Pelikan 2.1

--- license: apache-2.0 library_name: pytorch pipeline_tag: image-segmentation tags: - image-segmentation - mask-generation - promptable-segmentation - segmentation - transformer - vision-transformer - visual-prompting - safetensors - zundteam --- # Pelikan-2.1 - Promptable Mask Generation Model <p align="center"> <img src="assets/human_soccer_panel.png" alt="Pelikan-2.1 real-image promptable mask generation example" width="100%"> </p> Pelikan-2.1 is an in-house promptable mask-generation model developed by **ZundTeam**, a German AI lab. It is designed for image segmentation workflows where a user or system provides a visual prompt, such as a bounding box and foreground point, and the model predicts an object or region mask directly in image space. Pelikan-2.1 continues the Pelikan promptable segmentation line with the same SAM-style interaction pattern while remaining a custom architecture. The model encodes an image, embeds visual prompts, and uses a learned transformer mask decoder to produce candidate masks and quality estimates. It is not a wrapper around SAM, SAM2, SAM3, or any other released segmentation model. Unlike fixed-category semantic segmentation systems, Pelikan-2.1 is centered on visual intent rather than a closed label set. A prompt tells the model what region matters, and the model returns a mask for that region. This makes the model useful for interactive segmentation, visual editing tools, object isolation, dataset annotation, and experiments around promptable vision models. Pelikan-2.1 is intended to feel familiar to users who know promptable segmentation systems: select a region, pass the prompt into the model, receive a mask, then refine or use that mask downstream. The important difference is that Pelikan-2.1 is built as its own model line, with its own encoder, prompt pathway, decoder, mask heads, and PyTorch/safetensors release format. ## Visual Prompting Pelikan-2.1 follows a simple promptable segmentation flow: 1. An RGB image is converted into visual tokens. 2. A box prompt and foreground point are embedded as target hints. 3. The prompt information is merged with the image representation. 4. Learned mask tokens query the image features. 5. The decoder produces candidate masks and a mask-quality estimate. 6. A downstream system selects or post-processes the final mask. This design gives Pelikan-2.1 the structure ex...