lucataco
/
wan-2.1-1.3b-vid2vid
Wan 2.1 1.3b Video to Video. Wan is a powerful visual generation model developed by Tongyi Lab of Alibaba Group
Prediction
lucataco/wan-2.1-1.3b-vid2vid:93497665ID3aybzba7k5rmc0cnyynbneaztgStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- tiled
- prompt
- a puppy wearing black sunglasses
- cfg_scale
- 6
- num_frames
- 81
- input_video
- aspect_ratio
- 832x480
- negative_prompt
- low quality, blurry, distorted, disfigured, text, watermark
- frames_per_second
- 16
- denoising_strength
- 0.7
- num_inference_steps
- 30
{ "tiled": true, "prompt": "a puppy wearing black sunglasses", "cfg_scale": 6, "num_frames": 81, "input_video": "https://replicate.delivery/pbxt/MbUZEHGJFGoTaCAlbxPCAHvkmQrWOwAWGhb3o6xwdYRtoV7C/replicate-prediction-6jxv92xhadrma0cncbabf652xm.mp4", "aspect_ratio": "832x480", "negative_prompt": "low quality, blurry, distorted, disfigured, text, watermark", "frames_per_second": 16, "denoising_strength": 0.7, "num_inference_steps": 30 }Install Replicate’s Node.js client library:npm install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run lucataco/wan-2.1-1.3b-vid2vid using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/wan-2.1-1.3b-vid2vid:9349766527ed95fa6194dcca4cae3d497357e207025beb0b97fb0403420142b8", { input: { tiled: true, prompt: "a puppy wearing black sunglasses", cfg_scale: 6, num_frames: 81, input_video: "https://replicate.delivery/pbxt/MbUZEHGJFGoTaCAlbxPCAHvkmQrWOwAWGhb3o6xwdYRtoV7C/replicate-prediction-6jxv92xhadrma0cncbabf652xm.mp4", aspect_ratio: "832x480", negative_prompt: "low quality, blurry, distorted, disfigured, text, watermark", frames_per_second: 16, denoising_strength: 0.7, num_inference_steps: 30 } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:import replicateRun lucataco/wan-2.1-1.3b-vid2vid using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/wan-2.1-1.3b-vid2vid:9349766527ed95fa6194dcca4cae3d497357e207025beb0b97fb0403420142b8", input={ "tiled": True, "prompt": "a puppy wearing black sunglasses", "cfg_scale": 6, "num_frames": 81, "input_video": "https://replicate.delivery/pbxt/MbUZEHGJFGoTaCAlbxPCAHvkmQrWOwAWGhb3o6xwdYRtoV7C/replicate-prediction-6jxv92xhadrma0cncbabf652xm.mp4", "aspect_ratio": "832x480", "negative_prompt": "low quality, blurry, distorted, disfigured, text, watermark", "frames_per_second": 16, "denoising_strength": 0.7, "num_inference_steps": 30 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run lucataco/wan-2.1-1.3b-vid2vid 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": "9349766527ed95fa6194dcca4cae3d497357e207025beb0b97fb0403420142b8", "input": { "tiled": true, "prompt": "a puppy wearing black sunglasses", "cfg_scale": 6, "num_frames": 81, "input_video": "https://replicate.delivery/pbxt/MbUZEHGJFGoTaCAlbxPCAHvkmQrWOwAWGhb3o6xwdYRtoV7C/replicate-prediction-6jxv92xhadrma0cncbabf652xm.mp4", "aspect_ratio": "832x480", "negative_prompt": "low quality, blurry, distorted, disfigured, text, watermark", "frames_per_second": 16, "denoising_strength": 0.7, "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2025-04-02T18:03:40.537024Z", "created_at": "2025-04-02T18:01:26.681000Z", "data_removed": false, "error": null, "id": "3aybzba7k5rmc0cnyynbneaztg", "input": { "tiled": true, "prompt": "a puppy wearing black sunglasses", "cfg_scale": 6, "num_frames": 81, "input_video": "https://replicate.delivery/pbxt/MbUZEHGJFGoTaCAlbxPCAHvkmQrWOwAWGhb3o6xwdYRtoV7C/replicate-prediction-6jxv92xhadrma0cncbabf652xm.mp4", "aspect_ratio": "832x480", "negative_prompt": "low quality, blurry, distorted, disfigured, text, watermark", "frames_per_second": 16, "denoising_strength": 0.7, "num_inference_steps": 30 }, "logs": "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\nTo disable this warning, you can either:\n- Avoid using `tokenizers` before the fork if possible\n- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\nVAE encoding: 0%| | 0/9 [00:00<?, ?it/s]\nVAE encoding: 11%|█ | 1/9 [00:00<00:05, 1.58it/s]\nVAE encoding: 22%|██▏ | 2/9 [00:01<00:04, 1.58it/s]\nVAE encoding: 33%|███▎ | 3/9 [00:01<00:03, 1.58it/s]\nVAE encoding: 44%|████▍ | 4/9 [00:02<00:03, 1.57it/s]\nVAE encoding: 56%|█████▌ | 5/9 [00:03<00:02, 1.57it/s]\nVAE encoding: 67%|██████▋ | 6/9 [00:03<00:01, 1.58it/s]\nVAE encoding: 78%|███████▊ | 7/9 [00:04<00:01, 1.57it/s]\nVAE encoding: 89%|████████▉ | 8/9 [00:05<00:00, 1.57it/s]\nVAE encoding: 100%|██████████| 9/9 [00:05<00:00, 1.57it/s]\nVAE encoding: 100%|██████████| 9/9 [00:05<00:00, 1.57it/s]\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:03<01:44, 3.60s/it]\n 7%|▋ | 2/30 [00:07<01:40, 3.60s/it]\n 10%|█ | 3/30 [00:10<01:37, 3.60s/it]\n 13%|█▎ | 4/30 [00:14<01:33, 3.60s/it]\n 17%|█▋ | 5/30 [00:17<01:29, 3.60s/it]\n 20%|██ | 6/30 [00:21<01:26, 3.61s/it]\n 23%|██▎ | 7/30 [00:25<01:22, 3.60s/it]\n 27%|██▋ | 8/30 [00:28<01:19, 3.60s/it]\n 30%|███ | 9/30 [00:32<01:15, 3.60s/it]\n 33%|███▎ | 10/30 [00:36<01:12, 3.60s/it]\n 37%|███▋ | 11/30 [00:39<01:08, 3.61s/it]\n 40%|████ | 12/30 [00:43<01:04, 3.60s/it]\n 43%|████▎ | 13/30 [00:46<01:01, 3.60s/it]\n 47%|████▋ | 14/30 [00:50<00:57, 3.60s/it]\n 50%|█████ | 15/30 [00:54<00:54, 3.60s/it]\n 53%|█████▎ | 16/30 [00:57<00:50, 3.60s/it]\n 57%|█████▋ | 17/30 [01:01<00:46, 3.60s/it]\n 60%|██████ | 18/30 [01:04<00:43, 3.60s/it]\n 63%|██████▎ | 19/30 [01:08<00:39, 3.60s/it]\n 67%|██████▋ | 20/30 [01:12<00:35, 3.60s/it]\n 70%|███████ | 21/30 [01:15<00:32, 3.60s/it]\n 73%|███████▎ | 22/30 [01:19<00:28, 3.61s/it]\n 77%|███████▋ | 23/30 [01:22<00:25, 3.61s/it]\n 80%|████████ | 24/30 [01:26<00:21, 3.61s/it]\n 83%|████████▎ | 25/30 [01:30<00:18, 3.61s/it]\n 87%|████████▋ | 26/30 [01:33<00:14, 3.61s/it]\n 90%|█████████ | 27/30 [01:37<00:10, 3.61s/it]\n 93%|█████████▎| 28/30 [01:40<00:07, 3.61s/it]\n 97%|█████████▋| 29/30 [01:44<00:03, 3.61s/it]\n100%|██████████| 30/30 [01:48<00:00, 3.60s/it]\n100%|██████████| 30/30 [01:48<00:00, 3.60s/it]\nVAE decoding: 0%| | 0/9 [00:00<?, ?it/s]\nVAE decoding: 11%|█ | 1/9 [00:01<00:08, 1.12s/it]\nVAE decoding: 22%|██▏ | 2/9 [00:02<00:07, 1.11s/it]\nVAE decoding: 33%|███▎ | 3/9 [00:03<00:06, 1.11s/it]\nVAE decoding: 44%|████▍ | 4/9 [00:04<00:05, 1.11s/it]\nVAE decoding: 56%|█████▌ | 5/9 [00:05<00:04, 1.11s/it]\nVAE decoding: 67%|██████▋ | 6/9 [00:06<00:03, 1.11s/it]\nVAE decoding: 78%|███████▊ | 7/9 [00:07<00:02, 1.11s/it]\nVAE decoding: 89%|████████▉ | 8/9 [00:08<00:01, 1.11s/it]\nVAE decoding: 100%|██████████| 9/9 [00:09<00:00, 1.11s/it]\nVAE decoding: 100%|██████████| 9/9 [00:09<00:00, 1.11s/it]\nSaving video: 0%| | 0/81 [00:00<?, ?it/s]huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\nTo disable this warning, you can either:\n- Avoid using `tokenizers` before the fork if possible\n- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\nSaving video: 1%| | 1/81 [00:00<00:23, 3.33it/s]\nSaving video: 89%|████████▉ | 72/81 [00:00<00:00, 230.25it/s]\nSaving video: 100%|██████████| 81/81 [00:00<00:00, 186.99it/s]", "metrics": { "predict_time": 133.847287778, "total_time": 133.856024 }, "output": "https://replicate.delivery/xezq/8pFLomYr6wrQIJOYErDNrnZ5xwqQLiirI1yuB2ZmDSDfbZPKA/tmp_vurc1dr.mp4", "started_at": "2025-04-02T18:01:26.689737Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-fowizvzrn7x5glwymckz5k4gsffnz2kfshm6axaeqkzvqylmvorq", "get": "https://api.replicate.com/v1/predictions/3aybzba7k5rmc0cnyynbneaztg", "cancel": "https://api.replicate.com/v1/predictions/3aybzba7k5rmc0cnyynbneaztg/cancel" }, "version": "9349766527ed95fa6194dcca4cae3d497357e207025beb0b97fb0403420142b8" }Generated inhuggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) VAE encoding: 0%| | 0/9 [00:00<?, ?it/s] VAE encoding: 11%|█ | 1/9 [00:00<00:05, 1.58it/s] VAE encoding: 22%|██▏ | 2/9 [00:01<00:04, 1.58it/s] VAE encoding: 33%|███▎ | 3/9 [00:01<00:03, 1.58it/s] VAE encoding: 44%|████▍ | 4/9 [00:02<00:03, 1.57it/s] VAE encoding: 56%|█████▌ | 5/9 [00:03<00:02, 1.57it/s] VAE encoding: 67%|██████▋ | 6/9 [00:03<00:01, 1.58it/s] VAE encoding: 78%|███████▊ | 7/9 [00:04<00:01, 1.57it/s] VAE encoding: 89%|████████▉ | 8/9 [00:05<00:00, 1.57it/s] VAE encoding: 100%|██████████| 9/9 [00:05<00:00, 1.57it/s] VAE encoding: 100%|██████████| 9/9 [00:05<00:00, 1.57it/s] 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:03<01:44, 3.60s/it] 7%|▋ | 2/30 [00:07<01:40, 3.60s/it] 10%|█ | 3/30 [00:10<01:37, 3.60s/it] 13%|█▎ | 4/30 [00:14<01:33, 3.60s/it] 17%|█▋ | 5/30 [00:17<01:29, 3.60s/it] 20%|██ | 6/30 [00:21<01:26, 3.61s/it] 23%|██▎ | 7/30 [00:25<01:22, 3.60s/it] 27%|██▋ | 8/30 [00:28<01:19, 3.60s/it] 30%|███ | 9/30 [00:32<01:15, 3.60s/it] 33%|███▎ | 10/30 [00:36<01:12, 3.60s/it] 37%|███▋ | 11/30 [00:39<01:08, 3.61s/it] 40%|████ | 12/30 [00:43<01:04, 3.60s/it] 43%|████▎ | 13/30 [00:46<01:01, 3.60s/it] 47%|████▋ | 14/30 [00:50<00:57, 3.60s/it] 50%|█████ | 15/30 [00:54<00:54, 3.60s/it] 53%|█████▎ | 16/30 [00:57<00:50, 3.60s/it] 57%|█████▋ | 17/30 [01:01<00:46, 3.60s/it] 60%|██████ | 18/30 [01:04<00:43, 3.60s/it] 63%|██████▎ | 19/30 [01:08<00:39, 3.60s/it] 67%|██████▋ | 20/30 [01:12<00:35, 3.60s/it] 70%|███████ | 21/30 [01:15<00:32, 3.60s/it] 73%|███████▎ | 22/30 [01:19<00:28, 3.61s/it] 77%|███████▋ | 23/30 [01:22<00:25, 3.61s/it] 80%|████████ | 24/30 [01:26<00:21, 3.61s/it] 83%|████████▎ | 25/30 [01:30<00:18, 3.61s/it] 87%|████████▋ | 26/30 [01:33<00:14, 3.61s/it] 90%|█████████ | 27/30 [01:37<00:10, 3.61s/it] 93%|█████████▎| 28/30 [01:40<00:07, 3.61s/it] 97%|█████████▋| 29/30 [01:44<00:03, 3.61s/it] 100%|██████████| 30/30 [01:48<00:00, 3.60s/it] 100%|██████████| 30/30 [01:48<00:00, 3.60s/it] VAE decoding: 0%| | 0/9 [00:00<?, ?it/s] VAE decoding: 11%|█ | 1/9 [00:01<00:08, 1.12s/it] VAE decoding: 22%|██▏ | 2/9 [00:02<00:07, 1.11s/it] VAE decoding: 33%|███▎ | 3/9 [00:03<00:06, 1.11s/it] VAE decoding: 44%|████▍ | 4/9 [00:04<00:05, 1.11s/it] VAE decoding: 56%|█████▌ | 5/9 [00:05<00:04, 1.11s/it] VAE decoding: 67%|██████▋ | 6/9 [00:06<00:03, 1.11s/it] VAE decoding: 78%|███████▊ | 7/9 [00:07<00:02, 1.11s/it] VAE decoding: 89%|████████▉ | 8/9 [00:08<00:01, 1.11s/it] VAE decoding: 100%|██████████| 9/9 [00:09<00:00, 1.11s/it] VAE decoding: 100%|██████████| 9/9 [00:09<00:00, 1.11s/it] Saving video: 0%| | 0/81 [00:00<?, ?it/s]huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) Saving video: 1%| | 1/81 [00:00<00:23, 3.33it/s] Saving video: 89%|████████▉ | 72/81 [00:00<00:00, 230.25it/s] Saving video: 100%|██████████| 81/81 [00:00<00:00, 186.99it/s]Prediction
lucataco/wan-2.1-1.3b-vid2vid:93497665IDp4pryse6g1rmc0cnyysb22z7bmStatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- tiled
- prompt
- a dog made out of clay
- cfg_scale
- 6
- num_frames
- 81
- input_video
- aspect_ratio
- 832x480
- negative_prompt
- low quality, blurry, distorted, disfigured, text, watermark
- frames_per_second
- 16
- denoising_strength
- 0.7
- num_inference_steps
- 30
{ "tiled": true, "prompt": "a dog made out of clay", "cfg_scale": 6, "num_frames": 81, "input_video": "https://replicate.delivery/pbxt/MbUZEHGJFGoTaCAlbxPCAHvkmQrWOwAWGhb3o6xwdYRtoV7C/replicate-prediction-6jxv92xhadrma0cncbabf652xm.mp4", "aspect_ratio": "832x480", "negative_prompt": "low quality, blurry, distorted, disfigured, text, watermark", "frames_per_second": 16, "denoising_strength": 0.7, "num_inference_steps": 30 }Install Replicate’s Node.js client library:npm install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run lucataco/wan-2.1-1.3b-vid2vid using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/wan-2.1-1.3b-vid2vid:9349766527ed95fa6194dcca4cae3d497357e207025beb0b97fb0403420142b8", { input: { tiled: true, prompt: "a dog made out of clay", cfg_scale: 6, num_frames: 81, input_video: "https://replicate.delivery/pbxt/MbUZEHGJFGoTaCAlbxPCAHvkmQrWOwAWGhb3o6xwdYRtoV7C/replicate-prediction-6jxv92xhadrma0cncbabf652xm.mp4", aspect_ratio: "832x480", negative_prompt: "low quality, blurry, distorted, disfigured, text, watermark", frames_per_second: 16, denoising_strength: 0.7, num_inference_steps: 30 } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:import replicateRun lucataco/wan-2.1-1.3b-vid2vid using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/wan-2.1-1.3b-vid2vid:9349766527ed95fa6194dcca4cae3d497357e207025beb0b97fb0403420142b8", input={ "tiled": True, "prompt": "a dog made out of clay", "cfg_scale": 6, "num_frames": 81, "input_video": "https://replicate.delivery/pbxt/MbUZEHGJFGoTaCAlbxPCAHvkmQrWOwAWGhb3o6xwdYRtoV7C/replicate-prediction-6jxv92xhadrma0cncbabf652xm.mp4", "aspect_ratio": "832x480", "negative_prompt": "low quality, blurry, distorted, disfigured, text, watermark", "frames_per_second": 16, "denoising_strength": 0.7, "num_inference_steps": 30 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run lucataco/wan-2.1-1.3b-vid2vid 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": "9349766527ed95fa6194dcca4cae3d497357e207025beb0b97fb0403420142b8", "input": { "tiled": true, "prompt": "a dog made out of clay", "cfg_scale": 6, "num_frames": 81, "input_video": "https://replicate.delivery/pbxt/MbUZEHGJFGoTaCAlbxPCAHvkmQrWOwAWGhb3o6xwdYRtoV7C/replicate-prediction-6jxv92xhadrma0cncbabf652xm.mp4", "aspect_ratio": "832x480", "negative_prompt": "low quality, blurry, distorted, disfigured, text, watermark", "frames_per_second": 16, "denoising_strength": 0.7, "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2025-04-02T18:12:56.916564Z", "created_at": "2025-04-02T18:10:43.456000Z", "data_removed": false, "error": null, "id": "p4pryse6g1rmc0cnyysb22z7bm", "input": { "tiled": true, "prompt": "a dog made out of clay", "cfg_scale": 6, "num_frames": 81, "input_video": "https://replicate.delivery/pbxt/MbUZEHGJFGoTaCAlbxPCAHvkmQrWOwAWGhb3o6xwdYRtoV7C/replicate-prediction-6jxv92xhadrma0cncbabf652xm.mp4", "aspect_ratio": "832x480", "negative_prompt": "low quality, blurry, distorted, disfigured, text, watermark", "frames_per_second": 16, "denoising_strength": 0.7, "num_inference_steps": 30 }, "logs": "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\nTo disable this warning, you can either:\n- Avoid using `tokenizers` before the fork if possible\n- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\nVAE encoding: 0%| | 0/9 [00:00<?, ?it/s]\nVAE encoding: 11%|█ | 1/9 [00:00<00:05, 1.56it/s]\nVAE encoding: 22%|██▏ | 2/9 [00:01<00:04, 1.57it/s]\nVAE encoding: 33%|███▎ | 3/9 [00:01<00:03, 1.57it/s]\nVAE encoding: 44%|████▍ | 4/9 [00:02<00:03, 1.57it/s]\nVAE encoding: 56%|█████▌ | 5/9 [00:03<00:02, 1.57it/s]\nVAE encoding: 67%|██████▋ | 6/9 [00:03<00:01, 1.57it/s]\nVAE encoding: 78%|███████▊ | 7/9 [00:04<00:01, 1.57it/s]\nVAE encoding: 89%|████████▉ | 8/9 [00:05<00:00, 1.57it/s]\nVAE encoding: 100%|██████████| 9/9 [00:05<00:00, 1.57it/s]\nVAE encoding: 100%|██████████| 9/9 [00:05<00:00, 1.57it/s]\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:03<01:44, 3.61s/it]\n 7%|▋ | 2/30 [00:07<01:40, 3.60s/it]\n 10%|█ | 3/30 [00:10<01:37, 3.60s/it]\n 13%|█▎ | 4/30 [00:14<01:33, 3.61s/it]\n 17%|█▋ | 5/30 [00:18<01:30, 3.61s/it]\n 20%|██ | 6/30 [00:21<01:26, 3.61s/it]\n 23%|██▎ | 7/30 [00:25<01:23, 3.61s/it]\n 27%|██▋ | 8/30 [00:28<01:19, 3.61s/it]\n 30%|███ | 9/30 [00:32<01:15, 3.61s/it]\n 33%|███▎ | 10/30 [00:36<01:12, 3.61s/it]\n 37%|███▋ | 11/30 [00:39<01:08, 3.61s/it]\n 40%|████ | 12/30 [00:43<01:05, 3.62s/it]\n 43%|████▎ | 13/30 [00:46<01:01, 3.62s/it]\n 47%|████▋ | 14/30 [00:50<00:57, 3.62s/it]\n 50%|█████ | 15/30 [00:54<00:54, 3.62s/it]\n 53%|█████▎ | 16/30 [00:57<00:50, 3.62s/it]\n 57%|█████▋ | 17/30 [01:01<00:47, 3.62s/it]\n 60%|██████ | 18/30 [01:05<00:43, 3.61s/it]\n 63%|██████▎ | 19/30 [01:08<00:39, 3.61s/it]\n 67%|██████▋ | 20/30 [01:12<00:36, 3.61s/it]\n 70%|███████ | 21/30 [01:15<00:32, 3.61s/it]\n 73%|███████▎ | 22/30 [01:19<00:28, 3.60s/it]\n 77%|███████▋ | 23/30 [01:23<00:25, 3.60s/it]\n 80%|████████ | 24/30 [01:26<00:21, 3.60s/it]\n 83%|████████▎ | 25/30 [01:30<00:18, 3.60s/it]\n 87%|████████▋ | 26/30 [01:33<00:14, 3.61s/it]\n 90%|█████████ | 27/30 [01:37<00:10, 3.60s/it]\n 93%|█████████▎| 28/30 [01:41<00:07, 3.60s/it]\n 97%|█████████▋| 29/30 [01:44<00:03, 3.61s/it]\n100%|██████████| 30/30 [01:48<00:00, 3.60s/it]\n100%|██████████| 30/30 [01:48<00:00, 3.61s/it]\nVAE decoding: 0%| | 0/9 [00:00<?, ?it/s]\nVAE decoding: 11%|█ | 1/9 [00:01<00:08, 1.12s/it]\nVAE decoding: 22%|██▏ | 2/9 [00:02<00:07, 1.11s/it]\nVAE decoding: 33%|███▎ | 3/9 [00:03<00:06, 1.11s/it]\nVAE decoding: 44%|████▍ | 4/9 [00:04<00:05, 1.11s/it]\nVAE decoding: 56%|█████▌ | 5/9 [00:05<00:04, 1.11s/it]\nVAE decoding: 67%|██████▋ | 6/9 [00:06<00:03, 1.11s/it]\nVAE decoding: 78%|███████▊ | 7/9 [00:07<00:02, 1.11s/it]\nVAE decoding: 89%|████████▉ | 8/9 [00:08<00:01, 1.11s/it]\nVAE decoding: 100%|██████████| 9/9 [00:09<00:00, 1.11s/it]\nVAE decoding: 100%|██████████| 9/9 [00:09<00:00, 1.11s/it]\nSaving video: 0%| | 0/81 [00:00<?, ?it/s]huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\nTo disable this warning, you can either:\n- Avoid using `tokenizers` before the fork if possible\n- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\nSaving video: 1%| | 1/81 [00:00<00:23, 3.42it/s]\nSaving video: 91%|█████████▏| 74/81 [00:00<00:00, 222.41it/s]\nSaving video: 100%|██████████| 81/81 [00:00<00:00, 188.00it/s]", "metrics": { "predict_time": 133.450818946, "total_time": 133.460564 }, "output": "https://replicate.delivery/xezq/Tdz0wTX9xeQjLKUFrf3si0qdxRAsVmN6srgKSmwTIIPoAzeoA/tmp4j22p7qh.mp4", "started_at": "2025-04-02T18:10:43.465745Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-prrxu4subnyzwhsnjn4htccqln7ma4jesxtzxuceojq4jsfwavzq", "get": "https://api.replicate.com/v1/predictions/p4pryse6g1rmc0cnyysb22z7bm", "cancel": "https://api.replicate.com/v1/predictions/p4pryse6g1rmc0cnyysb22z7bm/cancel" }, "version": "9349766527ed95fa6194dcca4cae3d497357e207025beb0b97fb0403420142b8" }Generated inhuggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) VAE encoding: 0%| | 0/9 [00:00<?, ?it/s] VAE encoding: 11%|█ | 1/9 [00:00<00:05, 1.56it/s] VAE encoding: 22%|██▏ | 2/9 [00:01<00:04, 1.57it/s] VAE encoding: 33%|███▎ | 3/9 [00:01<00:03, 1.57it/s] VAE encoding: 44%|████▍ | 4/9 [00:02<00:03, 1.57it/s] VAE encoding: 56%|█████▌ | 5/9 [00:03<00:02, 1.57it/s] VAE encoding: 67%|██████▋ | 6/9 [00:03<00:01, 1.57it/s] VAE encoding: 78%|███████▊ | 7/9 [00:04<00:01, 1.57it/s] VAE encoding: 89%|████████▉ | 8/9 [00:05<00:00, 1.57it/s] VAE encoding: 100%|██████████| 9/9 [00:05<00:00, 1.57it/s] VAE encoding: 100%|██████████| 9/9 [00:05<00:00, 1.57it/s] 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:03<01:44, 3.61s/it] 7%|▋ | 2/30 [00:07<01:40, 3.60s/it] 10%|█ | 3/30 [00:10<01:37, 3.60s/it] 13%|█▎ | 4/30 [00:14<01:33, 3.61s/it] 17%|█▋ | 5/30 [00:18<01:30, 3.61s/it] 20%|██ | 6/30 [00:21<01:26, 3.61s/it] 23%|██▎ | 7/30 [00:25<01:23, 3.61s/it] 27%|██▋ | 8/30 [00:28<01:19, 3.61s/it] 30%|███ | 9/30 [00:32<01:15, 3.61s/it] 33%|███▎ | 10/30 [00:36<01:12, 3.61s/it] 37%|███▋ | 11/30 [00:39<01:08, 3.61s/it] 40%|████ | 12/30 [00:43<01:05, 3.62s/it] 43%|████▎ | 13/30 [00:46<01:01, 3.62s/it] 47%|████▋ | 14/30 [00:50<00:57, 3.62s/it] 50%|█████ | 15/30 [00:54<00:54, 3.62s/it] 53%|█████▎ | 16/30 [00:57<00:50, 3.62s/it] 57%|█████▋ | 17/30 [01:01<00:47, 3.62s/it] 60%|██████ | 18/30 [01:05<00:43, 3.61s/it] 63%|██████▎ | 19/30 [01:08<00:39, 3.61s/it] 67%|██████▋ | 20/30 [01:12<00:36, 3.61s/it] 70%|███████ | 21/30 [01:15<00:32, 3.61s/it] 73%|███████▎ | 22/30 [01:19<00:28, 3.60s/it] 77%|███████▋ | 23/30 [01:23<00:25, 3.60s/it] 80%|████████ | 24/30 [01:26<00:21, 3.60s/it] 83%|████████▎ | 25/30 [01:30<00:18, 3.60s/it] 87%|████████▋ | 26/30 [01:33<00:14, 3.61s/it] 90%|█████████ | 27/30 [01:37<00:10, 3.60s/it] 93%|█████████▎| 28/30 [01:41<00:07, 3.60s/it] 97%|█████████▋| 29/30 [01:44<00:03, 3.61s/it] 100%|██████████| 30/30 [01:48<00:00, 3.60s/it] 100%|██████████| 30/30 [01:48<00:00, 3.61s/it] VAE decoding: 0%| | 0/9 [00:00<?, ?it/s] VAE decoding: 11%|█ | 1/9 [00:01<00:08, 1.12s/it] VAE decoding: 22%|██▏ | 2/9 [00:02<00:07, 1.11s/it] VAE decoding: 33%|███▎ | 3/9 [00:03<00:06, 1.11s/it] VAE decoding: 44%|████▍ | 4/9 [00:04<00:05, 1.11s/it] VAE decoding: 56%|█████▌ | 5/9 [00:05<00:04, 1.11s/it] VAE decoding: 67%|██████▋ | 6/9 [00:06<00:03, 1.11s/it] VAE decoding: 78%|███████▊ | 7/9 [00:07<00:02, 1.11s/it] VAE decoding: 89%|████████▉ | 8/9 [00:08<00:01, 1.11s/it] VAE decoding: 100%|██████████| 9/9 [00:09<00:00, 1.11s/it] VAE decoding: 100%|██████████| 9/9 [00:09<00:00, 1.11s/it] Saving video: 0%| | 0/81 [00:00<?, ?it/s]huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) Saving video: 1%| | 1/81 [00:00<00:23, 3.42it/s] Saving video: 91%|█████████▏| 74/81 [00:00<00:00, 222.41it/s] Saving video: 100%|██████████| 81/81 [00:00<00:00, 188.00it/s]Prediction
lucataco/wan-2.1-1.3b-vid2vid:93497665IDja56031ezhrm80cnyyxb2mr8m0StatusSucceededSourceWebHardwareL40STotal durationCreatedInput
- tiled
- prompt
- a red balloon floating over a snowy mountain
- cfg_scale
- 6
- num_frames
- 81
- input_video
- aspect_ratio
- 480x832
- negative_prompt
- low quality, blurry, distorted, disfigured, text, watermark
- frames_per_second
- 16
- denoising_strength
- 0.7
- num_inference_steps
- 30
{ "tiled": true, "prompt": "a red balloon floating over a snowy mountain", "cfg_scale": 6, "num_frames": 81, "input_video": "https://replicate.delivery/pbxt/MlgIviRyvRHB6kml10ZKw7hHgnfYM81r7EAtKGmegUK6W2ee/replicate-prediction-tg0nyyenw5rmc0cny6xav9q4c4.mp4", "aspect_ratio": "480x832", "negative_prompt": "low quality, blurry, distorted, disfigured, text, watermark", "frames_per_second": 16, "denoising_strength": 0.7, "num_inference_steps": 30 }Install Replicate’s Node.js client library:npm install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run lucataco/wan-2.1-1.3b-vid2vid using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/wan-2.1-1.3b-vid2vid:9349766527ed95fa6194dcca4cae3d497357e207025beb0b97fb0403420142b8", { input: { tiled: true, prompt: "a red balloon floating over a snowy mountain", cfg_scale: 6, num_frames: 81, input_video: "https://replicate.delivery/pbxt/MlgIviRyvRHB6kml10ZKw7hHgnfYM81r7EAtKGmegUK6W2ee/replicate-prediction-tg0nyyenw5rmc0cny6xav9q4c4.mp4", aspect_ratio: "480x832", negative_prompt: "low quality, blurry, distorted, disfigured, text, watermark", frames_per_second: 16, denoising_strength: 0.7, num_inference_steps: 30 } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:import replicateRun lucataco/wan-2.1-1.3b-vid2vid using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/wan-2.1-1.3b-vid2vid:9349766527ed95fa6194dcca4cae3d497357e207025beb0b97fb0403420142b8", input={ "tiled": True, "prompt": "a red balloon floating over a snowy mountain", "cfg_scale": 6, "num_frames": 81, "input_video": "https://replicate.delivery/pbxt/MlgIviRyvRHB6kml10ZKw7hHgnfYM81r7EAtKGmegUK6W2ee/replicate-prediction-tg0nyyenw5rmc0cny6xav9q4c4.mp4", "aspect_ratio": "480x832", "negative_prompt": "low quality, blurry, distorted, disfigured, text, watermark", "frames_per_second": 16, "denoising_strength": 0.7, "num_inference_steps": 30 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run lucataco/wan-2.1-1.3b-vid2vid 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": "9349766527ed95fa6194dcca4cae3d497357e207025beb0b97fb0403420142b8", "input": { "tiled": true, "prompt": "a red balloon floating over a snowy mountain", "cfg_scale": 6, "num_frames": 81, "input_video": "https://replicate.delivery/pbxt/MlgIviRyvRHB6kml10ZKw7hHgnfYM81r7EAtKGmegUK6W2ee/replicate-prediction-tg0nyyenw5rmc0cny6xav9q4c4.mp4", "aspect_ratio": "480x832", "negative_prompt": "low quality, blurry, distorted, disfigured, text, watermark", "frames_per_second": 16, "denoising_strength": 0.7, "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2025-04-02T18:21:06.636075Z", "created_at": "2025-04-02T18:18:48.956000Z", "data_removed": false, "error": null, "id": "ja56031ezhrm80cnyyxb2mr8m0", "input": { "tiled": true, "prompt": "a red balloon floating over a snowy mountain", "cfg_scale": 6, "num_frames": 81, "input_video": "https://replicate.delivery/pbxt/MlgIviRyvRHB6kml10ZKw7hHgnfYM81r7EAtKGmegUK6W2ee/replicate-prediction-tg0nyyenw5rmc0cny6xav9q4c4.mp4", "aspect_ratio": "480x832", "negative_prompt": "low quality, blurry, distorted, disfigured, text, watermark", "frames_per_second": 16, "denoising_strength": 0.7, "num_inference_steps": 30 }, "logs": "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\nTo disable this warning, you can either:\n- Avoid using `tokenizers` before the fork if possible\n- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\nVAE encoding: 0%| | 0/12 [00:00<?, ?it/s]\nVAE encoding: 8%|▊ | 1/12 [00:00<00:06, 1.57it/s]\nVAE encoding: 17%|█▋ | 2/12 [00:01<00:04, 2.05it/s]\nVAE encoding: 25%|██▌ | 3/12 [00:01<00:05, 1.80it/s]\nVAE encoding: 33%|███▎ | 4/12 [00:02<00:03, 2.06it/s]\nVAE encoding: 42%|████▏ | 5/12 [00:02<00:03, 1.85it/s]\nVAE encoding: 50%|█████ | 6/12 [00:03<00:02, 2.07it/s]\nVAE encoding: 58%|█████▊ | 7/12 [00:03<00:02, 1.88it/s]\nVAE encoding: 67%|██████▋ | 8/12 [00:04<00:01, 2.07it/s]\nVAE encoding: 75%|███████▌ | 9/12 [00:04<00:01, 1.88it/s]\nVAE encoding: 83%|████████▎ | 10/12 [00:05<00:00, 2.08it/s]\nVAE encoding: 92%|█████████▏| 11/12 [00:05<00:00, 1.91it/s]\nVAE encoding: 100%|██████████| 12/12 [00:06<00:00, 2.11it/s]\nVAE encoding: 100%|██████████| 12/12 [00:06<00:00, 1.99it/s]\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:03<01:45, 3.65s/it]\n 7%|▋ | 2/30 [00:07<01:41, 3.64s/it]\n 10%|█ | 3/30 [00:10<01:38, 3.64s/it]\n 13%|█▎ | 4/30 [00:14<01:34, 3.64s/it]\n 17%|█▋ | 5/30 [00:18<01:30, 3.64s/it]\n 20%|██ | 6/30 [00:21<01:27, 3.64s/it]\n 23%|██▎ | 7/30 [00:25<01:23, 3.65s/it]\n 27%|██▋ | 8/30 [00:29<01:20, 3.65s/it]\n 30%|███ | 9/30 [00:32<01:16, 3.65s/it]\n 33%|███▎ | 10/30 [00:36<01:13, 3.65s/it]\n 37%|███▋ | 11/30 [00:40<01:09, 3.66s/it]\n 40%|████ | 12/30 [00:43<01:05, 3.66s/it]\n 43%|████▎ | 13/30 [00:47<01:02, 3.66s/it]\n 47%|████▋ | 14/30 [00:51<00:58, 3.67s/it]\n 50%|█████ | 15/30 [00:54<00:55, 3.67s/it]\n 53%|█████▎ | 16/30 [00:58<00:51, 3.67s/it]\n 57%|█████▋ | 17/30 [01:02<00:47, 3.67s/it]\n 60%|██████ | 18/30 [01:05<00:44, 3.67s/it]\n 63%|██████▎ | 19/30 [01:09<00:40, 3.67s/it]\n 67%|██████▋ | 20/30 [01:13<00:36, 3.68s/it]\n 70%|███████ | 21/30 [01:16<00:33, 3.68s/it]\n 73%|███████▎ | 22/30 [01:20<00:29, 3.68s/it]\n 77%|███████▋ | 23/30 [01:24<00:25, 3.69s/it]\n 80%|████████ | 24/30 [01:27<00:22, 3.69s/it]\n 83%|████████▎ | 25/30 [01:31<00:18, 3.68s/it]\n 87%|████████▋ | 26/30 [01:35<00:14, 3.68s/it]\n 90%|█████████ | 27/30 [01:38<00:11, 3.68s/it]\n 93%|█████████▎| 28/30 [01:42<00:07, 3.68s/it]\n 97%|█████████▋| 29/30 [01:46<00:03, 3.67s/it]\n100%|██████████| 30/30 [01:49<00:00, 3.67s/it]\n100%|██████████| 30/30 [01:49<00:00, 3.67s/it]\nVAE decoding: 0%| | 0/12 [00:00<?, ?it/s]\nVAE decoding: 8%|▊ | 1/12 [00:01<00:12, 1.15s/it]\nVAE decoding: 17%|█▋ | 2/12 [00:01<00:08, 1.15it/s]\nVAE decoding: 25%|██▌ | 3/12 [00:02<00:08, 1.02it/s]\nVAE decoding: 33%|███▎ | 4/12 [00:03<00:06, 1.18it/s]\nVAE decoding: 42%|████▏ | 5/12 [00:04<00:06, 1.06it/s]\nVAE decoding: 50%|█████ | 6/12 [00:05<00:05, 1.18it/s]\nVAE decoding: 58%|█████▊ | 7/12 [00:06<00:04, 1.07it/s]\nVAE decoding: 67%|██████▋ | 8/12 [00:07<00:03, 1.19it/s]\nVAE decoding: 75%|███████▌ | 9/12 [00:08<00:02, 1.08it/s]\nVAE decoding: 83%|████████▎ | 10/12 [00:08<00:01, 1.19it/s]\nVAE decoding: 92%|█████████▏| 11/12 [00:09<00:00, 1.10it/s]\nVAE decoding: 100%|██████████| 12/12 [00:10<00:00, 1.22it/s]\nVAE decoding: 100%|██████████| 12/12 [00:10<00:00, 1.14it/s]\nSaving video: 0%| | 0/81 [00:00<?, ?it/s]huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\nTo disable this warning, you can either:\n- Avoid using `tokenizers` before the fork if possible\n- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\nSaving video: 1%| | 1/81 [00:00<00:30, 2.59it/s]\nSaving video: 84%|████████▍ | 68/81 [00:00<00:00, 182.31it/s]\nSaving video: 100%|██████████| 81/81 [00:00<00:00, 158.07it/s]", "metrics": { "predict_time": 137.67046822, "total_time": 137.680075 }, "output": "https://replicate.delivery/xezq/63WXjFeYWk2ERSWamQTY2eQ5Ei2xmmaQ0crTXco90vpSIzeoA/tmpov5f23mb.mp4", "started_at": "2025-04-02T18:18:48.965607Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-bfzh6h37lnskbirbh62z2ex3n2hco5gpjsghu5hzakxxhdb36sqq", "get": "https://api.replicate.com/v1/predictions/ja56031ezhrm80cnyyxb2mr8m0", "cancel": "https://api.replicate.com/v1/predictions/ja56031ezhrm80cnyyxb2mr8m0/cancel" }, "version": "9349766527ed95fa6194dcca4cae3d497357e207025beb0b97fb0403420142b8" }Generated inhuggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) VAE encoding: 0%| | 0/12 [00:00<?, ?it/s] VAE encoding: 8%|▊ | 1/12 [00:00<00:06, 1.57it/s] VAE encoding: 17%|█▋ | 2/12 [00:01<00:04, 2.05it/s] VAE encoding: 25%|██▌ | 3/12 [00:01<00:05, 1.80it/s] VAE encoding: 33%|███▎ | 4/12 [00:02<00:03, 2.06it/s] VAE encoding: 42%|████▏ | 5/12 [00:02<00:03, 1.85it/s] VAE encoding: 50%|█████ | 6/12 [00:03<00:02, 2.07it/s] VAE encoding: 58%|█████▊ | 7/12 [00:03<00:02, 1.88it/s] VAE encoding: 67%|██████▋ | 8/12 [00:04<00:01, 2.07it/s] VAE encoding: 75%|███████▌ | 9/12 [00:04<00:01, 1.88it/s] VAE encoding: 83%|████████▎ | 10/12 [00:05<00:00, 2.08it/s] VAE encoding: 92%|█████████▏| 11/12 [00:05<00:00, 1.91it/s] VAE encoding: 100%|██████████| 12/12 [00:06<00:00, 2.11it/s] VAE encoding: 100%|██████████| 12/12 [00:06<00:00, 1.99it/s] 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:03<01:45, 3.65s/it] 7%|▋ | 2/30 [00:07<01:41, 3.64s/it] 10%|█ | 3/30 [00:10<01:38, 3.64s/it] 13%|█▎ | 4/30 [00:14<01:34, 3.64s/it] 17%|█▋ | 5/30 [00:18<01:30, 3.64s/it] 20%|██ | 6/30 [00:21<01:27, 3.64s/it] 23%|██▎ | 7/30 [00:25<01:23, 3.65s/it] 27%|██▋ | 8/30 [00:29<01:20, 3.65s/it] 30%|███ | 9/30 [00:32<01:16, 3.65s/it] 33%|███▎ | 10/30 [00:36<01:13, 3.65s/it] 37%|███▋ | 11/30 [00:40<01:09, 3.66s/it] 40%|████ | 12/30 [00:43<01:05, 3.66s/it] 43%|████▎ | 13/30 [00:47<01:02, 3.66s/it] 47%|████▋ | 14/30 [00:51<00:58, 3.67s/it] 50%|█████ | 15/30 [00:54<00:55, 3.67s/it] 53%|█████▎ | 16/30 [00:58<00:51, 3.67s/it] 57%|█████▋ | 17/30 [01:02<00:47, 3.67s/it] 60%|██████ | 18/30 [01:05<00:44, 3.67s/it] 63%|██████▎ | 19/30 [01:09<00:40, 3.67s/it] 67%|██████▋ | 20/30 [01:13<00:36, 3.68s/it] 70%|███████ | 21/30 [01:16<00:33, 3.68s/it] 73%|███████▎ | 22/30 [01:20<00:29, 3.68s/it] 77%|███████▋ | 23/30 [01:24<00:25, 3.69s/it] 80%|████████ | 24/30 [01:27<00:22, 3.69s/it] 83%|████████▎ | 25/30 [01:31<00:18, 3.68s/it] 87%|████████▋ | 26/30 [01:35<00:14, 3.68s/it] 90%|█████████ | 27/30 [01:38<00:11, 3.68s/it] 93%|█████████▎| 28/30 [01:42<00:07, 3.68s/it] 97%|█████████▋| 29/30 [01:46<00:03, 3.67s/it] 100%|██████████| 30/30 [01:49<00:00, 3.67s/it] 100%|██████████| 30/30 [01:49<00:00, 3.67s/it] VAE decoding: 0%| | 0/12 [00:00<?, ?it/s] VAE decoding: 8%|▊ | 1/12 [00:01<00:12, 1.15s/it] VAE decoding: 17%|█▋ | 2/12 [00:01<00:08, 1.15it/s] VAE decoding: 25%|██▌ | 3/12 [00:02<00:08, 1.02it/s] VAE decoding: 33%|███▎ | 4/12 [00:03<00:06, 1.18it/s] VAE decoding: 42%|████▏ | 5/12 [00:04<00:06, 1.06it/s] VAE decoding: 50%|█████ | 6/12 [00:05<00:05, 1.18it/s] VAE decoding: 58%|█████▊ | 7/12 [00:06<00:04, 1.07it/s] VAE decoding: 67%|██████▋ | 8/12 [00:07<00:03, 1.19it/s] VAE decoding: 75%|███████▌ | 9/12 [00:08<00:02, 1.08it/s] VAE decoding: 83%|████████▎ | 10/12 [00:08<00:01, 1.19it/s] VAE decoding: 92%|█████████▏| 11/12 [00:09<00:00, 1.10it/s] VAE decoding: 100%|██████████| 12/12 [00:10<00:00, 1.22it/s] VAE decoding: 100%|██████████| 12/12 [00:10<00:00, 1.14it/s] Saving video: 0%| | 0/81 [00:00<?, ?it/s]huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) Saving video: 1%| | 1/81 [00:00<00:30, 2.59it/s] Saving video: 84%|████████▍ | 68/81 [00:00<00:00, 182.31it/s] Saving video: 100%|██████████| 81/81 [00:00<00:00, 158.07it/s]Prediction
lucataco/wan-2.1-1.3b-vid2vid:93497665Input
- tiled
- prompt
- a polar bear playing a guitar in the snow
- cfg_scale
- 6
- num_frames
- 81
- input_video
- aspect_ratio
- 480x832
- negative_prompt
- low quality, blurry, distorted, disfigured, text, watermark
- frames_per_second
- 16
- denoising_strength
- 0.7
- num_inference_steps
- 30
{ "tiled": true, "prompt": "a polar bear playing a guitar in the snow", "cfg_scale": 6, "num_frames": 81, "input_video": "https://replicate.delivery/pbxt/MlgL4EPlBostGtrfHVQ0uRA7JNq7aIZCa3upvNGoYZcm8O5k/replicate-prediction-ypdk5b261hrme0cny83ahmcx78.mp4", "aspect_ratio": "480x832", "negative_prompt": "low quality, blurry, distorted, disfigured, text, watermark", "frames_per_second": 16, "denoising_strength": 0.7, "num_inference_steps": 30 }Install Replicate’s Node.js client library:npm install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run lucataco/wan-2.1-1.3b-vid2vid using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/wan-2.1-1.3b-vid2vid:9349766527ed95fa6194dcca4cae3d497357e207025beb0b97fb0403420142b8", { input: { tiled: true, prompt: "a polar bear playing a guitar in the snow", cfg_scale: 6, num_frames: 81, input_video: "https://replicate.delivery/pbxt/MlgL4EPlBostGtrfHVQ0uRA7JNq7aIZCa3upvNGoYZcm8O5k/replicate-prediction-ypdk5b261hrme0cny83ahmcx78.mp4", aspect_ratio: "480x832", negative_prompt: "low quality, blurry, distorted, disfigured, text, watermark", frames_per_second: 16, denoising_strength: 0.7, num_inference_steps: 30 } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:import replicateRun lucataco/wan-2.1-1.3b-vid2vid using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/wan-2.1-1.3b-vid2vid:9349766527ed95fa6194dcca4cae3d497357e207025beb0b97fb0403420142b8", input={ "tiled": True, "prompt": "a polar bear playing a guitar in the snow", "cfg_scale": 6, "num_frames": 81, "input_video": "https://replicate.delivery/pbxt/MlgL4EPlBostGtrfHVQ0uRA7JNq7aIZCa3upvNGoYZcm8O5k/replicate-prediction-ypdk5b261hrme0cny83ahmcx78.mp4", "aspect_ratio": "480x832", "negative_prompt": "low quality, blurry, distorted, disfigured, text, watermark", "frames_per_second": 16, "denoising_strength": 0.7, "num_inference_steps": 30 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run lucataco/wan-2.1-1.3b-vid2vid 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": "9349766527ed95fa6194dcca4cae3d497357e207025beb0b97fb0403420142b8", "input": { "tiled": true, "prompt": "a polar bear playing a guitar in the snow", "cfg_scale": 6, "num_frames": 81, "input_video": "https://replicate.delivery/pbxt/MlgL4EPlBostGtrfHVQ0uRA7JNq7aIZCa3upvNGoYZcm8O5k/replicate-prediction-ypdk5b261hrme0cny83ahmcx78.mp4", "aspect_ratio": "480x832", "negative_prompt": "low quality, blurry, distorted, disfigured, text, watermark", "frames_per_second": 16, "denoising_strength": 0.7, "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2025-04-02T18:23:17.550717Z", "created_at": "2025-04-02T18:21:02.785000Z", "data_removed": false, "error": null, "id": "xeyscp9sr5rmc0cnyyyb36qxcm", "input": { "tiled": true, "prompt": "a polar bear playing a guitar in the snow", "cfg_scale": 6, "num_frames": 81, "input_video": "https://replicate.delivery/pbxt/MlgL4EPlBostGtrfHVQ0uRA7JNq7aIZCa3upvNGoYZcm8O5k/replicate-prediction-ypdk5b261hrme0cny83ahmcx78.mp4", "aspect_ratio": "480x832", "negative_prompt": "low quality, blurry, distorted, disfigured, text, watermark", "frames_per_second": 16, "denoising_strength": 0.7, "num_inference_steps": 30 }, "logs": "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\nTo disable this warning, you can either:\n- Avoid using `tokenizers` before the fork if possible\n- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\nVAE encoding: 0%| | 0/12 [00:00<?, ?it/s]\nVAE encoding: 8%|▊ | 1/12 [00:00<00:06, 1.58it/s]\nVAE encoding: 17%|█▋ | 2/12 [00:01<00:04, 2.09it/s]\nVAE encoding: 25%|██▌ | 3/12 [00:01<00:04, 1.82it/s]\nVAE encoding: 33%|███▎ | 4/12 [00:02<00:03, 2.09it/s]\nVAE encoding: 42%|████▏ | 5/12 [00:02<00:03, 1.87it/s]\nVAE encoding: 50%|█████ | 6/12 [00:03<00:02, 2.09it/s]\nVAE encoding: 58%|█████▊ | 7/12 [00:03<00:02, 1.88it/s]\nVAE encoding: 67%|██████▋ | 8/12 [00:04<00:01, 2.08it/s]\nVAE encoding: 75%|███████▌ | 9/12 [00:04<00:01, 1.89it/s]\nVAE encoding: 83%|████████▎ | 10/12 [00:05<00:00, 2.08it/s]\nVAE encoding: 92%|█████████▏| 11/12 [00:05<00:00, 1.92it/s]\nVAE encoding: 100%|██████████| 12/12 [00:05<00:00, 2.13it/s]\nVAE encoding: 100%|██████████| 12/12 [00:05<00:00, 2.00it/s]\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:03<01:44, 3.59s/it]\n 7%|▋ | 2/30 [00:07<01:41, 3.61s/it]\n 10%|█ | 3/30 [00:10<01:37, 3.60s/it]\n 13%|█▎ | 4/30 [00:14<01:33, 3.61s/it]\n 17%|█▋ | 5/30 [00:18<01:30, 3.61s/it]\n 20%|██ | 6/30 [00:21<01:26, 3.61s/it]\n 23%|██▎ | 7/30 [00:25<01:23, 3.61s/it]\n 27%|██▋ | 8/30 [00:28<01:19, 3.61s/it]\n 30%|███ | 9/30 [00:32<01:15, 3.61s/it]\n 33%|███▎ | 10/30 [00:36<01:12, 3.61s/it]\n 37%|███▋ | 11/30 [00:39<01:08, 3.61s/it]\n 40%|████ | 12/30 [00:43<01:05, 3.61s/it]\n 43%|████▎ | 13/30 [00:46<01:01, 3.61s/it]\n 47%|████▋ | 14/30 [00:50<00:57, 3.62s/it]\n 50%|█████ | 15/30 [00:54<00:54, 3.62s/it]\n 53%|█████▎ | 16/30 [00:57<00:50, 3.62s/it]\n 57%|█████▋ | 17/30 [01:01<00:47, 3.62s/it]\n 60%|██████ | 18/30 [01:05<00:43, 3.62s/it]\n 63%|██████▎ | 19/30 [01:08<00:39, 3.62s/it]\n 67%|██████▋ | 20/30 [01:12<00:36, 3.62s/it]\n 70%|███████ | 21/30 [01:15<00:32, 3.62s/it]\n 73%|███████▎ | 22/30 [01:19<00:28, 3.62s/it]\n 77%|███████▋ | 23/30 [01:23<00:25, 3.62s/it]\n 80%|████████ | 24/30 [01:26<00:21, 3.63s/it]\n 83%|████████▎ | 25/30 [01:30<00:18, 3.63s/it]\n 87%|████████▋ | 26/30 [01:34<00:14, 3.62s/it]\n 90%|█████████ | 27/30 [01:37<00:10, 3.62s/it]\n 93%|█████████▎| 28/30 [01:41<00:07, 3.62s/it]\n 97%|█████████▋| 29/30 [01:44<00:03, 3.62s/it]\n100%|██████████| 30/30 [01:48<00:00, 3.62s/it]\n100%|██████████| 30/30 [01:48<00:00, 3.62s/it]\nVAE decoding: 0%| | 0/12 [00:00<?, ?it/s]\nVAE decoding: 8%|▊ | 1/12 [00:01<00:12, 1.14s/it]\nVAE decoding: 17%|█▋ | 2/12 [00:01<00:08, 1.17it/s]\nVAE decoding: 25%|██▌ | 3/12 [00:02<00:08, 1.02it/s]\nVAE decoding: 33%|███▎ | 4/12 [00:03<00:06, 1.18it/s]\nVAE decoding: 42%|████▏ | 5/12 [00:04<00:06, 1.05it/s]\nVAE decoding: 50%|█████ | 6/12 [00:05<00:05, 1.18it/s]\nVAE decoding: 58%|█████▊ | 7/12 [00:06<00:04, 1.06it/s]\nVAE decoding: 67%|██████▋ | 8/12 [00:07<00:03, 1.18it/s]\nVAE decoding: 75%|███████▌ | 9/12 [00:08<00:02, 1.07it/s]\nVAE decoding: 83%|████████▎ | 10/12 [00:08<00:01, 1.18it/s]\nVAE decoding: 92%|█████████▏| 11/12 [00:09<00:00, 1.09it/s]\nVAE decoding: 100%|██████████| 12/12 [00:10<00:00, 1.22it/s]\nVAE decoding: 100%|██████████| 12/12 [00:10<00:00, 1.14it/s]\nSaving video: 0%| | 0/81 [00:00<?, ?it/s]huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\nTo disable this warning, you can either:\n- Avoid using `tokenizers` before the fork if possible\n- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\nSaving video: 1%| | 1/81 [00:00<00:23, 3.36it/s]\nSaving video: 85%|████████▌ | 69/81 [00:00<00:00, 222.68it/s]\nSaving video: 100%|██████████| 81/81 [00:00<00:00, 187.73it/s]", "metrics": { "predict_time": 134.75340954, "total_time": 134.765717 }, "output": "https://replicate.delivery/xezq/X4w1KXvDtgImJRpCk2XB7meTGAkrKYYKY7iHXkdVQjtKlZPKA/tmpyzrbq4hz.mp4", "started_at": "2025-04-02T18:21:02.797308Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-o3cup2ko6gtyswtbrfxqeyqldwo76lbiq3o5ydpmntfr7c7yhyrq", "get": "https://api.replicate.com/v1/predictions/xeyscp9sr5rmc0cnyyyb36qxcm", "cancel": "https://api.replicate.com/v1/predictions/xeyscp9sr5rmc0cnyyyb36qxcm/cancel" }, "version": "9349766527ed95fa6194dcca4cae3d497357e207025beb0b97fb0403420142b8" }Generated inhuggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) VAE encoding: 0%| | 0/12 [00:00<?, ?it/s] VAE encoding: 8%|▊ | 1/12 [00:00<00:06, 1.58it/s] VAE encoding: 17%|█▋ | 2/12 [00:01<00:04, 2.09it/s] VAE encoding: 25%|██▌ | 3/12 [00:01<00:04, 1.82it/s] VAE encoding: 33%|███▎ | 4/12 [00:02<00:03, 2.09it/s] VAE encoding: 42%|████▏ | 5/12 [00:02<00:03, 1.87it/s] VAE encoding: 50%|█████ | 6/12 [00:03<00:02, 2.09it/s] VAE encoding: 58%|█████▊ | 7/12 [00:03<00:02, 1.88it/s] VAE encoding: 67%|██████▋ | 8/12 [00:04<00:01, 2.08it/s] VAE encoding: 75%|███████▌ | 9/12 [00:04<00:01, 1.89it/s] VAE encoding: 83%|████████▎ | 10/12 [00:05<00:00, 2.08it/s] VAE encoding: 92%|█████████▏| 11/12 [00:05<00:00, 1.92it/s] VAE encoding: 100%|██████████| 12/12 [00:05<00:00, 2.13it/s] VAE encoding: 100%|██████████| 12/12 [00:05<00:00, 2.00it/s] 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:03<01:44, 3.59s/it] 7%|▋ | 2/30 [00:07<01:41, 3.61s/it] 10%|█ | 3/30 [00:10<01:37, 3.60s/it] 13%|█▎ | 4/30 [00:14<01:33, 3.61s/it] 17%|█▋ | 5/30 [00:18<01:30, 3.61s/it] 20%|██ | 6/30 [00:21<01:26, 3.61s/it] 23%|██▎ | 7/30 [00:25<01:23, 3.61s/it] 27%|██▋ | 8/30 [00:28<01:19, 3.61s/it] 30%|███ | 9/30 [00:32<01:15, 3.61s/it] 33%|███▎ | 10/30 [00:36<01:12, 3.61s/it] 37%|███▋ | 11/30 [00:39<01:08, 3.61s/it] 40%|████ | 12/30 [00:43<01:05, 3.61s/it] 43%|████▎ | 13/30 [00:46<01:01, 3.61s/it] 47%|████▋ | 14/30 [00:50<00:57, 3.62s/it] 50%|█████ | 15/30 [00:54<00:54, 3.62s/it] 53%|█████▎ | 16/30 [00:57<00:50, 3.62s/it] 57%|█████▋ | 17/30 [01:01<00:47, 3.62s/it] 60%|██████ | 18/30 [01:05<00:43, 3.62s/it] 63%|██████▎ | 19/30 [01:08<00:39, 3.62s/it] 67%|██████▋ | 20/30 [01:12<00:36, 3.62s/it] 70%|███████ | 21/30 [01:15<00:32, 3.62s/it] 73%|███████▎ | 22/30 [01:19<00:28, 3.62s/it] 77%|███████▋ | 23/30 [01:23<00:25, 3.62s/it] 80%|████████ | 24/30 [01:26<00:21, 3.63s/it] 83%|████████▎ | 25/30 [01:30<00:18, 3.63s/it] 87%|████████▋ | 26/30 [01:34<00:14, 3.62s/it] 90%|█████████ | 27/30 [01:37<00:10, 3.62s/it] 93%|█████████▎| 28/30 [01:41<00:07, 3.62s/it] 97%|█████████▋| 29/30 [01:44<00:03, 3.62s/it] 100%|██████████| 30/30 [01:48<00:00, 3.62s/it] 100%|██████████| 30/30 [01:48<00:00, 3.62s/it] VAE decoding: 0%| | 0/12 [00:00<?, ?it/s] VAE decoding: 8%|▊ | 1/12 [00:01<00:12, 1.14s/it] VAE decoding: 17%|█▋ | 2/12 [00:01<00:08, 1.17it/s] VAE decoding: 25%|██▌ | 3/12 [00:02<00:08, 1.02it/s] VAE decoding: 33%|███▎ | 4/12 [00:03<00:06, 1.18it/s] VAE decoding: 42%|████▏ | 5/12 [00:04<00:06, 1.05it/s] VAE decoding: 50%|█████ | 6/12 [00:05<00:05, 1.18it/s] VAE decoding: 58%|█████▊ | 7/12 [00:06<00:04, 1.06it/s] VAE decoding: 67%|██████▋ | 8/12 [00:07<00:03, 1.18it/s] VAE decoding: 75%|███████▌ | 9/12 [00:08<00:02, 1.07it/s] VAE decoding: 83%|████████▎ | 10/12 [00:08<00:01, 1.18it/s] VAE decoding: 92%|█████████▏| 11/12 [00:09<00:00, 1.09it/s] VAE decoding: 100%|██████████| 12/12 [00:10<00:00, 1.22it/s] VAE decoding: 100%|██████████| 12/12 [00:10<00:00, 1.14it/s] Saving video: 0%| | 0/81 [00:00<?, ?it/s]huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) Saving video: 1%| | 1/81 [00:00<00:23, 3.36it/s] Saving video: 85%|████████▌ | 69/81 [00:00<00:00, 222.68it/s] Saving video: 100%|██████████| 81/81 [00:00<00:00, 187.73it/s]
Want to make some of these yourself?
Run this model