Finetuned E5 embeddings for instruct based on Mistral.

Translate audio while keeping the original style, pronunciation and tone of your original audio.

Convert scanned or electronic documents to markdown, very very very fast

make meow emojis!

Best-in-class clothing virtual try on in the wild (non-commercial use only)

Llama-3-8B finetuned with ReFT to hyperfocus on New Jersey, the Garden State, the best state, the only state!

An example using Garden State Llama to ReFT on the Golden Gate bridge.

SDXL finetuned on line art

GLM-4V is a multimodal model released by Tsinghua University that is competitive with GPT-4o and establishes a new SOTA on several benchmarks, including OCR.

Embed text with Qwen2-7b-Instruct

Flux finetuned for black and white line art.

Generate high quality videos from a prompt

SOTA open-source model for chatting with videos and the newest model in the Qwen family

Microsoft's tool to convert Office documents, PDFs, images, audio, and more to LLM-ready markdown.

Zonos-v0.1 beta, a SOTA text-to-speech Transformer model with extraordinary expressive range, built by Zyphra.

TTS with the voice of Mel Medarda from Arcane, trained using Zonos-v0.1