# Segment Anything

Use Meta's SAM for precise image segmentation on GPU.

{% hint style="success" %}
All examples can be run on GPU servers rented through [CLORE.AI Marketplace](https://clore.ai/marketplace).
{% endhint %}

## Renting on CLORE.AI

1. Visit [CLORE.AI Marketplace](https://clore.ai/marketplace)
2. Filter by GPU type, VRAM, and price
3. Choose **On-Demand** (fixed rate) or **Spot** (bid price)
4. Configure your order:
   * Select Docker image
   * Set ports (TCP for SSH, HTTP for web UIs)
   * Add environment variables if needed
   * Enter startup command
5. Select payment: **CLORE**, **BTC**, or **USDT/USDC**
6. Create order and wait for deployment

### Access Your Server

* Find connection details in **My Orders**
* Web interfaces: Use the HTTP port URL
* SSH: `ssh -p <port> root@<proxy-address>`

## What is SAM?

Segment Anything Model (SAM) can:

* Segment any object in images
* Work with prompts (points, boxes, text)
* Generate automatic masks
* Handle any image type

## Model Variants

| Model         | VRAM | Quality | Speed  |
| ------------- | ---- | ------- | ------ |
| SAM-H (huge)  | 8GB  | Best    | Slow   |
| SAM-L (large) | 6GB  | Great   | Medium |
| SAM-B (base)  | 4GB  | Good    | Fast   |
| SAM2          | 8GB+ | Best    | Medium |

## Quick Deploy

**Docker Image:**

```
pytorch/pytorch:2.5.1-cuda12.4-cudnn9-devel
```

**Ports:**

```
22/tcp
7860/http
```

**Command:**

```bash
pip install segment-anything gradio opencv-python && \
wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_h_4b8939.pth && \
python -c "
import gradio as gr
import numpy as np
from segment_anything import sam_model_registry, SamPredictor
import cv2

sam = sam_model_registry['vit_h'](checkpoint='sam_vit_h_4b8939.pth').cuda()
predictor = SamPredictor(sam)

def segment(image, evt: gr.SelectData):
    predictor.set_image(image)
    point = np.array([[evt.index[0], evt.index[1]]])
    masks, _, _ = predictor.predict(point_coords=point, point_labels=np.array([1]))
    mask = masks[0]
    colored = np.zeros_like(image)
    colored[mask] = [255, 0, 0]
    result = cv2.addWeighted(image, 0.7, colored, 0.3, 0)
    return result

demo = gr.Interface(fn=segment, inputs=gr.Image(), outputs=gr.Image(), title='Click to Segment')
demo.launch(server_name='0.0.0.0', server_port=7860)
"
```

## Accessing Your Service

After deployment, find your `http_pub` URL in **My Orders**:

1. Go to **My Orders** page
2. Click on your order
3. Find the `http_pub` URL (e.g., `abc123.clorecloud.net`)

Use `https://YOUR_HTTP_PUB_URL` instead of `localhost` in examples below.

## Installation

```bash
pip install segment-anything opencv-python
```

### Download Models

```bash

# SAM-H (best quality)
wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_h_4b8939.pth

# SAM-L (balanced)
wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_l_0b3195.pth

# SAM-B (fast)
wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_b_01ec64.pth
```

## Python API

### Basic Segmentation with Points

```python
from segment_anything import sam_model_registry, SamPredictor
import cv2
import numpy as np

# Load model
sam = sam_model_registry["vit_h"](checkpoint="sam_vit_h_4b8939.pth")
sam.to("cuda")

predictor = SamPredictor(sam)

# Load image
image = cv2.imread("photo.jpg")
image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

# Set image
predictor.set_image(image_rgb)

# Segment with point prompt
input_point = np.array([[500, 375]])  # x, y coordinates
input_label = np.array([1])  # 1 = foreground, 0 = background

masks, scores, logits = predictor.predict(
    point_coords=input_point,
    point_labels=input_label,
    multimask_output=True
)

# Get best mask
best_mask = masks[np.argmax(scores)]

# Save mask
cv2.imwrite("mask.png", best_mask.astype(np.uint8) * 255)
```

### Box Prompt

```python

# Segment with bounding box
input_box = np.array([100, 100, 400, 400])  # x1, y1, x2, y2

masks, scores, _ = predictor.predict(
    box=input_box,
    multimask_output=False
)
```

### Multiple Points

```python

# Multiple foreground/background points
input_points = np.array([
    [500, 375],   # Point 1
    [550, 400],   # Point 2
    [100, 100],   # Background point
])
input_labels = np.array([1, 1, 0])  # 1=foreground, 0=background

masks, scores, _ = predictor.predict(
    point_coords=input_points,
    point_labels=input_labels,
    multimask_output=True
)
```

### Combined Box + Point

```python
masks, scores, _ = predictor.predict(
    point_coords=input_point,
    point_labels=input_label,
    box=input_box,
    multimask_output=False
)
```

## Automatic Mask Generation

Generate all possible masks:

```python
from segment_anything import SamAutomaticMaskGenerator
import cv2

sam = sam_model_registry["vit_h"](checkpoint="sam_vit_h_4b8939.pth")
sam.to("cuda")

mask_generator = SamAutomaticMaskGenerator(
    model=sam,
    points_per_side=32,
    pred_iou_thresh=0.86,
    stability_score_thresh=0.92,
    crop_n_layers=1,
    crop_n_points_downscale_factor=2,
    min_mask_region_area=100
)

image = cv2.imread("photo.jpg")
image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

masks = mask_generator.generate(image_rgb)

# Each mask contains:

# - 'segmentation': binary mask

# - 'area': mask area in pixels

# - 'bbox': bounding box

# - 'predicted_iou': quality score

# - 'stability_score': stability score

print(f"Found {len(masks)} masks")
```

### Visualize All Masks

```python
import matplotlib.pyplot as plt

def show_masks(image, masks):
    plt.figure(figsize=(20, 20))
    plt.imshow(image)

    sorted_masks = sorted(masks, key=lambda x: x['area'], reverse=True)

    for mask in sorted_masks:
        m = mask['segmentation']
        color = np.random.random(3)
        colored = np.zeros((*m.shape, 4))
        colored[m] = [*color, 0.5]
        plt.imshow(colored)

    plt.axis('off')
    plt.savefig('all_masks.png')

show_masks(image_rgb, masks)
```

## SAM 2 (Latest Version)

```bash
pip install sam2
```

```python
from sam2.sam2_image_predictor import SAM2ImagePredictor

predictor = SAM2ImagePredictor.from_pretrained("facebook/sam2-hiera-large")

with torch.inference_mode():
    predictor.set_image(image)
    masks, scores, _ = predictor.predict(
        point_coords=points,
        point_labels=labels
    )
```

## Remove Background

```python
from segment_anything import sam_model_registry, SamPredictor
import cv2
import numpy as np

sam = sam_model_registry["vit_h"](checkpoint="sam_vit_h_4b8939.pth")
sam.to("cuda")
predictor = SamPredictor(sam)

def remove_background(image_path, point):
    image = cv2.imread(image_path)
    image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

    predictor.set_image(image_rgb)

    masks, scores, _ = predictor.predict(
        point_coords=np.array([point]),
        point_labels=np.array([1]),
        multimask_output=True
    )

    best_mask = masks[np.argmax(scores)]

    # Create RGBA image
    result = cv2.cvtColor(image, cv2.COLOR_BGR2BGRA)
    result[:, :, 3] = best_mask.astype(np.uint8) * 255

    return result

# Click on object to keep
result = remove_background("photo.jpg", [400, 300])
cv2.imwrite("no_background.png", result)
```

## Extract Object

```python
def extract_object(image_path, point):
    image = cv2.imread(image_path)
    image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

    predictor.set_image(image_rgb)

    masks, scores, _ = predictor.predict(
        point_coords=np.array([point]),
        point_labels=np.array([1]),
        multimask_output=True
    )

    best_mask = masks[np.argmax(scores)]

    # Get bounding box
    rows = np.any(best_mask, axis=1)
    cols = np.any(best_mask, axis=0)
    y1, y2 = np.where(rows)[0][[0, -1]]
    x1, x2 = np.where(cols)[0][[0, -1]]

    # Crop
    cropped = image[y1:y2+1, x1:x2+1]
    mask_cropped = best_mask[y1:y2+1, x1:x2+1]

    # Apply mask
    result = cv2.cvtColor(cropped, cv2.COLOR_BGR2BGRA)
    result[:, :, 3] = mask_cropped.astype(np.uint8) * 255

    return result
```

## Batch Processing

```python
import os
from segment_anything import sam_model_registry, SamAutomaticMaskGenerator
import cv2
import json

sam = sam_model_registry["vit_h"](checkpoint="sam_vit_h_4b8939.pth")
sam.to("cuda")

mask_generator = SamAutomaticMaskGenerator(sam)

input_dir = "./images"
output_dir = "./segmented"
os.makedirs(output_dir, exist_ok=True)

for filename in os.listdir(input_dir):
    if filename.lower().endswith(('.png', '.jpg', '.jpeg')):
        image = cv2.imread(os.path.join(input_dir, filename))
        image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

        masks = mask_generator.generate(image_rgb)

        # Save masks as JSON
        mask_data = []
        for i, mask in enumerate(masks):
            mask_data.append({
                'id': i,
                'area': int(mask['area']),
                'bbox': mask['bbox'],
                'score': float(mask['predicted_iou'])
            })

            # Save individual mask
            cv2.imwrite(
                os.path.join(output_dir, f"{filename}_mask_{i}.png"),
                mask['segmentation'].astype(np.uint8) * 255
            )

        with open(os.path.join(output_dir, f"{filename}_masks.json"), 'w') as f:
            json.dump(mask_data, f)
```

## API Server

```python
from fastapi import FastAPI, UploadFile
from fastapi.responses import Response
from segment_anything import sam_model_registry, SamPredictor
import cv2
import numpy as np
import json

app = FastAPI()

sam = sam_model_registry["vit_h"](checkpoint="sam_vit_h_4b8939.pth")
sam.to("cuda")
predictor = SamPredictor(sam)

@app.post("/segment")
async def segment(file: UploadFile, x: int, y: int):
    contents = await file.read()
    nparr = np.frombuffer(contents, np.uint8)
    image = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
    image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

    predictor.set_image(image_rgb)

    masks, scores, _ = predictor.predict(
        point_coords=np.array([[x, y]]),
        point_labels=np.array([1]),
        multimask_output=True
    )

    best_mask = masks[np.argmax(scores)]

    _, encoded = cv2.imencode('.png', best_mask.astype(np.uint8) * 255)
    return Response(content=encoded.tobytes(), media_type="image/png")
```

## Integration with Stable Diffusion

Use SAM masks for inpainting:

```python

# Generate mask with SAM
predictor.set_image(image)
masks, scores, _ = predictor.predict(point_coords=point, point_labels=label)
mask = masks[np.argmax(scores)]

# Use in SD inpainting
from diffusers import StableDiffusionInpaintPipeline

pipe = StableDiffusionInpaintPipeline.from_pretrained("runwayml/stable-diffusion-inpainting")
pipe.to("cuda")

result = pipe(
    prompt="a red sports car",
    image=image,
    mask_image=mask
).images[0]
```

## Performance

| Model | Image Size | GPU      | Time   |
| ----- | ---------- | -------- | ------ |
| SAM-H | 1024x1024  | RTX 3090 | \~0.5s |
| SAM-L | 1024x1024  | RTX 3090 | \~0.3s |
| SAM-B | 1024x1024  | RTX 3090 | \~0.2s |
| SAM2  | 1024x1024  | RTX 4090 | \~0.3s |

## Memory Optimization

```python

# For limited VRAM
sam = sam_model_registry["vit_b"](checkpoint="sam_vit_b_01ec64.pth")  # Use smaller model

# Or reduce automatic generation points
mask_generator = SamAutomaticMaskGenerator(
    model=sam,
    points_per_side=16,  # Reduce from 32
)
```

## Troubleshooting

### CUDA Out of Memory

* Use SAM-B instead of SAM-H
* Reduce image size before processing
* Clear cache: `torch.cuda.empty_cache()`

### Poor Segmentation

* Add more points (foreground + background)
* Use box prompt for better guidance
* Try multimask\_output=True and pick best

## Cost Estimate

Typical CLORE.AI marketplace rates (as of 2024):

| GPU       | Hourly Rate | Daily Rate | 4-Hour Session |
| --------- | ----------- | ---------- | -------------- |
| RTX 3060  | \~$0.03     | \~$0.70    | \~$0.12        |
| RTX 3090  | \~$0.06     | \~$1.50    | \~$0.25        |
| RTX 4090  | \~$0.10     | \~$2.30    | \~$0.40        |
| A100 40GB | \~$0.17     | \~$4.00    | \~$0.70        |
| A100 80GB | \~$0.25     | \~$6.00    | \~$1.00        |

*Prices vary by provider and demand. Check* [*CLORE.AI Marketplace*](https://clore.ai/marketplace) *for current rates.*

**Save money:**

* Use **Spot** market for flexible workloads (often 30-50% cheaper)
* Pay with **CLORE** tokens
* Compare prices across different providers

## Next Steps

* Stable Diffusion Inpainting
* [ControlNet Guide](https://docs.clore.ai/guides/image-processing/controlnet-advanced)
* [Real-ESRGAN Upscaling](https://docs.clore.ai/guides/image-processing/real-esrgan-upscaling)