# PixVerse Fusion

> Run PixVerse Fusion by pixverse online or via API. From $0.12 per second, no setup.

**URL:** https://inference.sh/apps/pixverse/fusion
**Last updated:** 2026-08-04

---

PixVerse Fusion — generate video from reference images. Compose 1-3 subject/background images into a video scene with text-guided motion.

- app: `pixverse/fusion`
- maker: [pixverse](https://inference.sh/apps/pixverse.md)
- category: [video](https://inference.sh/apps/category/video.md)
- input → output: reference → video
- tasks: [reference to video](https://inference.sh/apps/tag/reference-to-video.md)
- price: $0.12/sec
- runs via: api, javascript and python sdk, belt cli, mcp

## fusion API Guide

### About
pixverse fusion — generate video from reference images. compose 1-3 subject/background images into a video scene with text-guided motion.

### 1. Calling the API

#### Install the Client

```bash
pip install inferencesh
```

#### Setup Your API Key
Set `INFERENCE_API_KEY` as an environment variable. Get your key from settings → api keys.

```bash
export INFERENCE_API_KEY="inf_your_key"
```

#### Run and Get Result

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])


result = client.run({
        "app": "pixverse/fusion@053md77d",
        "input": {
            "prompt": "prompt",
            "image_references": [
                {
                    "image": "https://example.com/file.png",
                    "ref_name": "ref_name"
                }
            ]
        }
    })

print(result["output"])
```

#### Stream Live Updates

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])


## stream=True yields updates as they arrive
for update in client.run({
        "app": "pixverse/fusion@053md77d",
        "input": {
            "prompt": "prompt",
            "image_references": [
                {
                    "image": "https://example.com/file.png",
                    "ref_name": "ref_name"
                }
            ]
        }
    }, stream=True):
    if update.get("progress"):
        print(f"progress: {update['progress']}%")
    if update.get("output"):
        print(f"output: {update['output']}")
```

### 2. Authentication
The API uses API keys for authentication. See the authentication docs for detailed setup instructions.

### 3. Files

#### Automatic Upload

```python
## local file paths are automatically uploaded
result = client.run({
    "app": "pixverse/fusion@053md77d",
    "input": {
        "image": "/path/to/local/image.png",  # detected & uploaded
        "audio": "https://example.com/audio.mp3",  # url passed through
    }
})
```

#### Manual Upload

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

### 4. Schema

#### Input
- **prompt** (string) *required*: Scene description. Prefix ref_names with @ and include a space after (e.g. '@dog plays in the park').
- **image_references** (array) *required*: Reference images for composition (1-3). Each must have a unique ref_name.
- **model** (string): Generation model
- **quality** (string): Output resolution
- **duration** (integer): Video duration in seconds
- **aspect_ratio** (string): Video aspect ratio
- **seed** (integer): Seed for reproducibility

#### Output
- **video** (string): Generated video file

## other video apps

- [H3 Max Styles](https://inference.sh/apps/falai/minimax-h3-max-styles.md): $0.08/sec (768P)
- [H3 Max Insert Video](https://inference.sh/apps/falai/minimax-h3-max-insert-video.md): $0.05/sec 480p, $0.06/sec 768p
- [H3 Max 3D to Video](https://inference.sh/apps/falai/minimax-h3-max-3d-to-video.md): $0.50/request + $0.05/sec (480P), $0.08/sec (768P), $0.16/sec (1080P) + $0.10/generated ref; 5s min
- [H3 Max Recast](https://inference.sh/apps/falai/minimax-h3-max-recast.md): $0.30/sec at 768P, $0.45/sec at 1080P
- [H3 Max Relight](https://inference.sh/apps/falai/minimax-h3-max-relight.md): $0.05/s 480P, $0.08/s 768P, $0.16/s 1080P, $0.32/s 2K; up to 15s/video

## faq

### how much does PixVerse Fusion cost?

$0.12/sec. you pay per run from your inference shell credits. no subscription is required.

### how do I run PixVerse Fusion via api?

call pixverse/fusion with the javascript or python sdk, the rest api, or `belt app run pixverse/fusion` from a terminal. the api reference on this page lists every input.

### who makes PixVerse Fusion?

PixVerse Fusion is made by pixverse and runs on inference shell. every pixverse app is listed at https://inference.sh/apps/pixverse.

### can my agent use PixVerse Fusion?

yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do.

### what are the alternatives to PixVerse Fusion?

other video apps on inference shell include H3 Max Styles, H3 Max Insert Video, H3 Max 3D to Video, H3 Max Recast. they run through the same api, so switching is a one-line change.