apps/infsh/wan-2-2-animate-v2v

wan-2-2-animate-v2v

Creates animated videos by transferring movement from one video to a static character image, or replaces a character in an existing video with a new image while preserving the original motion and environment.

run in browser run via API

run with your agent

# install belt

$curl -fsSL https://cli.inference.sh | sh

# view schema & details

$belt app get infsh/wan-2-2-animate-v2v

# run

$belt app run infsh/wan-2-2-animate-v2v

api reference

about

creates animated videos by transferring movement from one video to a static character image, or replaces a character in an existing video with a new image while preserving the original motion and environment.

1. calling the api

install the client

the client provides a convenient way to interact with the api.

bash

1pip install inferencesh

setup your api key

set INFERENCE_API_KEY as an environment variable. get your key from settings → api keys.

bash

1export INFERENCE_API_KEY="inf_your_key"

run and get result

submit a request and wait for the final result. best for batch processing or when you don't need progress updates.

python

1from inferencesh import inference23client = inference()456result = client.run({7        "app": "infsh/wan-2-2-animate-v2v",8        "input": {}9    })1011print(result["output"])

stream live updates

get real-time progress updates as the task runs. ideal for showing progress bars, partial results, or long-running tasks.

python

1from inferencesh import inference23client = inference()456# stream=True yields updates as they arrive7for update in client.run({8        "app": "infsh/wan-2-2-animate-v2v",9        "input": {}10    }, stream=True):11    if update.get("progress"):12        print(f"progress: {update['progress']}%")13    if update.get("output"):14        print(f"output: {update['output']}")

2. authentication

the api uses api keys for authentication. see the authentication docs for detailed setup instructions.

3. files

file inputs are automatically handled by the sdk. you can pass local paths, urls, or base64 data.

automatic upload

the python sdk automatically detects local file paths and uploads them. urls are passed through as-is.

python

1# local file paths are automatically uploaded2result = client.run({3    "app": "infsh/wan-2-2-animate-v2v",4    "input": {5        "image": "/path/to/local/image.png",  # detected & uploaded6        "audio": "https://example.com/audio.mp3",  # url passed through7    }8})

manual upload

you can also upload files manually and use the returned url.

python

1# upload and get a hosted URL2file = client.files.upload("/path/to/file.png")3print(file.uri)  # https://cloud.inference.sh/...

4. webhooks

get notified when a task completes by providing a webhook url. when the task reaches a terminal state (completed, failed, or cancelled), a POST request is sent to your url with the task result.

python

1result = client.run({2    "app": "infsh/wan-2-2-animate-v2v",3    "input": {},4    "webhook": "https://your-server.com/webhook"5}, wait=False)

webhook payload

your endpoint receives a JSON POST with the task result:

json

1{2  "id": "task_abc123",3  "status": 9,4  "output": { ... },5  "error": "",6  "session_id": null,7  "created_at": "2024-01-15T10:30:00Z",8  "updated_at": "2024-01-15T10:30:05Z"9}

idstring— task id

statusnumber— terminal status (9=completed, 10=failed, 11=cancelled)

outputobject— task output (when completed)

errorstring— error message (when failed)

session_idstring— session id (if using sessions)

created_atstring— iso timestamp

updated_atstring— iso timestamp

5. schema

input

clip_leninteger

frames per clip (must be 4n+1, e.g., 77, 81, 121)

default: 77min:5max:121

driving_videostring(file)*

driving_video

fpsinteger

target fps (-1 to use original video fps)

default: 30min:-1max:60

guide_scalenumber

classifier-free guidance scale for expression control

default: 1min:1max:10

input_promptstring

text prompt (leave empty for default: '视频中的人在做动作')

default: ""

mask_h_subdivisionsinteger

mask height subdivisions for detail (replacement mode)

default: 1min:1max:5

mask_iterationsinteger

mask dilation iterations (replacement mode)

default: 3min:1max:10

mask_kernel_sizeinteger

mask dilation kernel size (replacement mode)

default: 7min:3max:15

mask_w_subdivisionsinteger

mask width subdivisions for detail (replacement mode)

default: 1min:1max:5

modestring

mode: 'animation' (character animation) or 'replacement' (replace character in video)

default: "animation"

n_promptstring

negative prompt

default: ""

offload_modelboolean

offload models to cpu to save vram

default: true

reference_imagestring(file)*

reference_image

refert_numinteger

temporal guidance frames (1 or 5 recommended)

default: 1

resolution_heightinteger

target height for processing

default: 720min:512max:1920

resolution_widthinteger

target width for processing

default: 1280min:512max:1920

retarget_flagboolean

enable pose retargeting (recommended for different body proportions)

default: false

sample_solverstring

sampling solver (dpm++ or unipc)

default: "dpm++"

sampling_stepsinteger

number of diffusion steps

default: 20min:10max:50

seedinteger

random seed (-1 for random)

default: -1

shiftnumber

noise schedule shift parameter

default: 5min:1max:10

use_fluxboolean

use flux image editing for better pose retargeting (slower but better quality)

default: false

output

output_videostring(file)*

output_video

ready to run wan-2-2-animate-v2v?

try in browser browse all tools

we use cookies

we use cookies to ensure you get the best experience on our website. for more information on how we use cookies, please see our cookie policy.

by clicking "accept", you agree to our use of cookies.
learn more.