Tracks many objects together
Follows several objects through one video at the same time.
Find objects and outlines
Sam 3 1 Video to RLE
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 video studio with Sam 3 1 Video to RLE ready to use. You can look around as a guest. Running it takes the Pro plan or higher.
What Sam 3 1 Video to RLE makes, what it needs and what you get
What it makes
Find objects and outlines
Finds objects, depth, poses and outlines in a video.
What you need
- The video to work on
Optional: the area to change and what to find.
What you get
Masks, depth maps or outlines
About Sam 3 1 Video to RLE
Sam 3 1 Video to RLE tracks several objects in one video at the same time. Marking which parts of each frame belong to an object is called segmentation. Max Num Objects sets how many objects to track, from 1 to 128, and it starts at 16. The output is the segmented video.
It has two modes, Video to RLE and Video to Video, and both need one video. Prompt takes object names separated by commas, for example person, cloth. Point Prompts and Box Prompts mark objects by position. Detection Threshold starts at 0.5, and lower values find more objects but are less precise. It runs from 0.01 to 1 in Video to RLE and from 0.1 to 1 in Video to Video.
In Video to RLE you can add a Mask image, and Frame Index sets the frame used first when you add a mask. Boundingbox Zip returns a zip file with a bounding box (a rectangle around an object) overlay for each frame. Video to Video adds Video Output Type, with MP4 or WebM. Apply Mask puts the mask on the video. It starts on in Video to Video and off in Video to RLE. Sam 3 1 Video to RLE costs 100 credits. Sam 3 costs 50 credits and does not have the Max Num Objects option.
Other models for this job
Same job: find objects and outlines. Compare before you choose.
Video Pro Open
Sam 3Find objects and outlines
SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.
Meta50 creditsper run
Video Pro Open
Depth Anything VideoFind objects and outlines
Generates depth maps from video using Video Depth Anything (CVPR 2025). Produces per-frame depth estimation with temporal consistency across frames. Supports 3 model sizes (Small, Base, Large), 5 colormaps including grayscale, side-by-side comparison with the original video, and raw depth export as .npz. Useful for 3D reconstruction, video effects, compositing, and scene understanding.
Open Source2,000 creditsper 5 s
Video Pro Open
DWPose Pose Prediction Video toFind objects and outlines
Predict poses from videos.
DWPose6 creditsper run
What it does well
Mask and starting frame
In Video to RLE, add a Mask image and choose which frame it starts from with Frame Index.
Bounding box zip file
Turn on Boundingbox Zip in Video to RLE to get a zip file with a bounding box (a rectangle around an object) overlay for each frame.
How to use Sam 3 1 Video to RLE
How It Works
How It Works
01
Add your video
Add the one video whose objects you want to track.
02
Choose a mode and name what to track
Choose Video to RLE or Video to Video. Type object names in Prompt, separated by commas. In Video to RLE you can also add a mask.
03
Generate
The segmented video comes back to you. It costs 100 credits.
Tip If text prompts fail in Video to RLE, try a Detection Threshold of 0.2 to 0.3.
Good for
Mark objects you name
Type names such as person, cloth in the prompt, separated by commas, and get them marked in the video.
Mark an object by position
Show where an object is with Point Prompts or Box Prompts. In Video to RLE you can add frame numbers.
Questions
Quick answers to help you get the most out of Sam 3 1 Video to RLE in FunAI Studio.
1. What is required?
2. How many objects can it track?
3. What does it cost?