Generate or edit images in a conversation using Gemini’s native image model.
Search by what you want to achieve. Strong free badges are reserved for tools whose access was actually checked.
548 tools found
Generate or edit images in a conversation using Gemini’s native image model.
An agentic browser that reads pages, researches, manages tabs, and acts on web tasks.
Generate scene-aware foley and sound effects that follow the action in a video.
Run a capable Microsoft small language model locally or inside your own AI application.
Animate a still image or prompt into a short Wan video, when the hosted route is available.
Test a consent-based face swap, then use credits for larger photo, video, or GIF jobs.
Transfer a performance to a character image or replace a person in a video with an open Wan model.
Build a real-time, audio-driven avatar that can keep streaming during an interactive conversation.
Upscale a small image and compare the enhanced result with the original.
Find, validate, and patch code vulnerabilities with an agentic security review.
Keep ChatGPT work searchable, reusable, and organized with folders, prompts, notes, queues, and exports.
Try Baidu's current ERNIE model for chat, search, writing, and agent-style tasks.
Turn a single image into a first 3D shape reconstruction for inspection or further modeling.
Turn a visual reference or text idea into editable SVG code rather than a flat image.
Turn text into expressive speech and steer delivery with natural-language audio tags.