# HunyuanCustom MCP and API - Image to video by Tencent | FlyMy.AI

> Tencent HunyuanCustom makes a video that keeps the subject of your image consistent, from an image and a text prompt, on FlyMy.AI GPUs.

Page: https://flymy.ai/mcp/models/hunyuan-custom/

MCP / Models / Image to video

# HunyuanCustom MCP: subject-consistent video with no API key

Tencent HunyuanCustom makes a video that keeps the subject of your image consistent, from an image and a text prompt, on FlyMy.AI GPUs. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

[Use HunyuanCustom](https://flymy.ai/mcp/models/hunyuan-custom/#start) [Inputs and price](https://flymy.ai/mcp/models/hunyuan-custom/#inputs)

No API key, $5.97 / hr, Image to video, Tencent, Commercial use

$ YOUR NEXT RUN

Claude Code, Codex, Cursor, Any agent

## Use HunyuanCustom in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

```
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/hunyuan-custom.md. Help me connect the FlyMy.AI MCP to this assistant, then run HunyuanCustom (flymyai/hunyuan-custom) for this task: Animate the photo I attach with HunyuanCustom: the person turns and smiles at the camera.
```

[Open FlyMy.AI](https://app.flymy.ai/new-agent) [Download brief](https://flymy.ai/mcp/models/hunyuan-custom.md)

## What HunyuanCustom does

HunyuanCustom is built on the Hunyuan Video framework and centers on subject consistency: the person or object in image stays recognizable while the prompt sets the action. Set width and height (512x896 by default), num_frames, num_inference_steps, fps, negative_prompt and random_seed. It runs on our GPUs and is billed by run time.

## HunyuanCustom inputs

Every input of `flymyai/hunyuan-custom` as its live schema lists them. Returns `output` (array).

| Input | Type, values and default |
|---|---|
| [#](https://flymy.ai/mcp/models/hunyuan-custom/#input-prompt) `prompt` | string required |
| [#](https://flymy.ai/mcp/models/hunyuan-custom/#input-negative_prompt) `negative_prompt` | string required |
| [#](https://flymy.ai/mcp/models/hunyuan-custom/#input-width) `width` | integer required Default: `512` |
| [#](https://flymy.ai/mcp/models/hunyuan-custom/#input-height) `height` | integer required Default: `896` |
| [#](https://flymy.ai/mcp/models/hunyuan-custom/#input-num_frames) `num_frames` | integer required Default: `129` |
| [#](https://flymy.ai/mcp/models/hunyuan-custom/#input-num_inference_steps) `num_inference_steps` | integer required Default: `30` |
| [#](https://flymy.ai/mcp/models/hunyuan-custom/#input-image) `image` | file required Allowed: image file, as a URL or upload |
| [#](https://flymy.ai/mcp/models/hunyuan-custom/#input-random_seed) `random_seed` | integer optional Default: `42` |
| [#](https://flymy.ai/mcp/models/hunyuan-custom/#input-fps) `fps` | integer optional Default: `25` |

## Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

**“Animate the photo I attach with HunyuanCustom: the person turns and smiles at the camera.”** runs `flymyai/hunyuan-custom`

**“Turn my product shot into a clip with HunyuanCustom, the camera slowly circling it.”** runs `flymyai/hunyuan-custom`

**“Bring this old family photo to life with HunyuanCustom: gentle smiles and a slight head turn.”** runs `flymyai/hunyuan-custom`

## HunyuanCustom price

$5.97 per hour of run time, billed per second. Billed per second of run time, $5.97 an hour. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

[See usage pricing →](https://flymy.ai/pricing/)

## Call HunyuanCustom from code

The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.

### From an agent, through the MCP

The agent calls `get_model_schema`, then `run_model` with:

```
{
  "endpoint_id": "flymyai/hunyuan-custom",
  "input": {
    "prompt": "Slow camera push-in with gentle, natural motion in the scene",
    "negative_prompt": "Aerial view, aerial view, overexposed, low quality, deformation, a poor composition, bad hands, bad teeth, bad eyes, bad limbs, distortion, blurring, text, subtitles, static, picture, black border.",
    "width": "512",
    "height": "896",
    "num_frames": "129",
    "num_inference_steps": "30"
  }
}
```

### From your code, over HTTP

Form fields, not JSON; files go as uploads or public URLs. The answer is a `prediction_id`; read the result at `https://api.flymy.ai/api/v1/flymyai/hunyuan-custom/predict/async/result/?request_id=<prediction_id>`.

```
curl -X POST https://api.flymy.ai/api/v1/flymyai/hunyuan-custom/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=Slow camera push-in with gentle, natural motion in the scene' \
  -F 'negative_prompt=Aerial view, aerial view, overexposed, low quality, deformation, a poor composition, bad hands, bad teeth, bad eyes, bad limbs, distortion, blurring, text, subtitles, static, picture, black border.' \
  -F 'width=512' \
  -F 'height=896' \
  -F 'num_frames=129' \
  -F 'num_inference_steps=30'
```

## Questions about HunyuanCustom

**Do I need a Tencent API key for HunyuanCustom?**

No. HunyuanCustom runs on FlyMy.AI GPUs, so you need no Tencent key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

**How much does HunyuanCustom cost?**

$5.97 per hour of run time, billed per second. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-09.

**How do I use HunyuanCustom in Claude Code, Codex or Cursor?**

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Animate the photo I attach with HunyuanCustom: the person turns and smiles at the camera." Your agent reads the inputs with get_model_schema and runs flymyai/hunyuan-custom with run_model.

**What does HunyuanCustom need as input?**

HunyuanCustom requires prompt, negative_prompt, width, height, num_frames, num_inference_steps and image; it also takes 2 optional inputs, each listed on this page with its allowed values and default.

**Can I call HunyuanCustom from my own code?**

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/hunyuan-custom/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.

## More image to video models

Animate a photo, or move from a first frame to a last one.

### Gemini Omni 1.2 Flash Image to Video

Gemini Omni from a photo: native sound, first-to-last-frame moves, up to 4K.

Image to video / from $0.024 / s

Link: https://flymy.ai/mcp/models/gemini-omni-1-2-flash-i2v/

### Wan 3.0 Image to Video

Wan 3.0 from your image: up to 30 seconds, adaptive framing and a soundtrack.

Image to video / from $0.05 / s

Link: https://flymy.ai/mcp/models/wan-3-0-i2v/

### Seedance 2.5 Image to Video

Seedance 2.5 from a photo: up to 30 seconds, first-to-last-frame moves, real people allowed.

Image to video / from $0.10794 / s

Link: https://flymy.ai/mcp/models/bytedance-seedance-2-5-image-to-video/

### Wan 2.7 Image to Video

Wan 2.7 from a still: first-to-last-frame moves with natural motion.

Image to video / from $0.10 / s

Link: https://flymy.ai/mcp/models/wan-2-7-i2v/

### Wan 2.6 Image to Video

The previous Wan generation for animating a still at 720P or 1080P.

Image to video / from $0.10 / s

Link: https://flymy.ai/mcp/models/wan-2-6-i2v/

### Seedance 2.0 Fast Image to Video

Quick Seedance 2.0 animation of one photo, for drafts at 480p or 720p.

Image to video / from $0.0538 / s

Link: https://flymy.ai/mcp/models/bytedance-seedance-2-0-fast-image-to-video/

## Go to the source

[HunyuanCustom in the playground →](https://app.flymy.ai/models/flymyai/hunyuan-custom), [Model endpoints in the docs →](https://docs.flymy.ai/api/models-endpoints), [Image to video guide →](https://docs.flymy.ai/guides/generate-videos), [Every model on FlyMy.AI →](https://flymy.ai/mcp/models/), [Every MCP in the catalog →](https://flymy.ai/mcp/#catalog), [Usage pricing →](https://flymy.ai/pricing/)

From the FlyMy.AI model catalog of 2026-11-09: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.

---

For agents: the FlyMyAI operating guide (sign up, connect, run models, tools and agents) is https://flymy.ai/skill.md, and https://flymy.ai/llms.txt lists the other pages and the documentation.