WeesaGen

WeesaGen

A free collection of browser-native AI tools — my way of letting you experience as much of what AI has to offer as possible, without installing anything outside a web browser.

Every model runs locally, right on your own hardware — powered by WebGPU and CPU, with no downloads, no accounts, no servers, and no data ever leaving your machine. Open a page and AI is ready to go.

Generate images and music, chat with vision AI, turn text into speech and back, remove backgrounds, detect objects, and even transform a single photo into an explorable 3D scene — all for free, from any modern browser.

Created by MeesaJarJar · This is my website

Generative

FLUX.2 Image Generation

Turn text prompts into high-quality images. Choose from multiple speed profiles, control resolution and steps, do image-to-image edits, and generate with your webcam — all running on your GPU.

Gemma 4 Chat

Have a conversation with a multimodal AI that understands both text and images. Ask questions, brainstorm ideas, or get detailed analysis of any image you upload.

Book Builder

Type one story idea and get a complete illustrated children's book: local Gemma writes every page, FLUX.2 draws every picture. Pick age, art style and page size, then export a print-ready PDF.

3D / Vision

SHARP 3D Gaussian Splat

Upload a single photo and watch it transform into a full 3D scene you can orbit and explore. Uses AI to reconstruct depth and geometry from one image.

Segment Anything

Click on any object in an image to instantly cut it out from the background. Perfect for creating masks, isolating subjects, or preparing images for compositing.

Depth Anything V2

See how an AI perceives depth in any photo. Generates detailed depth maps and reconstructs a 3D view you can rotate — great for understanding scene geometry.

Audio

Kokoro TTS

Convert any text into natural-sounding speech. Choose from multiple voices and languages, load custom voice profiles, and download the generated audio.

Whisper STT

Transcribe audio files or record directly from your microphone. Supports multiple model sizes for different accuracy vs speed tradeoffs.

Vision

Background Removal

Strip the background from any image in one click. Get clean, transparent PNGs ready for social media, product photos, or design projects.

Florence-2

A versatile vision AI that can caption images, read text (OCR), detect objects, and locate specific phrases — all from a single upload.

SmolVLM Image Chat

Ask unlimited questions about any image in a chat interface. Get detailed descriptions, identify objects, read text, or analyze scenes conversationally.

Object Detection

Automatically find and label every object in a photo with bounding boxes. Recognizes 80 common categories like people, animals, vehicles, and furniture.

Upscaling

Blow up small or blurry images to 4× their original size while adding sharp, realistic detail. Supports transparent backgrounds and tiled processing for large images.