Select by text
Type a Prompt that names what to select in the image.
Find objects and outlines
Sam 3 1
SAM 3.1 builds comes with Object Multiplex, a shared-memory approach for joint multi-object tracking that delivers faster speeds with larger number of objects tracked.
Made by Meta100 creditsper run Pro
Opens the image studio with Sam 3 1 ready to use. You can look around as a guest. Running it takes the Pro plan or higher.
What Sam 3 1 makes, what it needs and what you get
What it makes
Find objects and outlines
Finds objects, depth, poses and outlines in a picture.
What you need
- The picture to work on
- What to find
What you get
Masks, depth maps or outlines
About Sam 3 1
Sam 3 1, made by Meta, finds objects in an image and marks them with masks. A mask is a shape that outlines an object. You add one image and say what to select. In Image to Image mode, you get the mask images back.
You can say what to select with a text Prompt, Point Prompts or Box Prompts. The Prompt box starts with the word "wheel" in it, so type the object you want instead. Apply Mask puts the mask on your image and starts on. Return Multiple Masks starts off. When it is on, Max Masks sets the maximum number of masks, from 1 to 32, and starts at 3. Include Scores adds a number for each mask that shows how sure the model is about it. Include Boxes adds a box for each mask when available.
Sam 3 1 has two modes, Image to Image and Image to RLE (run-length encoding, a compact way to store a mask). Both take the same image and options. It costs 100 credits. Segment Anything Model 3 has one mode and costs 50 credits.
Other models for this job
Same job: find objects and outlines. Compare before you choose.
Image Pro Open
Hi3D Image to ReliefFind objects and outlines
Generate a 3D relief depth map with Hi3D from a single image.
Hitem3D2,000 creditsper run
Image Pro Open
PATINA Image to MapsFind objects and outlines
PATINA creates seamless high-resolution normal, roughness, basecolor (albedo), height (displacement) and metalness maps from images
Open Source100 creditsper run
Image Pro Open
Qwen Image LayeredFind objects and outlines
Qwen-Image-Layered is a model capable of decomposing an image into multiple RGBA layers.
Alibaba500 creditsper run
Image Pro Open
Seedream 5.0 Pro LayerizeFind objects and outlines
Splits a finished image into independent, editable transparent-PNG layers — background plus separate elements, from a text description, returning 2 to 17 layers per call for non-destructive reuse in design tools.
ByteDance338 creditsper run
What it does well
Point and box prompts
Point Prompts and Box Prompts let you mark the object on the image. You can use several boxes.
Up to 32 masks
Turn on Return Multiple Masks and set Max Masks from 1 to 32.
Scores and boxes
Include Scores adds a number for each mask that shows how sure the model is about it. Include Boxes adds a box for each mask when available.
How to use Sam 3 1
How It Works
How It Works
01
Add an image and choose a mode
Upload the one image you want objects selected in. Choose Image to Image, or Image to RLE if you need that mode.
02
Say what to select
Type a Prompt to replace the starting word "wheel", or add Point Prompts or Box Prompts. Switch on Return Multiple Masks, Include Scores or Include Boxes if you want them.
03
Generate
Run the model and review what comes back. A run costs 100 credits.
Tip Return Multiple Masks starts off. Turn it on, then set Max Masks from 1 to 32 to choose the maximum number of masks that come back.
Good for
Select an object in a photo
Type what you want selected and get a mask that marks it.
Mark an object by hand
Add points or boxes on the image to show which object you mean.
Questions
Quick answers to help you get the most out of Sam 3 1 in FunAI Studio.
1. What do I need to provide?
2. What do I get back?
3. How much does Sam 3 1 cost?