zsxkib / hunyuan-video2video
A state-of-the-art text-to-video generation model capable of creating high-quality videos with realistic motion from text descriptions
Prediction
zsxkib/hunyuan-video2video:d550f226f28b1030c2fedd2947f39f19b4b0233b50364904538caaf037fb18d3Input
- crf
- 19
- steps
- 30
- video
- width
- 768
- height
- 768
- prompt
- high quality nature video of a excited brown bear walking through the grass, masterpiece, best quality
- flow_shift
- 9
- force_rate
- 0
- force_size
- Disabled
- frame_rate
- 24
- custom_width
- 512
- custom_height
- 512
- frame_load_cap
- 101
- guidance_scale
- 6
- keep_proportion
- denoise_strength
- 0.85
- select_every_nth
- 1
- skip_first_frames
- 0
{ "crf": 19, "steps": 30, "video": "https://replicate.delivery/pbxt/M5n5MuDgBxhSERj6PvHgz4BJcOUdHc9o1ZBXz454GoGP5DrR/2024-12-03-18%3A25%3A47_seed47039_A%20cat%20walks%20on%20the%20grass%2C%20realistic%20style..mp4", "width": 768, "height": 768, "prompt": "high quality nature video of a excited brown bear walking through the grass, masterpiece, best quality", "flow_shift": 9, "force_rate": 0, "force_size": "Disabled", "frame_rate": 24, "custom_width": 512, "custom_height": 512, "frame_load_cap": 101, "guidance_scale": 6, "keep_proportion": true, "denoise_strength": 0.85, "select_every_nth": 1, "skip_first_frames": 0 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run zsxkib/hunyuan-video2video using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "zsxkib/hunyuan-video2video:d550f226f28b1030c2fedd2947f39f19b4b0233b50364904538caaf037fb18d3", { input: { crf: 19, steps: 30, video: "https://replicate.delivery/pbxt/M5n5MuDgBxhSERj6PvHgz4BJcOUdHc9o1ZBXz454GoGP5DrR/2024-12-03-18%3A25%3A47_seed47039_A%20cat%20walks%20on%20the%20grass%2C%20realistic%20style..mp4", width: 768, height: 768, prompt: "high quality nature video of a excited brown bear walking through the grass, masterpiece, best quality", flow_shift: 9, force_rate: 0, force_size: "Disabled", frame_rate: 24, custom_width: 512, custom_height: 512, frame_load_cap: 101, guidance_scale: 6, keep_proportion: true, denoise_strength: 0.85, select_every_nth: 1, skip_first_frames: 0 } } ); // 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 zsxkib/hunyuan-video2video using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "zsxkib/hunyuan-video2video:d550f226f28b1030c2fedd2947f39f19b4b0233b50364904538caaf037fb18d3", input={ "crf": 19, "steps": 30, "video": "https://replicate.delivery/pbxt/M5n5MuDgBxhSERj6PvHgz4BJcOUdHc9o1ZBXz454GoGP5DrR/2024-12-03-18%3A25%3A47_seed47039_A%20cat%20walks%20on%20the%20grass%2C%20realistic%20style..mp4", "width": 768, "height": 768, "prompt": "high quality nature video of a excited brown bear walking through the grass, masterpiece, best quality", "flow_shift": 9, "force_rate": 0, "force_size": "Disabled", "frame_rate": 24, "custom_width": 512, "custom_height": 512, "frame_load_cap": 101, "guidance_scale": 6, "keep_proportion": True, "denoise_strength": 0.85, "select_every_nth": 1, "skip_first_frames": 0 } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())To learn more, take a look at the guide on getting started with Python.
Run zsxkib/hunyuan-video2video 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": "zsxkib/hunyuan-video2video:d550f226f28b1030c2fedd2947f39f19b4b0233b50364904538caaf037fb18d3", "input": { "crf": 19, "steps": 30, "video": "https://replicate.delivery/pbxt/M5n5MuDgBxhSERj6PvHgz4BJcOUdHc9o1ZBXz454GoGP5DrR/2024-12-03-18%3A25%3A47_seed47039_A%20cat%20walks%20on%20the%20grass%2C%20realistic%20style..mp4", "width": 768, "height": 768, "prompt": "high quality nature video of a excited brown bear walking through the grass, masterpiece, best quality", "flow_shift": 9, "force_rate": 0, "force_size": "Disabled", "frame_rate": 24, "custom_width": 512, "custom_height": 512, "frame_load_cap": 101, "guidance_scale": 6, "keep_proportion": true, "denoise_strength": 0.85, "select_every_nth": 1, "skip_first_frames": 0 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-12-11T12:53:57.002078Z", "created_at": "2024-12-11T12:47:37.805000Z", "data_removed": false, "error": null, "id": "jqgegs5s9nrme0ckpq1abb2q74", "input": { "crf": 19, "steps": 30, "video": "https://replicate.delivery/pbxt/M5n5MuDgBxhSERj6PvHgz4BJcOUdHc9o1ZBXz454GoGP5DrR/2024-12-03-18%3A25%3A47_seed47039_A%20cat%20walks%20on%20the%20grass%2C%20realistic%20style..mp4", "width": 768, "height": 768, "prompt": "high quality nature video of a excited brown bear walking through the grass, masterpiece, best quality", "flow_shift": 9, "force_rate": 0, "force_size": "Disabled", "frame_rate": 24, "custom_width": 512, "custom_height": 512, "frame_load_cap": 101, "guidance_scale": 6, "keep_proportion": true, "denoise_strength": 0.85, "select_every_nth": 1, "skip_first_frames": 0 }, "logs": "Checking inputs\n✅ /tmp/inputs/input.mp4\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 43, title: Load Video (Upload) 🎥🅥🅗🅢, class type: VHS_LoadVideo\nExecuting node 42, title: Resize Image, class type: ImageResizeKJ\nExecuting node 39, title: Get Image Size & Count, class type: GetImageSizeAndCount\nExecuting node 7, title: HunyuanVideo VAE Loader, class type: HyVideoVAELoader\nExecuting node 38, title: HunyuanVideo Encode, class type: HyVideoEncode\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] ColorMod: Can't find pypng! Please install to enable 16bit image support.\n[ComfyUI] ColorMod: Ignoring node 'CV2TonemapDurand' due to cv2 edition/version\n[ComfyUI] ------------------------------------------\n[ComfyUI] \u001b[34mComfyroll Studio v1.76 : \u001b[92m 175 Nodes Loaded\u001b[0m\n[ComfyUI] ------------------------------------------\n[ComfyUI] ** For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md\n[ComfyUI] ** For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki\n[ComfyUI] ------------------------------------------\n[ComfyUI] \u001b[34mFizzleDorf Custom Nodes: \u001b[92mLoaded\u001b[0m\n[ComfyUI] \u001b[92m[tinyterraNodes] \u001b[32mLoaded\u001b[0m\n[ComfyUI] Please 'pip install xformers'\n[ComfyUI] Nvidia APEX normalization not installed, using PyTorch LayerNorm\n[ComfyUI] \u001b[0;33m[ReActor]\u001b[0m - \u001b[38;5;173mSTATUS\u001b[0m - \u001b[0;32mRunning v0.5.2-a1 in ComfyUI\u001b[0m\n[ComfyUI] Torch version: 2.5.1+cu124\n[ComfyUI]\n[ComfyUI] \u001b[36mEfficiency Nodes:\u001b[0m Attempting to add Control Net options to the 'HiRes-Fix Script' Node (comfyui_controlnet_aux add-on)...\u001b[92mSuccess!\u001b[0m\n[ComfyUI] \u001b[93mEfficiency Nodes Warning:\u001b[0m Failed to import python package 'simpleeval'; related nodes disabled.\n[ComfyUI]\n[ComfyUI]\n[ComfyUI]\n[ComfyUI] \u001b[92m[rgthree-comfy] Loaded 42 extraordinary nodes. 🎉\u001b[00m\n[ComfyUI]\n[ComfyUI] \u001b[34mWAS Node Suite: \u001b[0mOpenCV Python FFMPEG support is enabled\u001b[0m\n[ComfyUI] \u001b[34mWAS Node Suite: \u001b[0m`ffmpeg_bin_path` is set to: /usr/bin/ffmpeg\u001b[0m\n[ComfyUI] \u001b[34mWAS Node Suite: \u001b[0mFinished.\u001b[0m \u001b[32mLoaded\u001b[0m \u001b[0m218\u001b[0m \u001b[32mnodes successfully.\u001b[0m\n[ComfyUI] encoded latents shape torch.Size([1, 16, 26, 52, 96])\n[ComfyUI] Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s]\n[ComfyUI] Loading checkpoint shards: 25%|██▌ | 1/4 [00:00<00:02, 1.44it/s]\n[ComfyUI] Loading checkpoint shards: 50%|█████ | 2/4 [00:01<00:01, 1.45it/s]\n[ComfyUI] Loading checkpoint shards: 75%|███████▌ | 3/4 [00:02<00:00, 1.46it/s]\n[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 2.00it/s]\n[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 1.76it/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: 19\n[ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 20\nExecuting node 1, title: HunyuanVideo Model Loader, class type: HyVideoModelLoader\n[ComfyUI] Using accelerate to load and assign model weights to device...\n[ComfyUI] Input (height, width, video_length) = (416, 768, 101)\nExecuting node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler\n[ComfyUI] Sampling 101 frames in 26 latents at 768x416 with 25 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] tensor([978.2609, 972.9730, 967.2897, 961.1651, 954.5454, 947.3684, 939.5604, 931.0344, 921.6867, 911.3924, 900.0000, 887.3240, 873.1343, 857.1429, 838.9830, 818.1818, 794.1176, 765.9575, 732.5581, 692.3077, 642.8571, 580.6452, 500.0001, 391.3044, 236.8421], device='cuda:0')\n[ComfyUI] 0%| | 0/25 [00:00<?, ?it/s]\n[ComfyUI] 4%|▍ | 1/25 [00:07<03:11, 7.99s/it]\n[ComfyUI] 8%|▊ | 2/25 [00:16<03:06, 8.12s/it]\n[ComfyUI] 12%|█▏ | 3/25 [00:24<02:58, 8.11s/it]\n[ComfyUI] 16%|█▌ | 4/25 [00:32<02:50, 8.11s/it]\n[ComfyUI] 20%|██ | 5/25 [00:40<02:42, 8.11s/it]\n[ComfyUI] 24%|██▍ | 6/25 [00:48<02:34, 8.13s/it]\n[ComfyUI] 28%|██▊ | 7/25 [00:56<02:26, 8.12s/it]\n[ComfyUI] 32%|███▏ | 8/25 [01:04<02:18, 8.12s/it]\n[ComfyUI] 36%|███▌ | 9/25 [01:13<02:09, 8.12s/it]\n[ComfyUI] 40%|████ | 10/25 [01:21<02:01, 8.13s/it]\n[ComfyUI] 44%|████▍ | 11/25 [01:29<01:53, 8.14s/it]\n[ComfyUI] 48%|████▊ | 12/25 [01:37<01:45, 8.13s/it]\n[ComfyUI] 52%|█████▏ | 13/25 [01:45<01:37, 8.14s/it]\n[ComfyUI] 56%|█████▌ | 14/25 [01:53<01:29, 8.14s/it]\n[ComfyUI] 60%|██████ | 15/25 [02:01<01:21, 8.16s/it]\n[ComfyUI] 64%|██████▍ | 16/25 [02:10<01:13, 8.15s/it]\n[ComfyUI] 68%|██████▊ | 17/25 [02:18<01:05, 8.14s/it]\n[ComfyUI] 72%|███████▏ | 18/25 [02:26<00:56, 8.13s/it]\n[ComfyUI] 76%|███████▌ | 19/25 [02:34<00:48, 8.12s/it]\n[ComfyUI] 80%|████████ | 20/25 [02:42<00:40, 8.12s/it]\n[ComfyUI] 84%|████████▍ | 21/25 [02:50<00:32, 8.12s/it]\n[ComfyUI] 88%|████████▊ | 22/25 [02:58<00:24, 8.12s/it]\n[ComfyUI] 92%|█████████▏| 23/25 [03:06<00:16, 8.14s/it]\n[ComfyUI] 96%|█████████▌| 24/25 [03:15<00:08, 8.13s/it]\n[ComfyUI] 100%|██████████| 25/25 [03:23<00:00, 8.13s/it]\n[ComfyUI] 100%|██████████| 25/25 [03:23<00:00, 8.13s/it]\n[ComfyUI] Allocated memory: memory=12.306 GB\n[ComfyUI] Max allocated memory: max_memory=20.619 GB\n[ComfyUI] Max reserved memory: max_reserved=22.875 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, 1.51s/it]\n[ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:03<00:01, 1.56s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:03<00:00, 1.05s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:03<00:00, 1.18s/it]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 58.64it/s]\n[ComfyUI]\n[ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:01<00:02, 1.23s/it]\n[ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:02<00:01, 1.27s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:02<00:00, 1.18it/s]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:02<00:00, 1.04it/s]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 67.57it/s]\n[ComfyUI]\n[ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:00<00:00, 7.02it/s]\n[ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:00<00:00, 7.17it/s]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:00<00:00, 9.49it/s]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s]\nExecuting node 44, title: Image Concatenate Multi, class type: ImageConcatMulti\nExecuting node 53, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine\n[ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 95.57it/s]\n[ComfyUI] Prompt executed in 240.95 seconds\noutputs: {'39': {'text': ['101x768x416']}, '53': {'gifs': [{'filename': 'HunhuyanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 24.0}]}}\n====================================\nHunhuyanVideo_00001.png\nHunhuyanVideo_00001.mp4", "metrics": { "predict_time": 241.366450445, "total_time": 379.197078 }, "output": "https://replicate.delivery/xezq/uPc1qM90mBKtD1TsSSbXMu3V00SpUtbqQJSThKzqlGIZ9ceJA/HunhuyanVideo_00001.mp4", "started_at": "2024-12-11T12:49:55.635627Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-cbr4crg2vbfgdtk6c3px4luygzyrdqsm4dl3qdkxisybmvbzj6cq", "get": "https://api.replicate.com/v1/predictions/jqgegs5s9nrme0ckpq1abb2q74", "cancel": "https://api.replicate.com/v1/predictions/jqgegs5s9nrme0ckpq1abb2q74/cancel" }, "version": "d550f226f28b1030c2fedd2947f39f19b4b0233b50364904538caaf037fb18d3" }Generated inChecking inputs ✅ /tmp/inputs/input.mp4 ==================================== 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 43, title: Load Video (Upload) 🎥🅥🅗🅢, class type: VHS_LoadVideo Executing node 42, title: Resize Image, class type: ImageResizeKJ Executing node 39, title: Get Image Size & Count, class type: GetImageSizeAndCount Executing node 7, title: HunyuanVideo VAE Loader, class type: HyVideoVAELoader Executing node 38, title: HunyuanVideo Encode, class type: HyVideoEncode 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] ColorMod: Can't find pypng! Please install to enable 16bit image support. [ComfyUI] ColorMod: Ignoring node 'CV2TonemapDurand' due to cv2 edition/version [ComfyUI] ------------------------------------------ [ComfyUI] Comfyroll Studio v1.76 : 175 Nodes Loaded [ComfyUI] ------------------------------------------ [ComfyUI] ** For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md [ComfyUI] ** For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki [ComfyUI] ------------------------------------------ [ComfyUI] FizzleDorf Custom Nodes: Loaded [ComfyUI] [tinyterraNodes] Loaded [ComfyUI] Please 'pip install xformers' [ComfyUI] Nvidia APEX normalization not installed, using PyTorch LayerNorm [ComfyUI] [ReActor] - STATUS - Running v0.5.2-a1 in ComfyUI [ComfyUI] Torch version: 2.5.1+cu124 [ComfyUI] [ComfyUI] Efficiency Nodes: Attempting to add Control Net options to the 'HiRes-Fix Script' Node (comfyui_controlnet_aux add-on)...Success! [ComfyUI] Efficiency Nodes Warning: Failed to import python package 'simpleeval'; related nodes disabled. [ComfyUI] [ComfyUI] [ComfyUI] [ComfyUI] [rgthree-comfy] Loaded 42 extraordinary nodes. 🎉 [ComfyUI] [ComfyUI] WAS Node Suite: OpenCV Python FFMPEG support is enabled [ComfyUI] WAS Node Suite: `ffmpeg_bin_path` is set to: /usr/bin/ffmpeg [ComfyUI] WAS Node Suite: Finished. Loaded 218 nodes successfully. [ComfyUI] encoded latents shape torch.Size([1, 16, 26, 52, 96]) [ComfyUI] Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s] [ComfyUI] Loading checkpoint shards: 25%|██▌ | 1/4 [00:00<00:02, 1.44it/s] [ComfyUI] Loading checkpoint shards: 50%|█████ | 2/4 [00:01<00:01, 1.45it/s] [ComfyUI] Loading checkpoint shards: 75%|███████▌ | 3/4 [00:02<00:00, 1.46it/s] [ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 2.00it/s] [ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 1.76it/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: 19 [ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 20 Executing node 1, title: HunyuanVideo Model Loader, class type: HyVideoModelLoader [ComfyUI] Using accelerate to load and assign model weights to device... [ComfyUI] Input (height, width, video_length) = (416, 768, 101) Executing node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler [ComfyUI] Sampling 101 frames in 26 latents at 768x416 with 25 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] tensor([978.2609, 972.9730, 967.2897, 961.1651, 954.5454, 947.3684, 939.5604, 931.0344, 921.6867, 911.3924, 900.0000, 887.3240, 873.1343, 857.1429, 838.9830, 818.1818, 794.1176, 765.9575, 732.5581, 692.3077, 642.8571, 580.6452, 500.0001, 391.3044, 236.8421], device='cuda:0') [ComfyUI] 0%| | 0/25 [00:00<?, ?it/s] [ComfyUI] 4%|▍ | 1/25 [00:07<03:11, 7.99s/it] [ComfyUI] 8%|▊ | 2/25 [00:16<03:06, 8.12s/it] [ComfyUI] 12%|█▏ | 3/25 [00:24<02:58, 8.11s/it] [ComfyUI] 16%|█▌ | 4/25 [00:32<02:50, 8.11s/it] [ComfyUI] 20%|██ | 5/25 [00:40<02:42, 8.11s/it] [ComfyUI] 24%|██▍ | 6/25 [00:48<02:34, 8.13s/it] [ComfyUI] 28%|██▊ | 7/25 [00:56<02:26, 8.12s/it] [ComfyUI] 32%|███▏ | 8/25 [01:04<02:18, 8.12s/it] [ComfyUI] 36%|███▌ | 9/25 [01:13<02:09, 8.12s/it] [ComfyUI] 40%|████ | 10/25 [01:21<02:01, 8.13s/it] [ComfyUI] 44%|████▍ | 11/25 [01:29<01:53, 8.14s/it] [ComfyUI] 48%|████▊ | 12/25 [01:37<01:45, 8.13s/it] [ComfyUI] 52%|█████▏ | 13/25 [01:45<01:37, 8.14s/it] [ComfyUI] 56%|█████▌ | 14/25 [01:53<01:29, 8.14s/it] [ComfyUI] 60%|██████ | 15/25 [02:01<01:21, 8.16s/it] [ComfyUI] 64%|██████▍ | 16/25 [02:10<01:13, 8.15s/it] [ComfyUI] 68%|██████▊ | 17/25 [02:18<01:05, 8.14s/it] [ComfyUI] 72%|███████▏ | 18/25 [02:26<00:56, 8.13s/it] [ComfyUI] 76%|███████▌ | 19/25 [02:34<00:48, 8.12s/it] [ComfyUI] 80%|████████ | 20/25 [02:42<00:40, 8.12s/it] [ComfyUI] 84%|████████▍ | 21/25 [02:50<00:32, 8.12s/it] [ComfyUI] 88%|████████▊ | 22/25 [02:58<00:24, 8.12s/it] [ComfyUI] 92%|█████████▏| 23/25 [03:06<00:16, 8.14s/it] [ComfyUI] 96%|█████████▌| 24/25 [03:15<00:08, 8.13s/it] [ComfyUI] 100%|██████████| 25/25 [03:23<00:00, 8.13s/it] [ComfyUI] 100%|██████████| 25/25 [03:23<00:00, 8.13s/it] [ComfyUI] Allocated memory: memory=12.306 GB [ComfyUI] Max allocated memory: max_memory=20.619 GB [ComfyUI] Max reserved memory: max_reserved=22.875 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, 1.51s/it] [ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:03<00:01, 1.56s/it] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:03<00:00, 1.05s/it] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:03<00:00, 1.18s/it] [ComfyUI] [ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s] [ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 58.64it/s] [ComfyUI] [ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s] [ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:01<00:02, 1.23s/it] [ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:02<00:01, 1.27s/it] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:02<00:00, 1.18it/s] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:02<00:00, 1.04it/s] [ComfyUI] [ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s] [ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 67.57it/s] [ComfyUI] [ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s] [ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:00<00:00, 7.02it/s] [ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:00<00:00, 7.17it/s] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:00<00:00, 9.49it/s] [ComfyUI] [ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s] Executing node 44, title: Image Concatenate Multi, class type: ImageConcatMulti Executing node 53, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine [ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 95.57it/s] [ComfyUI] Prompt executed in 240.95 seconds outputs: {'39': {'text': ['101x768x416']}, '53': {'gifs': [{'filename': 'HunhuyanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 24.0}]}} ==================================== HunhuyanVideo_00001.png HunhuyanVideo_00001.mp4Prediction
zsxkib/hunyuan-video2video:d550f226f28b1030c2fedd2947f39f19b4b0233b50364904538caaf037fb18d3Input
- crf
- 19
- steps
- 30
- video
- width
- 768
- height
- 768
- prompt
- high quality nature video of a excited Bengal Tiger walking through the grass, masterpiece, best quality
- flow_shift
- 9
- force_rate
- 0
- force_size
- Disabled
- frame_rate
- 24
- custom_width
- 512
- custom_height
- 512
- frame_load_cap
- 101
- guidance_scale
- 6
- keep_proportion
- denoise_strength
- 0.85
- select_every_nth
- 1
- skip_first_frames
- 0
{ "crf": 19, "steps": 30, "video": "https://replicate.delivery/pbxt/M5n5MuDgBxhSERj6PvHgz4BJcOUdHc9o1ZBXz454GoGP5DrR/2024-12-03-18%3A25%3A47_seed47039_A%20cat%20walks%20on%20the%20grass%2C%20realistic%20style..mp4", "width": 768, "height": 768, "prompt": "high quality nature video of a excited Bengal Tiger walking through the grass, masterpiece, best quality", "flow_shift": 9, "force_rate": 0, "force_size": "Disabled", "frame_rate": 24, "custom_width": 512, "custom_height": 512, "frame_load_cap": 101, "guidance_scale": 6, "keep_proportion": true, "denoise_strength": 0.85, "select_every_nth": 1, "skip_first_frames": 0 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run zsxkib/hunyuan-video2video using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "zsxkib/hunyuan-video2video:d550f226f28b1030c2fedd2947f39f19b4b0233b50364904538caaf037fb18d3", { input: { crf: 19, steps: 30, video: "https://replicate.delivery/pbxt/M5n5MuDgBxhSERj6PvHgz4BJcOUdHc9o1ZBXz454GoGP5DrR/2024-12-03-18%3A25%3A47_seed47039_A%20cat%20walks%20on%20the%20grass%2C%20realistic%20style..mp4", width: 768, height: 768, prompt: "high quality nature video of a excited Bengal Tiger walking through the grass, masterpiece, best quality", flow_shift: 9, force_rate: 0, force_size: "Disabled", frame_rate: 24, custom_width: 512, custom_height: 512, frame_load_cap: 101, guidance_scale: 6, keep_proportion: true, denoise_strength: 0.85, select_every_nth: 1, skip_first_frames: 0 } } ); // 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 zsxkib/hunyuan-video2video using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "zsxkib/hunyuan-video2video:d550f226f28b1030c2fedd2947f39f19b4b0233b50364904538caaf037fb18d3", input={ "crf": 19, "steps": 30, "video": "https://replicate.delivery/pbxt/M5n5MuDgBxhSERj6PvHgz4BJcOUdHc9o1ZBXz454GoGP5DrR/2024-12-03-18%3A25%3A47_seed47039_A%20cat%20walks%20on%20the%20grass%2C%20realistic%20style..mp4", "width": 768, "height": 768, "prompt": "high quality nature video of a excited Bengal Tiger walking through the grass, masterpiece, best quality", "flow_shift": 9, "force_rate": 0, "force_size": "Disabled", "frame_rate": 24, "custom_width": 512, "custom_height": 512, "frame_load_cap": 101, "guidance_scale": 6, "keep_proportion": True, "denoise_strength": 0.85, "select_every_nth": 1, "skip_first_frames": 0 } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())To learn more, take a look at the guide on getting started with Python.
Run zsxkib/hunyuan-video2video 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": "zsxkib/hunyuan-video2video:d550f226f28b1030c2fedd2947f39f19b4b0233b50364904538caaf037fb18d3", "input": { "crf": 19, "steps": 30, "video": "https://replicate.delivery/pbxt/M5n5MuDgBxhSERj6PvHgz4BJcOUdHc9o1ZBXz454GoGP5DrR/2024-12-03-18%3A25%3A47_seed47039_A%20cat%20walks%20on%20the%20grass%2C%20realistic%20style..mp4", "width": 768, "height": 768, "prompt": "high quality nature video of a excited Bengal Tiger walking through the grass, masterpiece, best quality", "flow_shift": 9, "force_rate": 0, "force_size": "Disabled", "frame_rate": 24, "custom_width": 512, "custom_height": 512, "frame_load_cap": 101, "guidance_scale": 6, "keep_proportion": true, "denoise_strength": 0.85, "select_every_nth": 1, "skip_first_frames": 0 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-12-11T13:01:44.944299Z", "created_at": "2024-12-11T12:56:22.272000Z", "data_removed": false, "error": null, "id": "k0t5qf5t01rmc0ckpq58968zdm", "input": { "crf": 19, "steps": 30, "video": "https://replicate.delivery/pbxt/M5n5MuDgBxhSERj6PvHgz4BJcOUdHc9o1ZBXz454GoGP5DrR/2024-12-03-18%3A25%3A47_seed47039_A%20cat%20walks%20on%20the%20grass%2C%20realistic%20style..mp4", "width": 768, "height": 768, "prompt": "high quality nature video of a excited Bengal Tiger walking through the grass, masterpiece, best quality", "flow_shift": 9, "force_rate": 0, "force_size": "Disabled", "frame_rate": 24, "custom_width": 512, "custom_height": 512, "frame_load_cap": 101, "guidance_scale": 6, "keep_proportion": true, "denoise_strength": 0.85, "select_every_nth": 1, "skip_first_frames": 0 }, "logs": "Checking inputs\n✅ /tmp/inputs/input.mp4\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 43, title: Load Video (Upload) 🎥🅥🅗🅢, class type: VHS_LoadVideo\nExecuting node 42, title: Resize Image, class type: ImageResizeKJ\nExecuting node 39, title: Get Image Size & Count, class type: GetImageSizeAndCount\nExecuting node 7, title: HunyuanVideo VAE Loader, class type: HyVideoVAELoader\nExecuting node 38, title: HunyuanVideo Encode, class type: HyVideoEncode\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] ColorMod: Can't find pypng! Please install to enable 16bit image support.\n[ComfyUI] ColorMod: Ignoring node 'CV2TonemapDurand' due to cv2 edition/version\n[ComfyUI] ------------------------------------------\n[ComfyUI]\n[ComfyUI] \u001b[34mComfyroll Studio v1.76 : \u001b[92m 175 Nodes Loaded\u001b[0m\n[ComfyUI] ------------------------------------------\n[ComfyUI] ** For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md\n[ComfyUI] ** For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki\n[ComfyUI] ------------------------------------------\n[ComfyUI] \u001b[34mFizzleDorf Custom Nodes: \u001b[92mLoaded\u001b[0m\n[ComfyUI] \u001b[92m[tinyterraNodes] \u001b[32mLoaded\u001b[0m\n[ComfyUI] Please 'pip install xformers'\n[ComfyUI] Nvidia APEX normalization not installed, using PyTorch LayerNorm\n[ComfyUI] \u001b[0;33m[ReActor]\u001b[0m - \u001b[38;5;173mSTATUS\u001b[0m - \u001b[0;32mRunning v0.5.2-a1 in ComfyUI\u001b[0m\n[ComfyUI] Torch version: 2.5.1+cu124\n[ComfyUI]\n[ComfyUI] \u001b[36mEfficiency Nodes:\u001b[0m Attempting to add Control Net options to the 'HiRes-Fix Script' Node (comfyui_controlnet_aux add-on)...\u001b[92mSuccess!\u001b[0m\n[ComfyUI] \u001b[93mEfficiency Nodes Warning:\u001b[0m Failed to import python package 'simpleeval'; related nodes disabled.\n[ComfyUI]\n[ComfyUI]\n[ComfyUI] \u001b[92m[rgthree-comfy] Loaded 42 fantastic nodes. 🎉\u001b[00m\n[ComfyUI]\n[ComfyUI] \u001b[34mWAS Node Suite: \u001b[0mOpenCV Python FFMPEG support is enabled\u001b[0m\n[ComfyUI] \u001b[34mWAS Node Suite: \u001b[0m`ffmpeg_bin_path` is set to: /usr/bin/ffmpeg\u001b[0m\n[ComfyUI] \u001b[34mWAS Node Suite: \u001b[0mFinished.\u001b[0m \u001b[32mLoaded\u001b[0m \u001b[0m218\u001b[0m \u001b[32mnodes successfully.\u001b[0m\n[ComfyUI] encoded latents shape torch.Size([1, 16, 26, 52, 96])\n[ComfyUI] Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s]\n[ComfyUI] Loading checkpoint shards: 25%|██▌ | 1/4 [00:00<00:02, 1.46it/s]\n[ComfyUI] Loading checkpoint shards: 50%|█████ | 2/4 [00:01<00:01, 1.48it/s]\n[ComfyUI] Loading checkpoint shards: 75%|███████▌ | 3/4 [00:02<00:00, 1.49it/s]\n[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 2.10it/s]\n[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 1.82it/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: 19\n[ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 20\nExecuting node 1, title: HunyuanVideo Model Loader, class type: HyVideoModelLoader\n[ComfyUI] Using accelerate to load and assign model weights to device...\n[ComfyUI] Input (height, width, video_length) = (416, 768, 101)\nExecuting node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler\n[ComfyUI] Sampling 101 frames in 26 latents at 768x416 with 25 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] tensor([978.2609, 972.9730, 967.2897, 961.1651, 954.5454, 947.3684, 939.5604, 931.0344, 921.6867, 911.3924, 900.0000, 887.3240, 873.1343, 857.1429, 838.9830, 818.1818, 794.1176, 765.9575, 732.5581, 692.3077, 642.8571, 580.6452, 500.0001, 391.3044, 236.8421], device='cuda:0')\n[ComfyUI]\n[ComfyUI] 0%| | 0/25 [00:00<?, ?it/s]\n[ComfyUI] 4%|▍ | 1/25 [00:07<03:11, 7.99s/it]\n[ComfyUI] 8%|▊ | 2/25 [00:16<03:05, 8.05s/it]\n[ComfyUI] 12%|█▏ | 3/25 [00:24<02:57, 8.07s/it]\n[ComfyUI] 16%|█▌ | 4/25 [00:32<02:49, 8.07s/it]\n[ComfyUI] 20%|██ | 5/25 [00:40<02:41, 8.09s/it]\n[ComfyUI] 24%|██▍ | 6/25 [00:48<02:33, 8.08s/it]\n[ComfyUI] 28%|██▊ | 7/25 [00:56<02:25, 8.10s/it]\n[ComfyUI] 32%|███▏ | 8/25 [01:04<02:17, 8.10s/it]\n[ComfyUI] 36%|███▌ | 9/25 [01:12<02:10, 8.16s/it]\n[ComfyUI] 40%|████ | 10/25 [01:21<02:02, 8.14s/it]\n[ComfyUI] 44%|████▍ | 11/25 [01:29<01:53, 8.14s/it]\n[ComfyUI] 48%|████▊ | 12/25 [01:37<01:45, 8.14s/it]\n[ComfyUI] 52%|█████▏ | 13/25 [01:45<01:37, 8.14s/it]\n[ComfyUI] 56%|█████▌ | 14/25 [01:53<01:29, 8.13s/it]\n[ComfyUI] 60%|██████ | 15/25 [02:01<01:21, 8.12s/it]\n[ComfyUI] 64%|██████▍ | 16/25 [02:09<01:13, 8.12s/it]\n[ComfyUI] 68%|██████▊ | 17/25 [02:17<01:05, 8.13s/it]\n[ComfyUI] 72%|███████▏ | 18/25 [02:26<00:56, 8.14s/it]\n[ComfyUI] 76%|███████▌ | 19/25 [02:34<00:48, 8.13s/it]\n[ComfyUI] 80%|████████ | 20/25 [02:42<00:40, 8.14s/it]\n[ComfyUI] 84%|████████▍ | 21/25 [02:50<00:32, 8.13s/it]\n[ComfyUI] 88%|████████▊ | 22/25 [02:58<00:24, 8.13s/it]\n[ComfyUI] 92%|█████████▏| 23/25 [03:06<00:16, 8.12s/it]\n[ComfyUI] 96%|█████████▌| 24/25 [03:14<00:08, 8.13s/it]\n[ComfyUI] 100%|██████████| 25/25 [03:22<00:00, 8.13s/it]\n[ComfyUI] 100%|██████████| 25/25 [03:22<00:00, 8.12s/it]\n[ComfyUI] Allocated memory: memory=12.306 GB\n[ComfyUI] Max allocated memory: max_memory=20.619 GB\n[ComfyUI] Max reserved memory: max_reserved=22.875 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, 1.51s/it]\n[ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:03<00:01, 1.56s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:03<00:00, 1.04s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:03<00:00, 1.18s/it]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 58.36it/s]\n[ComfyUI]\n[ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:01<00:02, 1.22s/it]\n[ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:02<00:01, 1.27s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:02<00:00, 1.18it/s]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:02<00:00, 1.05it/s]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 66.36it/s]\n[ComfyUI]\n[ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:00<00:00, 7.03it/s]\n[ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:00<00:00, 7.17it/s]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:00<00:00, 9.50it/s]\n[ComfyUI]\n[ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s]\nExecuting node 44, title: Image Concatenate Multi, class type: ImageConcatMulti\nExecuting node 53, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine\n[ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 96.34it/s]\n[ComfyUI] Prompt executed in 241.31 seconds\noutputs: {'39': {'text': ['101x768x416']}, '53': {'gifs': [{'filename': 'HunhuyanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 24.0}]}}\n====================================\nHunhuyanVideo_00001.png\nHunhuyanVideo_00001.mp4", "metrics": { "predict_time": 241.745280032, "total_time": 322.672299 }, "output": "https://replicate.delivery/xezq/fPeeEckco8DfnQ8zUUpbawLy0ezXMEP5if95pXKyAYFKOf58JA/HunhuyanVideo_00001.mp4", "started_at": "2024-12-11T12:57:43.199019Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-r3lme75aec5z4qrc65ss7winvnfsbwvqvatk4ji7n6kmjbobx6iq", "get": "https://api.replicate.com/v1/predictions/k0t5qf5t01rmc0ckpq58968zdm", "cancel": "https://api.replicate.com/v1/predictions/k0t5qf5t01rmc0ckpq58968zdm/cancel" }, "version": "d550f226f28b1030c2fedd2947f39f19b4b0233b50364904538caaf037fb18d3" }Generated inChecking inputs ✅ /tmp/inputs/input.mp4 ==================================== 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 43, title: Load Video (Upload) 🎥🅥🅗🅢, class type: VHS_LoadVideo Executing node 42, title: Resize Image, class type: ImageResizeKJ Executing node 39, title: Get Image Size & Count, class type: GetImageSizeAndCount Executing node 7, title: HunyuanVideo VAE Loader, class type: HyVideoVAELoader Executing node 38, title: HunyuanVideo Encode, class type: HyVideoEncode 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] ColorMod: Can't find pypng! Please install to enable 16bit image support. [ComfyUI] ColorMod: Ignoring node 'CV2TonemapDurand' due to cv2 edition/version [ComfyUI] ------------------------------------------ [ComfyUI] [ComfyUI] Comfyroll Studio v1.76 : 175 Nodes Loaded [ComfyUI] ------------------------------------------ [ComfyUI] ** For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md [ComfyUI] ** For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki [ComfyUI] ------------------------------------------ [ComfyUI] FizzleDorf Custom Nodes: Loaded [ComfyUI] [tinyterraNodes] Loaded [ComfyUI] Please 'pip install xformers' [ComfyUI] Nvidia APEX normalization not installed, using PyTorch LayerNorm [ComfyUI] [ReActor] - STATUS - Running v0.5.2-a1 in ComfyUI [ComfyUI] Torch version: 2.5.1+cu124 [ComfyUI] [ComfyUI] Efficiency Nodes: Attempting to add Control Net options to the 'HiRes-Fix Script' Node (comfyui_controlnet_aux add-on)...Success! [ComfyUI] Efficiency Nodes Warning: Failed to import python package 'simpleeval'; related nodes disabled. [ComfyUI] [ComfyUI] [ComfyUI] [rgthree-comfy] Loaded 42 fantastic nodes. 🎉 [ComfyUI] [ComfyUI] WAS Node Suite: OpenCV Python FFMPEG support is enabled [ComfyUI] WAS Node Suite: `ffmpeg_bin_path` is set to: /usr/bin/ffmpeg [ComfyUI] WAS Node Suite: Finished. Loaded 218 nodes successfully. [ComfyUI] encoded latents shape torch.Size([1, 16, 26, 52, 96]) [ComfyUI] Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s] [ComfyUI] Loading checkpoint shards: 25%|██▌ | 1/4 [00:00<00:02, 1.46it/s] [ComfyUI] Loading checkpoint shards: 50%|█████ | 2/4 [00:01<00:01, 1.48it/s] [ComfyUI] Loading checkpoint shards: 75%|███████▌ | 3/4 [00:02<00:00, 1.49it/s] [ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 2.10it/s] [ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 1.82it/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: 19 [ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 20 Executing node 1, title: HunyuanVideo Model Loader, class type: HyVideoModelLoader [ComfyUI] Using accelerate to load and assign model weights to device... [ComfyUI] Input (height, width, video_length) = (416, 768, 101) Executing node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler [ComfyUI] Sampling 101 frames in 26 latents at 768x416 with 25 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] tensor([978.2609, 972.9730, 967.2897, 961.1651, 954.5454, 947.3684, 939.5604, 931.0344, 921.6867, 911.3924, 900.0000, 887.3240, 873.1343, 857.1429, 838.9830, 818.1818, 794.1176, 765.9575, 732.5581, 692.3077, 642.8571, 580.6452, 500.0001, 391.3044, 236.8421], device='cuda:0') [ComfyUI] [ComfyUI] 0%| | 0/25 [00:00<?, ?it/s] [ComfyUI] 4%|▍ | 1/25 [00:07<03:11, 7.99s/it] [ComfyUI] 8%|▊ | 2/25 [00:16<03:05, 8.05s/it] [ComfyUI] 12%|█▏ | 3/25 [00:24<02:57, 8.07s/it] [ComfyUI] 16%|█▌ | 4/25 [00:32<02:49, 8.07s/it] [ComfyUI] 20%|██ | 5/25 [00:40<02:41, 8.09s/it] [ComfyUI] 24%|██▍ | 6/25 [00:48<02:33, 8.08s/it] [ComfyUI] 28%|██▊ | 7/25 [00:56<02:25, 8.10s/it] [ComfyUI] 32%|███▏ | 8/25 [01:04<02:17, 8.10s/it] [ComfyUI] 36%|███▌ | 9/25 [01:12<02:10, 8.16s/it] [ComfyUI] 40%|████ | 10/25 [01:21<02:02, 8.14s/it] [ComfyUI] 44%|████▍ | 11/25 [01:29<01:53, 8.14s/it] [ComfyUI] 48%|████▊ | 12/25 [01:37<01:45, 8.14s/it] [ComfyUI] 52%|█████▏ | 13/25 [01:45<01:37, 8.14s/it] [ComfyUI] 56%|█████▌ | 14/25 [01:53<01:29, 8.13s/it] [ComfyUI] 60%|██████ | 15/25 [02:01<01:21, 8.12s/it] [ComfyUI] 64%|██████▍ | 16/25 [02:09<01:13, 8.12s/it] [ComfyUI] 68%|██████▊ | 17/25 [02:17<01:05, 8.13s/it] [ComfyUI] 72%|███████▏ | 18/25 [02:26<00:56, 8.14s/it] [ComfyUI] 76%|███████▌ | 19/25 [02:34<00:48, 8.13s/it] [ComfyUI] 80%|████████ | 20/25 [02:42<00:40, 8.14s/it] [ComfyUI] 84%|████████▍ | 21/25 [02:50<00:32, 8.13s/it] [ComfyUI] 88%|████████▊ | 22/25 [02:58<00:24, 8.13s/it] [ComfyUI] 92%|█████████▏| 23/25 [03:06<00:16, 8.12s/it] [ComfyUI] 96%|█████████▌| 24/25 [03:14<00:08, 8.13s/it] [ComfyUI] 100%|██████████| 25/25 [03:22<00:00, 8.13s/it] [ComfyUI] 100%|██████████| 25/25 [03:22<00:00, 8.12s/it] [ComfyUI] Allocated memory: memory=12.306 GB [ComfyUI] Max allocated memory: max_memory=20.619 GB [ComfyUI] Max reserved memory: max_reserved=22.875 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, 1.51s/it] [ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:03<00:01, 1.56s/it] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:03<00:00, 1.04s/it] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:03<00:00, 1.18s/it] [ComfyUI] [ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s] [ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 58.36it/s] [ComfyUI] [ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s] [ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:01<00:02, 1.22s/it] [ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:02<00:01, 1.27s/it] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:02<00:00, 1.18it/s] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:02<00:00, 1.05it/s] [ComfyUI] [ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s] [ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 66.36it/s] [ComfyUI] [ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s] [ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:00<00:00, 7.03it/s] [ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:00<00:00, 7.17it/s] [ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:00<00:00, 9.50it/s] [ComfyUI] [ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s] Executing node 44, title: Image Concatenate Multi, class type: ImageConcatMulti Executing node 53, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine [ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 96.34it/s] [ComfyUI] Prompt executed in 241.31 seconds outputs: {'39': {'text': ['101x768x416']}, '53': {'gifs': [{'filename': 'HunhuyanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 24.0}]}} ==================================== HunhuyanVideo_00001.png HunhuyanVideo_00001.mp4
Want to make some of these yourself?
Run this model
