How to Use Sa2VA 8B image segmentation in Instinct
Sa2VA 8B returns a text answer and image segmentation masks for a supplied still image. Use it to evaluate image descriptions and object masks with the model that scored 84.4 on MMBench versus 4B's 81.8.
Prompts to try with Sa2VA 8B image segmentation in Instinct
Copy an example into Instinct, or ask in your own words.
Each Friday, use Sa2VA 8B image segmentation on the supplied LEGO Technic product photos. Describe the visible model and request its mask, then collect the results for catalog review.
Every Monday, use Sa2VA 8B image segmentation on the NASA Perseverance rover photos supplied for that week's lesson. Request a short description and masks for the rover in each photo, then prepare a review digest.
Once a week, use Sa2VA 8B image segmentation on https://raw.githubusercontent.com/facebookresearch/segment-anything-2/main/notebooks/images/truck.jpg. Request the truck description and mask, then compare the result with the previous run for our evaluation log.
Every Monday at 9am: use Sa2VA 8B image segmentation to look this up and give me the result as a table.
Pull the latest numbers from Sa2VA 8B image segmentation and tell me what changed since last week.
How to set up Sa2VA 8B image segmentation in Instinct
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send Instinct this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use Spiral's MCP server
- Create an API key
In the console, open API keys and create a key for Instinct. Copy it.
- Send Instinct this message
Instinct reads Spiral's skill and asks for your API key.
set up https://spiral.ai/SKILL.md
- Give Instinct the key
When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Sa2VA 8B image segmentation
One request; the result comes back by polling or a webhook.
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/8b/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: Instinct finds Sa2VA 8B image segmentation on Spiral, shows the price and runs it.
Sa2VA 8B image segmentation providers and prices
Spiral runs Sa2VA 8B image segmentation through fal. Open a card for today's price, with every fee included.
What can you do with Sa2VA 8B image segmentation in Instinct?
Prepare a recurring review queue of media descriptions and object masks from newly supplied assets. A scheduled agent can ask Sa2VA the same visual questions for each delivery and collect the results for an editor.
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.
More on Sa2VA 8B image segmentation and Instinct
Overview
Sa2VA 8B image segmentation in other agents
Questions about Sa2VA 8B image segmentation in Instinct
Can Instinct use Sa2VA 8B image segmentation?
Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Sa2VA 8B image segmentation like any built-in tool.
How much does Sa2VA 8B image segmentation cost in Instinct?
$0.052 per image. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Instinct plan is separate.
Do I need a fal account to use Sa2VA 8B image segmentation in Instinct?
You need no fal account. Instinct uses one Spiral API key for every tool, and Spiral runs Sa2VA 8B image segmentation on its own fal account.
How long does it take to set up Sa2VA 8B image segmentation in Instinct?
About two minutes: create an API key, then send Instinct this message, then give Instinct the key.
Does Instinct wait while Sa2VA 8B image segmentation runs?
Sa2VA 8B image segmentation runs in the background. Instinct 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.
Start using Sa2VA 8B image segmentation in Instinct
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Instinct:
set up https://spiral.ai/SKILL.md


