Official

wavespeedai / wan-2.1-t2v-480p

Accelerated inference for Wan 2.1 14B text to video, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.

Warm

Public
25.2K runs
$0.07 per second of video
Commercial use
GitHub
Weights
License

Run with an API

Playground API Examples README

Input

prompt

*string

Shift + Return to add a new line

A cat is doing an acrobatic dive into a swimming pool at the olympics, from a 10m high diving board, flips and spinsA cat is doing an acrobatic dive into a swimming pool at the olympics, from a 10m high diving board, flips and spins

Prompt for video generation

num_frames

integer

(minimum: 81, maximum: 100)

Number of video frames. 81 frames give the best results

Default: 81

aspect_ratio

string

Aspect ratio of video. 16:9 corresponds to 832x480px, and 9:16 is 480x832px

Default: "16:9"

frames_per_second

integer

(minimum: 5, maximum: 24)

Frames per second. Note that the pricing of this model is based on the video duration at 16 fps

Default: 16

fast_mode

string

Speed up generation with different levels of acceleration. Faster modes may degrade quality somewhat. The speedup is dependent on the content, so different videos may see different speedups.

Default: "Balanced"

sample_steps

integer

(minimum: 1, maximum: 40)

Number of generation steps. Fewer steps means faster generation, at the expensive of output quality. 30 steps is sufficient for most prompts

Default: 30

sample_guide_scale

number

(minimum: 0, maximum: 10)

Higher guide scale makes prompt adherence better, but can reduce variation

Default: 5

sample_shift

number

(minimum: 1, maximum: 10)

Sample shift factor

Default: 5

seed

integer

Random seed. Leave blank for random

lora_weights

string

Shift + Return to add a new line

Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'

lora_scale

number

Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.

Default: 1

Run this model in Node.js with one line of code:

npx create-replicate --model=wavespeedai/wan-2.1-t2v-480p

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment 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 wavespeedai/wan-2.1-t2v-480p using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  prompt: "A cat is doing an acrobatic dive into a swimming pool at the olympics, from a 10m high diving board, flips and spins",
  fast_mode: "Balanced",
  lora_scale: 1,
  num_frames: 81,
  aspect_ratio: "16:9",
  sample_shift: 5,
  sample_steps: 30,
  frames_per_second: 16,
  sample_guide_scale: 5
};

const output = await replicate.run("wavespeedai/wan-2.1-t2v-480p", { input });
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 replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run wavespeedai/wan-2.1-t2v-480p using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "wavespeedai/wan-2.1-t2v-480p",
    input={
        "prompt": "A cat is doing an acrobatic dive into a swimming pool at the olympics, from a 10m high diving board, flips and spins",
        "fast_mode": "Balanced",
        "lora_scale": 1,
        "num_frames": 81,
        "aspect_ratio": "16:9",
        "sample_shift": 5,
        "sample_steps": 30,
        "frames_per_second": 16,
        "sample_guide_scale": 5
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run wavespeedai/wan-2.1-t2v-480p 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 $'{
    "input": {
      "prompt": "A cat is doing an acrobatic dive into a swimming pool at the olympics, from a 10m high diving board, flips and spins",
      "fast_mode": "Balanced",
      "lora_scale": 1,
      "num_frames": 81,
      "aspect_ratio": "16:9",
      "sample_shift": 5,
      "sample_steps": 30,
      "frames_per_second": 16,
      "sample_guide_scale": 5
    }
  }' \
  https://api.replicate.com/v1/models/wavespeedai/wan-2.1-t2v-480p/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-03-03T11:10:17Z",
  "created_at": "2025-03-03T11:09:47.627000Z",
  "data_removed": false,
  "error": "",
  "id": "gh27r84yxdrma0cnbesbaaphr0",
  "input": {
    "prompt": "A cat is doing an acrobatic dive into a swimming pool at the olympics, from a 10m high diving board, flips and spins",
    "fast_mode": "Balanced",
    "num_frames": 81,
    "aspect_ratio": "16:9",
    "sample_shift": 5,
    "sample_steps": 30,
    "frames_per_second": 16,
    "sample_guide_scale": 5
  },
  "logs": "Moderating content...\r\nModeration complete in 0.20sec\r\nUsing seed: 1765621119\r\n0%|          | 0/30 [00:00<?, ?it/s]\r\n0%|          | 0/30 [00:00<?, ?it/s]\r\n0%|          | 0/30 [00:00<?, ?it/s]\r\n0%|          | 0/30 [00:00<?, ?it/s]\r\n0%|          | 0/30 [00:00<?, ?it/s]\r\n0%|          | 0/30 [00:00<?, ?it/s]\r\n0%|          | 0/30 [00:00<?, ?it/s]\r\n  0%|          | 0/30 [00:00<?, ?it/s]\r\n3%|▎         | 1/30 [00:01<00:33,  1.16s/it]\r\n3%|▎         | 1/30 [00:01<00:33,  1.16s/it]\r\n3%|▎         | 1/30 [00:01<00:33,  1.16s/it]\r\n3%|▎         | 1/30 [00:01<00:33,  1.17s/it]\r\n3%|▎         | 1/30 [00:01<00:33,  1.16s/it]\r\n3%|▎         | 1/30 [00:01<00:33,  1.16s/it]\r\n3%|▎         | 1/30 [00:01<00:33,  1.16s/it]\r\n  3%|▎         | 1/30 [00:01<00:33,  1.17s/it]\r\n7%|▋         | 2/30 [00:02<00:32,  1.17s/it]\r\n7%|▋         | 2/30 [00:02<00:32,  1.17s/it]\r\n7%|▋         | 2/30 [00:02<00:32,  1.17s/it]\r\n7%|▋         | 2/30 [00:02<00:32,  1.17s/it]\r\n7%|▋         | 2/30 [00:02<00:32,  1.17s/it]\r\n7%|▋         | 2/30 [00:02<00:32,  1.17s/it]\r\n7%|▋         | 2/30 [00:02<00:32,  1.17s/it]\r\n  7%|▋         | 2/30 [00:02<00:32,  1.17s/it]\r\n10%|█         | 3/30 [00:03<00:31,  1.17s/it]\r\n10%|█         | 3/30 [00:03<00:31,  1.17s/it]\r\n10%|█         | 3/30 [00:03<00:31,  1.17s/it]\r\n10%|█         | 3/30 [00:03<00:31,  1.17s/it]\r\n10%|█         | 3/30 [00:03<00:31,  1.17s/it]\r\n10%|█         | 3/30 [00:03<00:31,  1.17s/it]\r\n10%|█         | 3/30 [00:03<00:31,  1.17s/it]\r\n 10%|█         | 3/30 [00:03<00:31,  1.17s/it]\r\n13%|█▎        | 4/30 [00:04<00:30,  1.17s/it]\r\n13%|█▎        | 4/30 [00:04<00:30,  1.17s/it]\r\n13%|█▎        | 4/30 [00:04<00:30,  1.17s/it]\r\n13%|█▎        | 4/30 [00:04<00:30,  1.17s/it]\r\n13%|█▎        | 4/30 [00:04<00:30,  1.17s/it]\r\n13%|█▎        | 4/30 [00:04<00:30,  1.17s/it]\r\n13%|█▎        | 4/30 [00:04<00:30,  1.17s/it]\r\n 13%|█▎        | 4/30 [00:04<00:30,  1.17s/it]\r\n17%|█▋        | 5/30 [00:05<00:29,  1.17s/it]\r\n17%|█▋        | 5/30 [00:05<00:29,  1.17s/it]\r\n17%|█▋        | 5/30 [00:05<00:29,  1.17s/it]\r\n17%|█▋        | 5/30 [00:05<00:29,  1.17s/it]\r\n17%|█▋        | 5/30 [00:05<00:29,  1.17s/it]\r\n17%|█▋        | 5/30 [00:05<00:29,  1.17s/it]\r\n17%|█▋        | 5/30 [00:05<00:29,  1.17s/it]\r\n 17%|█▋        | 5/30 [00:05<00:29,  1.17s/it]\r\n20%|██        | 6/30 [00:07<00:28,  1.17s/it]\r\n20%|██        | 6/30 [00:07<00:28,  1.17s/it]\r\n20%|██        | 6/30 [00:07<00:28,  1.17s/it]\r\n20%|██        | 6/30 [00:07<00:28,  1.18s/it]\r\n20%|██        | 6/30 [00:07<00:28,  1.17s/it]\r\n20%|██        | 6/30 [00:07<00:28,  1.17s/it]\r\n 20%|██        | 6/30 [00:07<00:28,  1.18s/it]\r\n 20%|██        | 6/30 [00:07<00:28,  1.18s/it]\r\n23%|██▎       | 7/30 [00:08<00:27,  1.18s/it]\r\n23%|██▎       | 7/30 [00:08<00:27,  1.18s/it]\r\n23%|██▎       | 7/30 [00:08<00:27,  1.18s/it]\r\n23%|██▎       | 7/30 [00:08<00:27,  1.18s/it]\r\n23%|██▎       | 7/30 [00:08<00:27,  1.18s/it]\r\n23%|██▎       | 7/30 [00:08<00:27,  1.18s/it]\r\n 23%|██▎       | 7/30 [00:08<00:27,  1.18s/it]\r\n 23%|██▎       | 7/30 [00:08<00:27,  1.18s/it]\r\n27%|██▋       | 8/30 [00:09<00:25,  1.18s/it]\r\n27%|██▋       | 8/30 [00:09<00:25,  1.18s/it]\r\n27%|██▋       | 8/30 [00:09<00:25,  1.18s/it]\r\n27%|██▋       | 8/30 [00:09<00:25,  1.18s/it]\r\n27%|██▋       | 8/30 [00:09<00:25,  1.18s/it]\r\n27%|██▋       | 8/30 [00:09<00:25,  1.18s/it]\r\n27%|██▋       | 8/30 [00:09<00:25,  1.18s/it]\r\n 27%|██▋       | 8/30 [00:09<00:25,  1.18s/it]\r\n33%|███▎      | 10/30 [00:10<00:18,  1.10it/s]\r\n33%|███▎      | 10/30 [00:10<00:18,  1.10it/s]\r\n33%|███▎      | 10/30 [00:10<00:18,  1.10it/s]\r\n33%|███▎      | 10/30 [00:10<00:18,  1.10it/s]\r\n33%|███▎      | 10/30 [00:10<00:18,  1.10it/s]\r\n33%|███▎      | 10/30 [00:10<00:18,  1.10it/s]\r\n33%|███▎      | 10/30 [00:10<00:18,  1.10it/s]\r\n 33%|███▎      | 10/30 [00:10<00:18,  1.10it/s]\r\n40%|████      | 12/30 [00:11<00:14,  1.27it/s]\r\n40%|████      | 12/30 [00:11<00:14,  1.27it/s]\r\n40%|████      | 12/30 [00:11<00:14,  1.27it/s]\r\n40%|████      | 12/30 [00:11<00:14,  1.27it/s]\r\n40%|████      | 12/30 [00:11<00:14,  1.27it/s]\r\n40%|████      | 12/30 [00:11<00:14,  1.27it/s]\r\n40%|████      | 12/30 [00:11<00:14,  1.27it/s]\r\n 40%|████      | 12/30 [00:11<00:14,  1.27it/s]\r\n47%|████▋     | 14/30 [00:13<00:11,  1.38it/s]\r\n47%|████▋     | 14/30 [00:13<00:11,  1.38it/s]\r\n47%|████▋     | 14/30 [00:13<00:11,  1.38it/s]\r\n47%|████▋     | 14/30 [00:13<00:11,  1.38it/s]\r\n47%|████▋     | 14/30 [00:13<00:11,  1.38it/s]\r\n47%|████▋     | 14/30 [00:13<00:11,  1.38it/s]\r\n47%|████▋     | 14/30 [00:13<00:11,  1.38it/s]\r\n 47%|████▋     | 14/30 [00:13<00:11,  1.38it/s]\r\n53%|█████▎    | 16/30 [00:14<00:09,  1.46it/s]\r\n53%|█████▎    | 16/30 [00:14<00:09,  1.46it/s]\r\n53%|█████▎    | 16/30 [00:14<00:09,  1.46it/s]\r\n53%|█████▎    | 16/30 [00:14<00:09,  1.46it/s]\r\n53%|█████▎    | 16/30 [00:14<00:09,  1.46it/s]\r\n53%|█████▎    | 16/30 [00:14<00:09,  1.46it/s]\r\n53%|█████▎    | 16/30 [00:14<00:09,  1.46it/s]\r\n 53%|█████▎    | 16/30 [00:14<00:09,  1.46it/s]\r\n60%|██████    | 18/30 [00:15<00:07,  1.52it/s]\r\n60%|██████    | 18/30 [00:15<00:07,  1.52it/s]\r\n60%|██████    | 18/30 [00:15<00:07,  1.52it/s]\r\n60%|██████    | 18/30 [00:15<00:07,  1.52it/s]\r\n60%|██████    | 18/30 [00:15<00:07,  1.52it/s]\r\n60%|██████    | 18/30 [00:15<00:07,  1.52it/s]\r\n60%|██████    | 18/30 [00:15<00:07,  1.52it/s]\r\n 60%|██████    | 18/30 [00:15<00:07,  1.52it/s]\r\n67%|██████▋   | 20/30 [00:16<00:06,  1.55it/s]\r\n67%|██████▋   | 20/30 [00:16<00:06,  1.55it/s]\r\n67%|██████▋   | 20/30 [00:16<00:06,  1.55it/s]\r\n67%|██████▋   | 20/30 [00:16<00:06,  1.55it/s]\r\n67%|██████▋   | 20/30 [00:16<00:06,  1.55it/s]\r\n67%|██████▋   | 20/30 [00:16<00:06,  1.55it/s]\r\n 67%|██████▋   | 20/30 [00:16<00:06,  1.55it/s]\r\n 67%|██████▋   | 20/30 [00:16<00:06,  1.55it/s]\r\n73%|███████▎  | 22/30 [00:17<00:05,  1.58it/s]\r\n73%|███████▎  | 22/30 [00:17<00:05,  1.58it/s]\r\n73%|███████▎  | 22/30 [00:17<00:05,  1.58it/s]\r\n73%|███████▎  | 22/30 [00:17<00:05,  1.58it/s]\r\n73%|███████▎  | 22/30 [00:17<00:05,  1.58it/s]\r\n73%|███████▎  | 22/30 [00:17<00:05,  1.58it/s]\r\n73%|███████▎  | 22/30 [00:17<00:05,  1.58it/s]\r\n 73%|███████▎  | 22/30 [00:17<00:05,  1.58it/s]\r\n77%|███████▋  | 23/30 [00:19<00:05,  1.36it/s]\r\n77%|███████▋  | 23/30 [00:19<00:05,  1.36it/s]\r\n77%|███████▋  | 23/30 [00:19<00:05,  1.36it/s]\r\n77%|███████▋  | 23/30 [00:19<00:05,  1.36it/s]\r\n77%|███████▋  | 23/30 [00:19<00:05,  1.36it/s]\r\n77%|███████▋  | 23/30 [00:19<00:05,  1.36it/s]\r\n77%|███████▋  | 23/30 [00:19<00:05,  1.36it/s]\r\n 77%|███████▋  | 23/30 [00:19<00:05,  1.36it/s]\r\n80%|████████  | 24/30 [00:20<00:04,  1.21it/s]\r\n80%|████████  | 24/30 [00:20<00:04,  1.21it/s]\r\n80%|████████  | 24/30 [00:20<00:04,  1.21it/s]\r\n80%|████████  | 24/30 [00:20<00:04,  1.21it/s]\r\n80%|████████  | 24/30 [00:20<00:04,  1.21it/s]\r\n80%|████████  | 24/30 [00:20<00:04,  1.21it/s]\r\n80%|████████  | 24/30 [00:20<00:04,  1.21it/s]\r\n 80%|████████  | 24/30 [00:20<00:04,  1.21it/s]\r\n83%|████████▎ | 25/30 [00:21<00:04,  1.10it/s]\r\n83%|████████▎ | 25/30 [00:21<00:04,  1.10it/s]\r\n83%|████████▎ | 25/30 [00:21<00:04,  1.10it/s]\r\n83%|████████▎ | 25/30 [00:21<00:04,  1.10it/s]\r\n83%|████████▎ | 25/30 [00:21<00:04,  1.10it/s]\r\n83%|████████▎ | 25/30 [00:21<00:04,  1.10it/s]\r\n83%|████████▎ | 25/30 [00:21<00:04,  1.10it/s]\r\n 83%|████████▎ | 25/30 [00:21<00:04,  1.10it/s]\r\n87%|████████▋ | 26/30 [00:22<00:03,  1.03it/s]\r\n87%|████████▋ | 26/30 [00:22<00:03,  1.03it/s]\r\n87%|████████▋ | 26/30 [00:22<00:03,  1.03it/s]\r\n87%|████████▋ | 26/30 [00:22<00:03,  1.03it/s]\r\n87%|████████▋ | 26/30 [00:22<00:03,  1.03it/s]\r\n87%|████████▋ | 26/30 [00:22<00:03,  1.03it/s]\r\n87%|████████▋ | 26/30 [00:22<00:03,  1.03it/s]\r\n 87%|████████▋ | 26/30 [00:22<00:03,  1.03it/s]\r\n90%|█████████ | 27/30 [00:23<00:03,  1.03s/it]\r\n90%|█████████ | 27/30 [00:23<00:03,  1.03s/it]\r\n90%|█████████ | 27/30 [00:23<00:03,  1.03s/it]\r\n90%|█████████ | 27/30 [00:23<00:03,  1.03s/it]\r\n90%|█████████ | 27/30 [00:23<00:03,  1.03s/it]\r\n90%|█████████ | 27/30 [00:23<00:03,  1.03s/it]\r\n90%|█████████ | 27/30 [00:23<00:03,  1.03s/it]\r\n 90%|█████████ | 27/30 [00:23<00:03,  1.03s/it]\r\n93%|█████████▎| 28/30 [00:25<00:02,  1.07s/it]\r\n93%|█████████▎| 28/30 [00:25<00:02,  1.07s/it]\r\n93%|█████████▎| 28/30 [00:25<00:02,  1.07s/it]\r\n93%|█████████▎| 28/30 [00:25<00:02,  1.07s/it]\r\n93%|█████████▎| 28/30 [00:25<00:02,  1.07s/it]\r\n93%|█████████▎| 28/30 [00:25<00:02,  1.07s/it]\r\n93%|█████████▎| 28/30 [00:25<00:02,  1.07s/it]\r\n 93%|█████████▎| 28/30 [00:25<00:02,  1.07s/it]\r\n97%|█████████▋| 29/30 [00:26<00:01,  1.10s/it]\r\n97%|█████████▋| 29/30 [00:26<00:01,  1.10s/it]\r\n97%|█████████▋| 29/30 [00:26<00:01,  1.10s/it]\r\n97%|█████████▋| 29/30 [00:26<00:01,  1.10s/it]\r\n97%|█████████▋| 29/30 [00:26<00:01,  1.10s/it]\r\n97%|█████████▋| 29/30 [00:26<00:01,  1.10s/it]\r\n97%|█████████▋| 29/30 [00:26<00:01,  1.10s/it]\r\n 97%|█████████▋| 29/30 [00:26<00:01,  1.10s/it]\r\n100%|██████████| 30/30 [00:27<00:00,  1.12s/it]\r\n100%|██████████| 30/30 [00:27<00:00,  1.12s/it]\r\n100%|██████████| 30/30 [00:27<00:00,  1.12s/it]\r\n100%|██████████| 30/30 [00:27<00:00,  1.12s/it]\r\n100%|██████████| 30/30 [00:27<00:00,  1.12s/it]\r\n100%|██████████| 30/30 [00:27<00:00,  1.12s/it]\r\n100%|██████████| 30/30 [00:27<00:00,  1.12s/it]\r\n100%|██████████| 30/30 [00:27<00:00,  1.10it/s]\r\n100%|██████████| 30/30 [00:27<00:00,  1.10it/s]\r\n100%|██████████| 30/30 [00:27<00:00,  1.10it/s]\r\n100%|██████████| 30/30 [00:27<00:00,  1.10it/s]\r\n100%|██████████| 30/30 [00:27<00:00,  1.10it/s]\r\n100%|██████████| 30/30 [00:27<00:00,  1.10it/s]\r\n100%|██████████| 30/30 [00:27<00:00,  1.10it/s]\r\n100%|██████████| 30/30 [00:27<00:00,  1.12s/it]\r\n100%|██████████| 30/30 [00:27<00:00,  1.10it/s]\r\nTime elapsed: 29.23s\r\nSaving generated video to output.mp4",
  "metrics": {
    "predict_time": 30.174848852,
    "total_time": 29.373
  },
  "output": "https://replicate.delivery/xezq/1Cr8exFBJ9X5BqOvabmkoxe5eHC2FFE6GDlw8Xva064yAopoA/output.mp4",
  "started_at": "2025-03-03T11:09:47Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-nbjkkjkhbxljcr4b6go3wywp4udmmuizilyrobxzb3ni5zqjf3za",
    "get": "https://api.replicate.com/v1/predictions/gh27r84yxdrma0cnbesbaaphr0",
    "cancel": "https://api.replicate.com/v1/predictions/gh27r84yxdrma0cnbesbaaphr0/cancel"
  },
  "version": "hidden"
}

Generated in

30.2 seconds

Tweak it ShareReport

Moderating content...
Moderation complete in 0.20sec
Using seed: 1765621119
0%|          | 0/30 [00:00<?, ?it/s]
0%|          | 0/30 [00:00<?, ?it/s]
0%|          | 0/30 [00:00<?, ?it/s]
0%|          | 0/30 [00:00<?, ?it/s]
0%|          | 0/30 [00:00<?, ?it/s]
0%|          | 0/30 [00:00<?, ?it/s]
0%|          | 0/30 [00:00<?, ?it/s]
  0%|          | 0/30 [00:00<?, ?it/s]
3%|▎         | 1/30 [00:01<00:33,  1.16s/it]
3%|▎         | 1/30 [00:01<00:33,  1.16s/it]
3%|▎         | 1/30 [00:01<00:33,  1.16s/it]
3%|▎         | 1/30 [00:01<00:33,  1.17s/it]
3%|▎         | 1/30 [00:01<00:33,  1.16s/it]
3%|▎         | 1/30 [00:01<00:33,  1.16s/it]
3%|▎         | 1/30 [00:01<00:33,  1.16s/it]
  3%|▎         | 1/30 [00:01<00:33,  1.17s/it]
7%|▋         | 2/30 [00:02<00:32,  1.17s/it]
7%|▋         | 2/30 [00:02<00:32,  1.17s/it]
7%|▋         | 2/30 [00:02<00:32,  1.17s/it]
7%|▋         | 2/30 [00:02<00:32,  1.17s/it]
7%|▋         | 2/30 [00:02<00:32,  1.17s/it]
7%|▋         | 2/30 [00:02<00:32,  1.17s/it]
7%|▋         | 2/30 [00:02<00:32,  1.17s/it]
  7%|▋         | 2/30 [00:02<00:32,  1.17s/it]
10%|█         | 3/30 [00:03<00:31,  1.17s/it]
10%|█         | 3/30 [00:03<00:31,  1.17s/it]
10%|█         | 3/30 [00:03<00:31,  1.17s/it]
10%|█         | 3/30 [00:03<00:31,  1.17s/it]
10%|█         | 3/30 [00:03<00:31,  1.17s/it]
10%|█         | 3/30 [00:03<00:31,  1.17s/it]
10%|█         | 3/30 [00:03<00:31,  1.17s/it]
 10%|█         | 3/30 [00:03<00:31,  1.17s/it]
13%|█▎        | 4/30 [00:04<00:30,  1.17s/it]
13%|█▎        | 4/30 [00:04<00:30,  1.17s/it]
13%|█▎        | 4/30 [00:04<00:30,  1.17s/it]
13%|█▎        | 4/30 [00:04<00:30,  1.17s/it]
13%|█▎        | 4/30 [00:04<00:30,  1.17s/it]
13%|█▎        | 4/30 [00:04<00:30,  1.17s/it]
13%|█▎        | 4/30 [00:04<00:30,  1.17s/it]
 13%|█▎        | 4/30 [00:04<00:30,  1.17s/it]
17%|█▋        | 5/30 [00:05<00:29,  1.17s/it]
17%|█▋        | 5/30 [00:05<00:29,  1.17s/it]
17%|█▋        | 5/30 [00:05<00:29,  1.17s/it]
17%|█▋        | 5/30 [00:05<00:29,  1.17s/it]
17%|█▋        | 5/30 [00:05<00:29,  1.17s/it]
17%|█▋        | 5/30 [00:05<00:29,  1.17s/it]
17%|█▋        | 5/30 [00:05<00:29,  1.17s/it]
 17%|█▋        | 5/30 [00:05<00:29,  1.17s/it]
20%|██        | 6/30 [00:07<00:28,  1.17s/it]
20%|██        | 6/30 [00:07<00:28,  1.17s/it]
20%|██        | 6/30 [00:07<00:28,  1.17s/it]
20%|██        | 6/30 [00:07<00:28,  1.18s/it]
20%|██        | 6/30 [00:07<00:28,  1.17s/it]
20%|██        | 6/30 [00:07<00:28,  1.17s/it]
 20%|██        | 6/30 [00:07<00:28,  1.18s/it]
 20%|██        | 6/30 [00:07<00:28,  1.18s/it]
23%|██▎       | 7/30 [00:08<00:27,  1.18s/it]
23%|██▎       | 7/30 [00:08<00:27,  1.18s/it]
23%|██▎       | 7/30 [00:08<00:27,  1.18s/it]
23%|██▎       | 7/30 [00:08<00:27,  1.18s/it]
23%|██▎       | 7/30 [00:08<00:27,  1.18s/it]
23%|██▎       | 7/30 [00:08<00:27,  1.18s/it]
 23%|██▎       | 7/30 [00:08<00:27,  1.18s/it]
 23%|██▎       | 7/30 [00:08<00:27,  1.18s/it]
27%|██▋       | 8/30 [00:09<00:25,  1.18s/it]
27%|██▋       | 8/30 [00:09<00:25,  1.18s/it]
27%|██▋       | 8/30 [00:09<00:25,  1.18s/it]
27%|██▋       | 8/30 [00:09<00:25,  1.18s/it]
27%|██▋       | 8/30 [00:09<00:25,  1.18s/it]
27%|██▋       | 8/30 [00:09<00:25,  1.18s/it]
27%|██▋       | 8/30 [00:09<00:25,  1.18s/it]
 27%|██▋       | 8/30 [00:09<00:25,  1.18s/it]
33%|███▎      | 10/30 [00:10<00:18,  1.10it/s]
33%|███▎      | 10/30 [00:10<00:18,  1.10it/s]
33%|███▎      | 10/30 [00:10<00:18,  1.10it/s]
33%|███▎      | 10/30 [00:10<00:18,  1.10it/s]
33%|███▎      | 10/30 [00:10<00:18,  1.10it/s]
33%|███▎      | 10/30 [00:10<00:18,  1.10it/s]
33%|███▎      | 10/30 [00:10<00:18,  1.10it/s]
 33%|███▎      | 10/30 [00:10<00:18,  1.10it/s]
40%|████      | 12/30 [00:11<00:14,  1.27it/s]
40%|████      | 12/30 [00:11<00:14,  1.27it/s]
40%|████      | 12/30 [00:11<00:14,  1.27it/s]
40%|████      | 12/30 [00:11<00:14,  1.27it/s]
40%|████      | 12/30 [00:11<00:14,  1.27it/s]
40%|████      | 12/30 [00:11<00:14,  1.27it/s]
40%|████      | 12/30 [00:11<00:14,  1.27it/s]
 40%|████      | 12/30 [00:11<00:14,  1.27it/s]
47%|████▋     | 14/30 [00:13<00:11,  1.38it/s]
47%|████▋     | 14/30 [00:13<00:11,  1.38it/s]
47%|████▋     | 14/30 [00:13<00:11,  1.38it/s]
47%|████▋     | 14/30 [00:13<00:11,  1.38it/s]
47%|████▋     | 14/30 [00:13<00:11,  1.38it/s]
47%|████▋     | 14/30 [00:13<00:11,  1.38it/s]
47%|████▋     | 14/30 [00:13<00:11,  1.38it/s]
 47%|████▋     | 14/30 [00:13<00:11,  1.38it/s]
53%|█████▎    | 16/30 [00:14<00:09,  1.46it/s]
53%|█████▎    | 16/30 [00:14<00:09,  1.46it/s]
53%|█████▎    | 16/30 [00:14<00:09,  1.46it/s]
53%|█████▎    | 16/30 [00:14<00:09,  1.46it/s]
53%|█████▎    | 16/30 [00:14<00:09,  1.46it/s]
53%|█████▎    | 16/30 [00:14<00:09,  1.46it/s]
53%|█████▎    | 16/30 [00:14<00:09,  1.46it/s]
 53%|█████▎    | 16/30 [00:14<00:09,  1.46it/s]
60%|██████    | 18/30 [00:15<00:07,  1.52it/s]
60%|██████    | 18/30 [00:15<00:07,  1.52it/s]
60%|██████    | 18/30 [00:15<00:07,  1.52it/s]
60%|██████    | 18/30 [00:15<00:07,  1.52it/s]
60%|██████    | 18/30 [00:15<00:07,  1.52it/s]
60%|██████    | 18/30 [00:15<00:07,  1.52it/s]
60%|██████    | 18/30 [00:15<00:07,  1.52it/s]
 60%|██████    | 18/30 [00:15<00:07,  1.52it/s]
67%|██████▋   | 20/30 [00:16<00:06,  1.55it/s]
67%|██████▋   | 20/30 [00:16<00:06,  1.55it/s]
67%|██████▋   | 20/30 [00:16<00:06,  1.55it/s]
67%|██████▋   | 20/30 [00:16<00:06,  1.55it/s]
67%|██████▋   | 20/30 [00:16<00:06,  1.55it/s]
67%|██████▋   | 20/30 [00:16<00:06,  1.55it/s]
 67%|██████▋   | 20/30 [00:16<00:06,  1.55it/s]
 67%|██████▋   | 20/30 [00:16<00:06,  1.55it/s]
73%|███████▎  | 22/30 [00:17<00:05,  1.58it/s]
73%|███████▎  | 22/30 [00:17<00:05,  1.58it/s]
73%|███████▎  | 22/30 [00:17<00:05,  1.58it/s]
73%|███████▎  | 22/30 [00:17<00:05,  1.58it/s]
73%|███████▎  | 22/30 [00:17<00:05,  1.58it/s]
73%|███████▎  | 22/30 [00:17<00:05,  1.58it/s]
73%|███████▎  | 22/30 [00:17<00:05,  1.58it/s]
 73%|███████▎  | 22/30 [00:17<00:05,  1.58it/s]
77%|███████▋  | 23/30 [00:19<00:05,  1.36it/s]
77%|███████▋  | 23/30 [00:19<00:05,  1.36it/s]
77%|███████▋  | 23/30 [00:19<00:05,  1.36it/s]
77%|███████▋  | 23/30 [00:19<00:05,  1.36it/s]
77%|███████▋  | 23/30 [00:19<00:05,  1.36it/s]
77%|███████▋  | 23/30 [00:19<00:05,  1.36it/s]
77%|███████▋  | 23/30 [00:19<00:05,  1.36it/s]
 77%|███████▋  | 23/30 [00:19<00:05,  1.36it/s]
80%|████████  | 24/30 [00:20<00:04,  1.21it/s]
80%|████████  | 24/30 [00:20<00:04,  1.21it/s]
80%|████████  | 24/30 [00:20<00:04,  1.21it/s]
80%|████████  | 24/30 [00:20<00:04,  1.21it/s]
80%|████████  | 24/30 [00:20<00:04,  1.21it/s]
80%|████████  | 24/30 [00:20<00:04,  1.21it/s]
80%|████████  | 24/30 [00:20<00:04,  1.21it/s]
 80%|████████  | 24/30 [00:20<00:04,  1.21it/s]
83%|████████▎ | 25/30 [00:21<00:04,  1.10it/s]
83%|████████▎ | 25/30 [00:21<00:04,  1.10it/s]
83%|████████▎ | 25/30 [00:21<00:04,  1.10it/s]
83%|████████▎ | 25/30 [00:21<00:04,  1.10it/s]
83%|████████▎ | 25/30 [00:21<00:04,  1.10it/s]
83%|████████▎ | 25/30 [00:21<00:04,  1.10it/s]
83%|████████▎ | 25/30 [00:21<00:04,  1.10it/s]
 83%|████████▎ | 25/30 [00:21<00:04,  1.10it/s]
87%|████████▋ | 26/30 [00:22<00:03,  1.03it/s]
87%|████████▋ | 26/30 [00:22<00:03,  1.03it/s]
87%|████████▋ | 26/30 [00:22<00:03,  1.03it/s]
87%|████████▋ | 26/30 [00:22<00:03,  1.03it/s]
87%|████████▋ | 26/30 [00:22<00:03,  1.03it/s]
87%|████████▋ | 26/30 [00:22<00:03,  1.03it/s]
87%|████████▋ | 26/30 [00:22<00:03,  1.03it/s]
 87%|████████▋ | 26/30 [00:22<00:03,  1.03it/s]
90%|█████████ | 27/30 [00:23<00:03,  1.03s/it]
90%|█████████ | 27/30 [00:23<00:03,  1.03s/it]
90%|█████████ | 27/30 [00:23<00:03,  1.03s/it]
90%|█████████ | 27/30 [00:23<00:03,  1.03s/it]
90%|█████████ | 27/30 [00:23<00:03,  1.03s/it]
90%|█████████ | 27/30 [00:23<00:03,  1.03s/it]
90%|█████████ | 27/30 [00:23<00:03,  1.03s/it]
 90%|█████████ | 27/30 [00:23<00:03,  1.03s/it]
93%|█████████▎| 28/30 [00:25<00:02,  1.07s/it]
93%|█████████▎| 28/30 [00:25<00:02,  1.07s/it]
93%|█████████▎| 28/30 [00:25<00:02,  1.07s/it]
93%|█████████▎| 28/30 [00:25<00:02,  1.07s/it]
93%|█████████▎| 28/30 [00:25<00:02,  1.07s/it]
93%|█████████▎| 28/30 [00:25<00:02,  1.07s/it]
93%|█████████▎| 28/30 [00:25<00:02,  1.07s/it]
 93%|█████████▎| 28/30 [00:25<00:02,  1.07s/it]
97%|█████████▋| 29/30 [00:26<00:01,  1.10s/it]
97%|█████████▋| 29/30 [00:26<00:01,  1.10s/it]
97%|█████████▋| 29/30 [00:26<00:01,  1.10s/it]
97%|█████████▋| 29/30 [00:26<00:01,  1.10s/it]
97%|█████████▋| 29/30 [00:26<00:01,  1.10s/it]
97%|█████████▋| 29/30 [00:26<00:01,  1.10s/it]
97%|█████████▋| 29/30 [00:26<00:01,  1.10s/it]
 97%|█████████▋| 29/30 [00:26<00:01,  1.10s/it]
100%|██████████| 30/30 [00:27<00:00,  1.12s/it]
100%|██████████| 30/30 [00:27<00:00,  1.12s/it]
100%|██████████| 30/30 [00:27<00:00,  1.12s/it]
100%|██████████| 30/30 [00:27<00:00,  1.12s/it]
100%|██████████| 30/30 [00:27<00:00,  1.12s/it]
100%|██████████| 30/30 [00:27<00:00,  1.12s/it]
100%|██████████| 30/30 [00:27<00:00,  1.12s/it]
100%|██████████| 30/30 [00:27<00:00,  1.10it/s]
100%|██████████| 30/30 [00:27<00:00,  1.10it/s]
100%|██████████| 30/30 [00:27<00:00,  1.10it/s]
100%|██████████| 30/30 [00:27<00:00,  1.10it/s]
100%|██████████| 30/30 [00:27<00:00,  1.10it/s]
100%|██████████| 30/30 [00:27<00:00,  1.10it/s]
100%|██████████| 30/30 [00:27<00:00,  1.10it/s]
100%|██████████| 30/30 [00:27<00:00,  1.12s/it]
100%|██████████| 30/30 [00:27<00:00,  1.10it/s]
Time elapsed: 29.23s
Saving generated video to output.mp4

Examples

View more examples

Pricing

This model is priced by how many seconds of video are generated.

Type	Per unit	Per $1
Output	$0.07 / second of video or 14 seconds of video / $1

For example, generating 100 seconds of video should cost around $7.00.

Check out our docs for more information about how per second of video pricing works on Replicate.

Readme

Accelerated Inference for Wan 2.1 14B

We are WaveSpeedAI, providing highly-optimized inference optimization for generative AI models.

We are excited to introduce our new product, a highly-optimized inference endpoint for Wan-2.1 14B model, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.

We utilize cutting-edge inference acceleration techniques to provide very fast inference for this model. And we are happy to bring this to you together with Replicate and DataCrunch.

Model Description ✨

Wan: Open and Advanced Large-Scale Video Generative Models

In this repository, we present Wan2.1, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation. Wan2.1 offers these key features: - 👍 SOTA Performance: Wan2.1 consistently outperforms existing open-source models and state-of-the-art commercial solutions across multiple benchmarks. - 👍 Supports Consumer-grade GPUs: The T2V-1.3B model requires only 8.19 GB VRAM, making it compatible with almost all consumer-grade GPUs. It can generate a 5-second 480P video on an RTX 4090 in about 4 minutes (without optimization techniques like quantization). Its performance is even comparable to some closed-source models. - 👍 Multiple Tasks: Wan2.1 excels in Text-to-Video, Image-to-Video, Video Editing, Text-to-Image, and Video-to-Audio, advancing the field of video generation. - 👍 Visual Text Generation: Wan2.1 is the first video model capable of generating both Chinese and English text, featuring robust text generation that enhances its practical applications. - 👍 Powerful Video VAE: Wan-VAE delivers exceptional efficiency and performance, encoding and decoding 1080P videos of any length while preserving temporal information, making it an ideal foundation for video and image generation.