Everything in the catalog

Blends a QR code into AI-generated artwork from a text prompt, producing an image that still contains the code.

Imitates a target voice for voice conversion and text-to-speech, with control over how closely the voice is matched.

Free web security, SEO & AI-visibility (GEO) scan

Qwen-Image-2512 + LoRAs

Creates a short video from a starting image and a text prompt.

Machine translation across many languages with the Qwen3-MT model.

Converts text to speech with Microsoft Edge voices, with speech rate and pitch controls.

Calibrated yes/no, choice and score answers on images

Play expressive emotions on your robot.

Robot shames you for phone addiction with AI vision

Ontology·Graph·Decision engine with zero-token ZTC verify

Qwen 2.1 with multiple LoRAs

High-resolution 2K image editing with FireRed

Checks whether an image looks AI-generated or synthetic, free and without sign-up.

Try several small OCR vision-language models on the same image.

Describe a voice in words and have Qwen3-TTS speak your text in it.

All in One Banana for you!

Object Detection, Visual Grounding, Keypoint Detection

Explore RL environments, browse tasks and run agent rollouts

Reconstructs a 3D Gaussian splat scene from a single image.

Tags anime-style images with descriptive labels using PixAI Tagger v1.0.

Fast speech recognition with the Moonshine model.

Fast 4x upscaling of images and videos with GAN models.

Runs a fruit fly simulation in your browser using WebGPU.