Everything in the catalog

Classifies a message as negative, neutral or positive while the text stays encrypted.

Captions an image with Florence 2 and uses the caption to generate a FLUX image.

Chat with a gentleman who has read only 1800–1899 print

Exports a Hugging Face model to ONNX and opens a pull request with the result; needs login.

Restyles an interior photo into a new design look from a text prompt.

Creates a conversational podcast from text, URLs or PDFs; a Gemini key is required.

Whisper transcription compiled to WebAssembly with Rust Candle, running in the page.

Fetches a GitHub repository and merges its files into one text file for pasting into an LLM.

Generate video together with synchronized audio using a fast quantized MiniMax-H3 model.

Demo of a Collection of Impressive LoRAs for Z-Image-Turbo

Turns a clothing sketch into a rendered fashion design image.

Small vision-language model for describing images and video clips.

Creates new portrait images that keep the face identity of a reference photo, built on Kolors and Flux.

Speech recognition tool for uploaded or recorded audio in many languages.

Generates short videos together with a synchronized soundtrack, with LoRA options.

Compares transcripts and speed of Whisper and Distil-Whisper on the same audio.

Counts the number of tokens a piece of text uses with the Llama tokenizer.

Converts an uploaded PDF into Markdown text.

Demo of Circlestone Labs's new Anima V1 mode

Answers your questions about computer science papers on arXiv using a language model.

Karaoke and music-minus-one maker that isolates vocals and instruments from a song.

LLM: Finding the relevant Samplers and Template settings

Generates music from text prompts using version 1.5 of the ACE-Step music generation model.

Estimates whether a passage of text was written by an AI model.