s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.45s/it]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Blending tiles: 33%|███▎ | 1/3 [00:00<00:00, 7.82it/s]\nExecuting node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine\n[ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 18.08it/s]\n[ComfyUI] Prompt executed in 200.52 seconds\noutputs: {'34': {'gifs': [{'filename': 'HunyuanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 20.0, 'workflow': 'HunyuanVideo_00001.png', 'fullpath': '/tmp/outputs/HunyuanVideo_00001.mp4'}]}}\n====================================\nHunyuanVideo_00001.png\nHunyuanVideo_00001.mp4", "metrics": { "predict_time": 215.296567202, "total_time": 243.791111 }, "output": "https://replicate.delivery/xezq/bm8FLxFcphaYM9harJGWOw4rWf9hiiOzJRJyJchsmhRZKYCKA/HunyuanVideo_00001.mp4", "started_at": "2025-01-13T17:50:19.280543Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-f2if2dysywguxizqnlaba3fdvvnlnhnix3nwedsn23e5o7xmdmpa", "get": "https://api.replicate.com/v1/predictions/3bqqjyj589rme0cmc34vejvpxr", "cancel": "https://api.replicate.com/v1/predictions/3bqqjyj589rme0cmc34vejvpxr/cancel" }, "version": "ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b" }Generated inRandom seed set to: 1903901857 Checking inputs ==================================== Checking weights ✅ hunyuan_video_720_fp8_e4m3fn.safetensors exists in ComfyUI/models/diffusion_models ✅ hunyuan_video_vae_bf16.safetensors exists in ComfyUI/models/vae ==================================== Running workflow [ComfyUI] got prompt Executing node 7, title: HunyuanVideo VAE Loader, class type: HyVideoVAELoader [ComfyUI] Loading text encoder model (clipL) from: /src/ComfyUI/models/clip/clip-vit-large-patch14 Executing node 16, title: (Down)Load HunyuanVideo TextEncoder, class type: DownloadAndLoadHyVideoTextEncoder [ComfyUI] Text encoder to dtype: torch.float16 [ComfyUI] Loading tokenizer (clipL) from: /src/ComfyUI/models/clip/clip-vit-large-patch14 [ComfyUI] Loading text encoder model (llm) from: /src/ComfyUI/models/LLM/llava-llama-3-8b-text-encoder-tokenizer [ComfyUI] [ComfyUI] Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s] [ComfyUI] Loading checkpoint shards: 25%|██▌ | 1/4 [00:00<00:01, 1.66it/s] [ComfyUI] Loading checkpoint shards: 50%|█████ | 2/4 [00:01<00:01, 1.71it/s] [ComfyUI] Loading checkpoint shards: 75%|███████▌ | 3/4 [00:01<00:00, 1.69it/s] [ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00, 2.52it/s] [ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00, 2.13it/s] [ComfyUI] Text encoder to dtype: torch.float16 [ComfyUI] Loading tokenizer (llm) from: /src/ComfyUI/models/LLM/llava-llama-3-8b-text-encoder-tokenizer Executing node 30, title: HunyuanVideo TextEncode, class type: HyVideoTextEncode [ComfyUI] llm prompt attention_mask shape: torch.Size([1, 161]), masked tokens: 47 [ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 49 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] Using accelerate to load and assign model weights to device... [ComfyUI] Loading LoRA: lora_comfyui with strength: 1.0 [ComfyUI] Requested to load HyVideoModel [ComfyUI] Loading 1 new model [ComfyUI] loaded completely 0.0 12555.953247070312 True [ComfyUI] Input (height, width, video_length) = (544, 960, 49) Executing node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler [ComfyUI] Sampling 49 frames in 13 latents at 960x544 with 30 inference steps [ComfyUI] Scheduler config: FrozenDict([('num_train_timesteps', 1000), ('shift', 9.0), ('reverse', True), ('solver', 'euler'), ('n_tokens', None), ('_use_default_values', ['num_train_timesteps', 'n_tokens'])]) [ComfyUI] [ComfyUI] 0%| | 0/30 [00:00<?, ?it/s] [ComfyUI] 3%|▎ | 1/30 [00:04<01:59, 4.13s/it] [ComfyUI] 7%|▋ | 2/30 [00:09<02:18, 4.95s/it] [ComfyUI] 10%|█ | 3/30 [00:15<02:20, 5.20s/it] [ComfyUI] 13%|█▎ | 4/30 [00:20<02:18, 5.32s/it] [ComfyUI] 17%|█▋ | 5/30 [00:26<02:14, 5.39s/it] [ComfyUI] 20%|██ | 6/30 [00:31<02:10, 5.43s/it] [ComfyUI] 23%|██▎ | 7/30 [00:37<02:05, 5.46s/it] [ComfyUI] 27%|██▋ | 8/30 [00:42<02:00, 5.47s/it] [ComfyUI] 30%|███ | 9/30 [00:48<01:55, 5.48s/it] [ComfyUI] 33%|███▎ | 10/30 [00:53<01:49, 5.49s/it] [ComfyUI] 37%|███▋ | 11/30 [00:59<01:44, 5.50s/it] [ComfyUI] 40%|████ | 12/30 [01:04<01:39, 5.50s/it] [ComfyUI] 43%|████▎ | 13/30 [01:10<01:33, 5.50s/it] [ComfyUI] 47%|████▋ | 14/30 [01:15<01:28, 5.51s/it] [ComfyUI] 50%|█████ | 15/30 [01:21<01:22, 5.51s/it] [ComfyUI] 53%|█████▎ | 16/30 [01:26<01:17, 5.51s/it] [ComfyUI] 57%|█████▋ | 17/30 [01:32<01:11, 5.51s/it] [ComfyUI] 60%|██████ | 18/30 [01:37<01:06, 5.51s/it] [ComfyUI] 63%|██████▎ | 19/30 [01:43<01:00, 5.51s/it] [ComfyUI] 67%|██████▋ | 20/30 [01:48<00:55, 5.51s/it] [ComfyUI] 70%|███████ | 21/30 [01:54<00:49, 5.51s/it] [ComfyUI] 73%|███████▎ | 22/30 [01:59<00:44, 5.51s/it] [ComfyUI] 77%|███████▋ | 23/30 [02:05<00:38, 5.51s/it] [ComfyUI] 80%|████████ | 24/30 [02:10<00:33, 5.51s/it] [ComfyUI] 83%|████████▎ | 25/30 [02:16<00:27, 5.51s/it] [ComfyUI] 87%|████████▋ | 26/30 [02:21<00:22, 5.51s/it] [ComfyUI] 90%|█████████ | 27/30 [02:27<00:16, 5.51s/it] [ComfyUI] 93%|█████████▎| 28/30 [02:32<00:11, 5.51s/it] [ComfyUI] 97%|█████████▋| 29/30 [02:38<00:05, 5.51s/it] [ComfyUI] 100%|██████████| 30/30 [02:43<00:00, 5.51s/it] [ComfyUI] 100%|██████████| 30/30 [02:43<00:00, 5.47s/it] [ComfyUI] Allocated memory: memory=12.760 GB [ComfyUI] Max allocated memory: max_memory=18.839 GB [ComfyUI] Max reserved memory: max_reserved=20.719 GB Executing node 5, title: HunyuanVideo Decode, class type: HyVideoDecode [ComfyUI] [ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s] [ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:01<00:03, 1.54s/it] [ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:03<00:01, 1.62s/it] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.40s/it] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.45s/it] [ComfyUI] [ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s] [ComfyUI] Blending tiles: 33%|███▎ | 1/3 [00:00<00:00, 7.82it/s] Executing node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine [ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 18.08it/s] [ComfyUI] Prompt executed in 200.52 seconds outputs: {'34': {'gifs': [{'filename': 'HunyuanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 20.0, '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
