Choose a category in More filters to see relevant price sorts.
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.
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.
Generate subject consistent videos using Lynx from ByteDance!
Precise camera position and angle control (rotation, zoom, vertical movement)
Apply designs/graphics onto people's shirts
Remove existing lighting and apply soft, even illumination
Remove unwanted elements (objects, people, text) while maintaining image consistency
Create cinematic transitions and scene progressions (camera movements, framing changes)
Blend products into backgrounds with automatic perspective and lighting correction
Generate full portrait from a cropped face photo
Add a realistic scene behind the object with white background
Add automatic subtitles to videos
Directional outpainting. Choose edges to expand. left, right, top, or center (uniform all sides). Only expanded areas are generated; an optional zoom-out pulls the frame back by the chosen amount.
Flux Vision Upscaler for magnify/upscaling images with high fidelity and creativity.
Generate music from text prompts using the MiniMax Music 2.0 model, which leverages advanced AI techniques to create high-quality, diverse musical compositions.
Structured Prompt Generation endpoint for Fibo, Bria's SOTA Open source model.
Generate speech from text prompts and different voices using the MiniMax Speech-2.6 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.
Generate speech from text prompts and different voices using the MiniMax Speech-2.6 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.
SOTA open-source text-to-image model delivering high-fidelity outputs with accurate typography. JSON-structured prompts provide production-ready controllability for enterprise and agentic workflows. Trained…
SOTA stemming model for voice, drums, bass, guitar and more.
Video background removal version of bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS)
Meshy-6-Preview is the latest model from Meshy. It generates realistic and production ready 3D models.