Florence-2 WebGPU
Runs Microsoft's Florence-2 vision model in the browser for captioning, detection and OCR tasks.
Artifact by Xenova
Use it
Opens huggingface.co in a new tab. Nothing to install.
- You provide
- Image and task type
- You get
- Caption, boxes or text
- Account
- No sign-up needed
- AI
- AI-powered; no API key needed
- Your input
- Processed in your browser, not uploaded (stated by the tool or its repo)
- Price
- Free to use
- Made with
- Hugging Face Space
- Source
- Open source
About
Category: AI creative · vision tasks
Reviews
Write a reviewNo reviews yet. Used it? Sign in with an established GitHub account to rate it. How reviews work
More ai creative tools
- 0.822score
Inpaint-web
lxfater
Removes unwanted objects from a photo and upscales images using models that run in the browser.
ArtifactAINo sign-upIn-browser★ 6.1Kai creative - 0.809score
Web Stable Diffusion
MLC AI
Stable Diffusion that runs completely in the browser through WebGPU, with no server-side inference.
ArtifactAINo sign-upIn-browser★ 3.7Kai creative - 0.795score
MusicVAE (Magenta.js)
Magenta
Generates and interpolates between short melodies and drum patterns using a variational autoencoder in the browser.
ArtifactAINo sign-upIn-browser★ 2.1Kai creative - 0.795score
Piano Genie (Magenta.js)
Magenta
Play a few buttons and a neural net turns them into a full piano performance in your browser.
ArtifactAINo sign-upIn-browser★ 2.1Kai creative - 0.795score
Piano Transcription (Magenta.js)
Magenta
Transcribes piano audio into MIDI notes in the browser using the Onsets and Frames model.
ArtifactAINo sign-upIn-browser★ 2.1Kai creative - 0.790score
Omni Image Editor
selfit-camera
Browser image tool that edits pictures, generates images from text, upscales them and removes watermarks.
ArtifactAI★ 2.9Kai creative
Signals
- Hugging Face likes
- 95
From Hugging Face.
Details
- Auth
- No auth
- License
- Open source
- First seen
- Oct 31, 2026
- Last checked
- Oct 31, 2026
- Source
- Hugging Face
More from Xenova
- 0.760score
Whisper Web
Xenova
Transcribes or translates speech from an audio file, URL or microphone with Whisper running inside the browser tab.
ArtifactAINo sign-upIn-browser★ 1.3Kaudio video - 0.634score
Realtime Whisper WebGPU
Xenova
Streams live microphone audio through Whisper on the GPU in your browser and prints the words as you speak.
ArtifactAINo sign-upIn-browser★ 467audio video - 0.627score
Whisper Speaker Diarization
Xenova
Transcribes a recording in the browser and labels which speaker said each segment.
ArtifactAINo sign-upIn-browser★ 333audio video - 0.622score
Whisper WebGPU
Xenova
WebGPU-accelerated Whisper that turns microphone or file audio into text locally in the browser.
ArtifactAINo sign-upIn-browser★ 260audio video - 0.622score
Segment Anything Web
Xenova
Click on objects in an image to cut out segmentation masks using Segment Anything in the browser.
ArtifactAINo sign-up★ 281design media - 0.619score
Distil-Whisper Web
Xenova
Speech recognition with the smaller Distil-Whisper model, executed locally in the browser.
ArtifactAINo sign-upIn-browser★ 230audio video
Cite this page
Florence-2 WebGPU: free online tool. Agent Mart. https://agentmart.dev/artifacts/florence-2-webgpu (last updated 2026-10-31)