Inference Logoinference shell

P-Video-2-Pro-Reference

Video from a prompt plus up to 9 image, 3 video and 3 audio references on MiniMax H3. Consistent characters, motion transfer, 5-15s, 480p to 4k.

reference to videoimage to video
run in browser →run via API
run with your agent
# install belt
$curl -fsSL https://cli.inference.sh | sh
# sign in (or set INFERENCE_API_KEY on a headless machine)
$belt login
# view schema & details
$belt app get pruna/p-video-2-pro-reference
# run
$belt app run pruna/p-video-2-pro-reference --input '{"prompt":"prompt"}'
maker
pruna
category
video
input → output
reference → video, image → video
price
Output: cost $0.015-$0.105/sec, speed $0.02-$0.115/sec. Ref video: $0.03-$0.06/sec. Ref img: $0.005/img. Ref audio: $0.0015-$0.0025/sec
runs via
api, javascript and python sdk, belt cli, mcp
updated
2026-10-23

api reference

about

video from a prompt plus up to 9 image, 3 video and 3 audio references on minimax h3. consistent characters, motion transfer, 5-15s, 480p to 4k.

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
1import os2from inferencesh import inference34client = inference(api_key=os.environ["INFERENCE_API_KEY"])567result = client.run({8        "app": "pruna/p-video-2-pro-reference",9        "input": {10            "prompt": "prompt"11        }12    })1314print(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
1import os2from inferencesh import inference34client = inference(api_key=os.environ["INFERENCE_API_KEY"])567# stream=True yields updates as they arrive8for update in client.run({9        "app": "pruna/p-video-2-pro-reference",10        "input": {11            "prompt": "prompt"12        }13    }, stream=True):14    if update.get("progress"):15        print(f"progress: {update['progress']}%")16    if update.get("output"):17        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": "pruna/p-video-2-pro-reference",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": "pruna/p-video-2-pro-reference",3    "input": {4        "prompt": "prompt"5    },6    "webhook": "https://your-server.com/webhook"7}, wait=False)

webhook payload

your endpoint receives a JSON POST with the task result:

json
1{2  "event": "task.completed",3  "timestamp": "2024-01-15T10:30:05Z",4  "data": {5    "id": "task_abc123",6    "short_id": "abc123",7    "status": 10,8    "status_text": "completed",9    "output": { ... },10    "created_at": "2024-01-15T10:30:00Z",11    "updated_at": "2024-01-15T10:30:05Z"12  }13}
eventstringtask.completed, task.failed or task.cancelled
timestampstringiso timestamp of the delivery
data.idstringtask id
data.short_idstringshort task id
data.statusnumberterminal status (10=completed, 11=failed, 12=cancelled, 13=rejected)
data.status_textstringthe status as a word: completed, failed or cancelled
data.outputobjecttask output (when completed)
data.errorstringerror message (when failed, omitted otherwise)
data.session_idstringsession id (when the task ran in a session, omitted otherwise)
data.created_atstringiso timestamp
data.updated_atstringiso timestamp

5. schema

input

promptstring*

text description for video generation. refer to references by what they show.

imagesarray

reference images (up to 9 including first and last frames; 20 mib, 4096 px each).

videosarray

reference videos (up to 3; 2-15s each, 15s combined, up to 1080p/60 fps).

audiosarray

reference audio (up to 3, 15s combined). set keep_audio to use one file as the soundtrack.

keep_audioboolean

keep the single audio file as the video's audio. needs exactly one audio file.

default: false
first_frame_imagestring(file)

optional opening image (soft keyframe, counts as a reference image).

last_frame_imagestring(file)

optional closing image (soft keyframe, counts as a reference image).

durationinteger

video duration in seconds (5-15).

default: 5min:5max:15
resolutionstring

480p or 768p native. 1080p, 2k and 4k generate at 768p and upscale.

default: "768p"
options:"480p""768p""1080p""2k""4k"
modestring

speed (default) or cost (cheaper, slower).

default: "speed"
options:"cost""speed"
prompt_upsamplerstring

rewrite the prompt before generation: turbo, max or off. frame images force turbo.

default: "turbo"
options:"off""turbo""max"
aspect_ratiostring

aspect ratio. adaptive follows the references.

default: "16:9"
options:"adaptive""16:9""9:16""4:3""3:4""3:2""2:3""1:1"
seedinteger

random seed for reproducible generation.

enable_safety_filterboolean

check inputs against the content policy. always-on categories are blocked either way.

default: false

output

seedinteger

seed used for generation.

videostring(file)*

generated video with audio.

other video apps

VACE

pruna/vace

$0.40/video

P-Video-Animate

pruna/p-video-animate

$0.03/sec 720p, $0.06/sec 1080p

P-Video-Upscale

pruna/p-video-upscale

Std: $0.01/sec 720p, $0.02 1080p, $0.04 2k, $0.08 4k; high fps 2x

P-Video-2-Pro-Avatar

pruna/p-video-2-pro-avatar

$0.02/sec 480p, $0.04/sec 768p, $0.06/sec 1080p, $0.08/sec 2k, $0.12/sec 4k

P-Video-2-Pro

pruna/p-video-2-pro

$0.01-$0.155/sec; cost: $0.01-$0.105, speed: $0.02-$0.115, quality: $0.04-$0.155 (480p-4k)

more from pruna

VACE

pruna/vace

$0.40/video

P-Video-Animate

pruna/p-video-animate

$0.03/sec 720p, $0.06/sec 1080p

P-Video-Upscale

pruna/p-video-upscale

Std: $0.01/sec 720p, $0.02 1080p, $0.04 2k, $0.08 4k; high fps 2x

P-Video-2-Pro-Avatar

pruna/p-video-2-pro-avatar

$0.02/sec 480p, $0.04/sec 768p, $0.06/sec 1080p, $0.08/sec 2k, $0.12/sec 4k

new models

  1. VACE

    pruna/vace

    video$0.40/video

  2. P-Video-Animate

    pruna/p-video-animate

    video$0.03/sec 720p, $0.06/sec 1080p

  3. P-Video-Upscale

    pruna/p-video-upscale

    videoStd: $0.01/sec 720p, $0.02 1080p, $0.04 2k, $0.08 4k; high fps 2x

  4. P-Video-2-Pro-Avatar

    pruna/p-video-2-pro-avatar

    video$0.02/sec 480p, $0.04/sec 768p, $0.06/sec 1080p, $0.08/sec 2k, $0.12/sec 4k

  5. P-Video-2-Pro

    pruna/p-video-2-pro

    video$0.01-$0.155/sec; cost: $0.01-$0.105, speed: $0.02-$0.115, quality: $0.04-$0.155 (480p-4k)

ready to run P-Video-2-Pro-Reference?

try in browserbrowse all apps

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.