Compare the best 3 zero shot segmentation models and try 1 of them on your own images, free in the Roboflow Playground. 3 are open-weight, so you can self-host them for free under their licenses.
3 models · 3 open-weight · 1 free to try · prices synced Aug 26, 2026
3 models with downloadable weights you can self-host under their licenses (Custom and Apache 2.0). 1 run live in the Playground through hosted APIs, so self-hosting is optional.
Zero-shot segmenters produce masks for things they were never trained on, guided by prompts. The practical choice is between prompt types and speed tiers within the SAM family and its combinations.
Click and box prompts (classic SAM) fit interactive use: a human indicates the object, the model returns the mask. Text-driven combinations like Grounded SAM chain an open-vocabulary detector into SAM so "every forklift" becomes masks with no clicks, which is what automated pipelines need. Newer concept-promptable models fold that into one step.
The highest-value production use of zero-shot segmentation is building datasets: masks that took minutes each by hand take seconds with a promptable model, and a compact trained segmentation model then serves production traffic at low latency. Using the big zero-shot model directly in production is usually the expensive path.
The bottom line: Interactive cutouts: click-prompt SAM. Automated pipelines: text-driven combinations. Either way, its biggest payoff is labeling data to train a faster production model.
Zero-shot segmentation is the task of producing object masks for things the model was never specifically trained to segment, guided by a prompt such as a click, a box, or a text phrase. The SAM family established the recipe: a heavy image encoder computes features once, then a light prompt encoder and mask decoder turn each prompt into a mask interactively. Because the model learned a general notion of object boundaries from enormous mask datasets, it transfers to new domains without fine-tuning. It is used to accelerate dataset labeling, power click-to-cut-out image editing, and provide masks in open-world settings where classes are not known in advance. This page lists 3 zero shot segmentation models, including 3 open-weight options you can self-host; 1 of them run live in the Playground so you can test them on your own images.
It depends on your task and constraints. For fixed categories in production, a model fine-tuned on your own data typically beats any general-purpose model. Compare the zero shot segmentation models on this page and try them on your own images to see which fits.
Yes. 3 of the 3 zero shot segmentation models here are open-weight (for example SAM 3, Grounded SAM, and SAM-CLIP), free to self-host under their licenses (Custom and Apache 2.0).
Yes. You can run 1 of them in the Roboflow Playground for free. Upload an image and compare the models' output side by side, no setup required.
This page lists all 3 zero shot segmentation models in the Roboflow Playground catalog, all of them open-weight and free to self-host; 1 of them run live in the Roboflow Playground on your own images. Compare licenses, parameters, and release dates side by side, or open any model page for full details.