[Integrations](https://spiral.ai/integrations) › [Cline](https://spiral.ai/integrations/cline) › [Sa2VA 4B image segmentation](https://spiral.ai/integrations/cline/sa2va-4b-image-segmentation)

# How to Use Sa2VA 4B image segmentation in Cline

Sa2VA 4B returns a text answer and image segmentation masks for a supplied still image. Use it to describe objects and isolate their visible regions when you need image masks rather than video masks.

|  |  |
| --- | --- |
| Model | Sa2VA 4B image segmentation |
| Available through | fal |
| Category | Data |
| Price | $0.026 per image. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Sa2VA 4B image segmentation in Cline

- Use Sa2VA 4B image segmentation on the truck photo at https://raw.githubusercontent.com/facebookresearch/segment-anything-2/main/notebooks/images/truck.jpg. Request a truck description and mask, then add the result to this project's annotation viewer.
- Use Sa2VA 4B image segmentation on the supplied NASA Perseverance rover photo. Ask which visible parts belong to the rover and request corresponding masks, then build a review page in this project.
- Use Sa2VA 4B image segmentation on the truck photo at https://raw.githubusercontent.com/facebookresearch/segment-anything-2/main/notebooks/images/truck.jpg. Request separate masks for the truck and building, then add a comparison view for the original image and returned masks.
- Use Sa2VA 4B image segmentation to look this up and give me the result as a table. Save the result in ./assets.
- Pull the latest numbers from Sa2VA 4B image segmentation and tell me what changed since last week.

## How to set up Sa2VA 4B image segmentation in Cline

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the server**: In the Cline panel, click the MCP Servers icon and open the Remote Servers tab. Enter:

```bash
cline mcp add spiral https://api.spiral.ai/mcp --transport http --yes
```

2. **Sign in**: Open the Configure tab and click Authenticate on the Spiral server. Sign in to Spiral, pick the organization and click Authorize. No API key.

3. **Check it**: Spiral shows as connected on the Configure tab. In the CLI:

```bash
cline config mcp
```

### Use the Spiral skill

1. **Send Cline this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Sa2VA 4B image segmentation**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/sa2va/4b/image",
    "input": {
      "prompt": "Could you please give me a brief description of the image? Please respond with interleaved segmentation masks for the corresponding parts of the answer.",
      "image_url": "https://raw.githubusercontent.com/facebookresearch/segment-anything-2/main/notebooks/images/truck.jpg"
    }
  }'
```

Then paste one of the prompts above: Cline finds Sa2VA 4B image segmentation on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/cline

## Sa2VA 4B image segmentation tools and prices

- [Sa2VA 4B Image · Vision](https://spiral.ai/tools/fal/fal-ai/sa2va/4b/image) (fal): $0.026 per image.

## What can you do with Sa2VA 4B image segmentation in Cline?

Build a media review screen that places Sa2VA descriptions beside the corresponding object masks. A coding agent can work with your project's image and video assets and add the returned results to an annotation review workflow.

### Draft visual descriptions

Ask Sa2VA to describe a product photo or demonstration clip, then use the answer as a draft for a media caption.

### Prepare annotation drafts

Request object descriptions with corresponding masks for an image or video dataset. Give annotators the text and masks together for review.

### Catalog product media

Describe visible products, colors, and surroundings in catalog photos and demonstration videos. Use the descriptions to draft searchable asset labels.

### Prepare masks for editing

Name the object an editor needs to isolate and request its segmentation mask. Review the returned image mask or mask video before using it in an editing workflow.

### Review generated media

Ask specific questions about objects and their relationships in generated stills or clips. Compare the answers and masks with the creative brief during review.

### Create visual teaching material

Use licensed illustrations or animation clips to draft object descriptions and visual questions. Request matching masks to highlight the regions discussed in a lesson.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Cline guides](https://spiral.ai/integrations/cline)

## Sa2VA 4B image segmentation in other agents

- [Amp](https://spiral.ai/integrations/amp/sa2va-4b-image-segmentation)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/sa2va-4b-image-segmentation)
- [Claude](https://spiral.ai/integrations/claude-desktop/sa2va-4b-image-segmentation)
- [Claude Code](https://spiral.ai/integrations/claude-code/sa2va-4b-image-segmentation)
- [Codex](https://spiral.ai/integrations/codex/sa2va-4b-image-segmentation)
- [Cursor](https://spiral.ai/integrations/cursor/sa2va-4b-image-segmentation)
- [Devin](https://spiral.ai/integrations/devin/sa2va-4b-image-segmentation)
- [dots](https://spiral.ai/integrations/dots/sa2va-4b-image-segmentation)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/sa2va-4b-image-segmentation)
- [Gemini](https://spiral.ai/integrations/gemini/sa2va-4b-image-segmentation)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/sa2va-4b-image-segmentation)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/sa2va-4b-image-segmentation)
- [goose](https://spiral.ai/integrations/goose/sa2va-4b-image-segmentation)
- [Grok](https://spiral.ai/integrations/grok/sa2va-4b-image-segmentation)
- [Grok Build](https://spiral.ai/integrations/grok-build/sa2va-4b-image-segmentation)
- [Hermes](https://spiral.ai/integrations/hermes/sa2va-4b-image-segmentation)
- [Instinct](https://spiral.ai/integrations/instinct/sa2va-4b-image-segmentation)
- [Manus](https://spiral.ai/integrations/manus/sa2va-4b-image-segmentation)
- [Muse](https://spiral.ai/integrations/muse/sa2va-4b-image-segmentation)
- [Muse Code](https://spiral.ai/integrations/muse-code/sa2va-4b-image-segmentation)
- [n8n](https://spiral.ai/integrations/n8n/sa2va-4b-image-segmentation)
- [Notion](https://spiral.ai/integrations/notion/sa2va-4b-image-segmentation)
- [OpenClaw](https://spiral.ai/integrations/openclaw/sa2va-4b-image-segmentation)
- [opencode](https://spiral.ai/integrations/opencode/sa2va-4b-image-segmentation)
- [Perplexity](https://spiral.ai/integrations/perplexity/sa2va-4b-image-segmentation)
- [Raycast](https://spiral.ai/integrations/raycast/sa2va-4b-image-segmentation)
- [VS Code](https://spiral.ai/integrations/vscode/sa2va-4b-image-segmentation)
- [Windsurf](https://spiral.ai/integrations/windsurf/sa2va-4b-image-segmentation)
- [Zapier](https://spiral.ai/integrations/zapier/sa2va-4b-image-segmentation)

## More Cline guides

- [SAM 3 image embedding](https://spiral.ai/integrations/cline/sam-3-image-embedding)
- [Sa2VA 4B video segmentation](https://spiral.ai/integrations/cline/sa2va-4b-video-segmentation)
- [Moondream 2 object coordinates](https://spiral.ai/integrations/cline/moondream-2-object-coordinates)
- [Sa2VA 8B image segmentation](https://spiral.ai/integrations/cline/sa2va-8b-image-segmentation)
- [Moondream 2 object bounding boxes](https://spiral.ai/integrations/cline/moondream-2-object-bounding-boxes)
- [Sa2VA 8B video segmentation](https://spiral.ai/integrations/cline/sa2va-8b-video-segmentation)

## Questions about Sa2VA 4B image segmentation in Cline

**Can Cline use Sa2VA 4B image segmentation?**

Yes. Add Spiral to Cline as an MCP server, and Cline can find and run Sa2VA 4B image segmentation like any built-in tool.

**How much does Sa2VA 4B image segmentation cost in Cline?**

$0.026 per image. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Cline plan is separate.

**Do I need a fal account to use Sa2VA 4B image segmentation in Cline?**

No. Spiral runs Sa2VA 4B image segmentation on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Sa2VA 4B image segmentation in Cline?**

About two minutes: add the server, then sign in, then check it.

**Does Cline wait while Sa2VA 4B image segmentation runs?**

Sa2VA 4B image segmentation runs in the background. Cline starts the run, checks on it and gives you the json when it's ready.

**What does Sa2VA return besides a description?**

Its documented outputs include generated text and segmentation masks. Image analysis returns image masks; video analysis returns mask video files.

**Can Sa2VA fetch media behind a login?**

Externally hosted media URLs must be publicly accessible. A link that requires a website login falls outside that documented boundary.

**How do the published 4B and 8B results compare?**

ByteDance reports MMBench scores of 81.8 for 4B and 84.4 for 8B. On the MeVIS video segmentation benchmark, it reports 55.9 and 58.9 respectively; these are benchmark scores, not accuracy percentages for your media.

**How should I ask for segmentation masks?**

Explicitly request masks for the objects discussed in the answer. ByteDance's example asks for interleaved segmentation masks corresponding to parts of the description.

**Which scenes need closer review?**

The Sa2VA paper identifies occlusion and long referring descriptions as challenges. It also calls out longer videos with camera motion, so review those results closely before using the masks as annotations.

